Last active
March 6, 2025 14:47
-
-
Save ysdede/da189c5239454de712c076d68f78f945 to your computer and use it in GitHub Desktop.
Phi-4-mm Trainable params
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Trainable parameters: 1,296,888,448 | |
| Unfrozen components: | |
| - model.embed_tokens_extend.audio_embed.encoder.embed.out.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.embed.out.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.embed.conv.0.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.embed.conv.0.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.embed.conv.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.embed.conv.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.embed.conv.3.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.embed.conv.3.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.embed.conv.5.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.embed.conv.5.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.embed.conv.6.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.embed.conv.6.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.relative_attention_bias_layer.bias_values.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.feed_forward_in.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.feed_forward_in.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.feed_forward_in.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.feed_forward_in.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.feed_forward_in.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.feed_forward_in.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.self_attn.linear_q.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.self_attn.linear_q.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.self_attn.linear_k.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.self_attn.linear_k.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.self_attn.linear_v.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.self_attn.linear_v.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.self_attn.linear_out.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.self_attn.linear_out.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.conv.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.conv.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.conv.glu.b1 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.conv.glu.b2 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.conv.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.conv.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.feed_forward_out.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.feed_forward_out.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.feed_forward_out.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.feed_forward_out.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.feed_forward_out.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.feed_forward_out.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.layer_norm_att.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.layer_norm_att.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.0._checkpoint_wrapped_module.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.feed_forward_in.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.feed_forward_in.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.feed_forward_in.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.feed_forward_in.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.feed_forward_in.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.feed_forward_in.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.self_attn.linear_q.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.self_attn.linear_q.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.self_attn.linear_k.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.self_attn.linear_k.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.self_attn.linear_v.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.self_attn.linear_v.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.self_attn.linear_out.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.self_attn.linear_out.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.conv.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.conv.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.conv.glu.b1 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.conv.glu.b2 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.conv.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.conv.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.feed_forward_out.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.feed_forward_out.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.feed_forward_out.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.feed_forward_out.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.feed_forward_out.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.feed_forward_out.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.layer_norm_att.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.layer_norm_att.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.1._checkpoint_wrapped_module.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.feed_forward_in.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.feed_forward_in.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.feed_forward_in.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.feed_forward_in.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.feed_forward_in.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.feed_forward_in.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.self_attn.linear_q.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.self_attn.linear_q.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.self_attn.linear_k.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.self_attn.linear_k.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.self_attn.linear_v.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.self_attn.linear_v.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.self_attn.linear_out.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.self_attn.linear_out.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.conv.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.conv.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.conv.glu.b1 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.conv.glu.b2 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.conv.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.conv.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.feed_forward_out.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.feed_forward_out.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.feed_forward_out.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.feed_forward_out.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.feed_forward_out.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.feed_forward_out.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.layer_norm_att.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.layer_norm_att.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.2._checkpoint_wrapped_module.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.feed_forward_in.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.feed_forward_in.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.feed_forward_in.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.feed_forward_in.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.feed_forward_in.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.feed_forward_in.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.self_attn.linear_q.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.self_attn.linear_q.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.self_attn.linear_k.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.self_attn.linear_k.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.self_attn.linear_v.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.self_attn.linear_v.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.self_attn.linear_out.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.self_attn.linear_out.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.conv.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.conv.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.conv.glu.b1 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.conv.glu.b2 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.conv.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.conv.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.feed_forward_out.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.feed_forward_out.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.feed_forward_out.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.feed_forward_out.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.feed_forward_out.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.feed_forward_out.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.layer_norm_att.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.layer_norm_att.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.3._checkpoint_wrapped_module.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.feed_forward_in.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.feed_forward_in.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.feed_forward_in.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.feed_forward_in.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.feed_forward_in.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.feed_forward_in.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.self_attn.linear_q.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.self_attn.linear_q.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.self_attn.linear_k.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.self_attn.linear_k.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.self_attn.linear_v.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.self_attn.linear_v.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.self_attn.linear_out.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.self_attn.linear_out.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.conv.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.conv.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.conv.glu.b1 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.conv.glu.b2 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.conv.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.conv.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.feed_forward_out.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.feed_forward_out.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.feed_forward_out.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.feed_forward_out.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.feed_forward_out.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.feed_forward_out.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.layer_norm_att.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.layer_norm_att.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.4._checkpoint_wrapped_module.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.feed_forward_in.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.feed_forward_in.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.feed_forward_in.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.feed_forward_in.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.feed_forward_in.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.feed_forward_in.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.self_attn.linear_q.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.self_attn.linear_q.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.self_attn.linear_k.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.self_attn.linear_k.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.self_attn.linear_v.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.self_attn.linear_v.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.self_attn.linear_out.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.self_attn.linear_out.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.conv.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.conv.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.conv.glu.b1 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.conv.glu.b2 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.conv.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.conv.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.feed_forward_out.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.feed_forward_out.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.feed_forward_out.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.feed_forward_out.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.feed_forward_out.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.feed_forward_out.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.layer_norm_att.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.layer_norm_att.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.5._checkpoint_wrapped_module.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.feed_forward_in.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.feed_forward_in.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.feed_forward_in.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.feed_forward_in.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.feed_forward_in.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.feed_forward_in.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.self_attn.linear_q.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.self_attn.linear_q.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.self_attn.linear_k.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.self_attn.linear_k.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.self_attn.linear_v.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.self_attn.linear_v.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.self_attn.linear_out.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.self_attn.linear_out.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.conv.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.conv.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.conv.glu.b1 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.conv.glu.b2 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.conv.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.conv.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.feed_forward_out.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.feed_forward_out.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.feed_forward_out.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.feed_forward_out.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.feed_forward_out.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.feed_forward_out.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.layer_norm_att.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.layer_norm_att.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.6._checkpoint_wrapped_module.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.feed_forward_in.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.feed_forward_in.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.feed_forward_in.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.feed_forward_in.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.feed_forward_in.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.feed_forward_in.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.self_attn.linear_q.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.self_attn.linear_q.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.self_attn.linear_k.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.self_attn.linear_k.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.self_attn.linear_v.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.self_attn.linear_v.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.self_attn.linear_out.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.self_attn.linear_out.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.conv.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.conv.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.conv.glu.b1 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.conv.glu.b2 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.conv.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.conv.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.feed_forward_out.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.feed_forward_out.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.feed_forward_out.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.feed_forward_out.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.feed_forward_out.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.feed_forward_out.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.layer_norm_att.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.layer_norm_att.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.7._checkpoint_wrapped_module.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.feed_forward_in.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.feed_forward_in.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.feed_forward_in.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.feed_forward_in.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.feed_forward_in.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.feed_forward_in.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.self_attn.linear_q.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.self_attn.linear_q.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.self_attn.linear_k.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.self_attn.linear_k.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.self_attn.linear_v.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.self_attn.linear_v.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.self_attn.linear_out.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.self_attn.linear_out.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.conv.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.conv.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.conv.glu.b1 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.conv.glu.b2 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.conv.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.conv.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.feed_forward_out.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.feed_forward_out.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.feed_forward_out.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.feed_forward_out.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.feed_forward_out.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.feed_forward_out.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.layer_norm_att.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.layer_norm_att.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.8._checkpoint_wrapped_module.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.feed_forward_in.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.feed_forward_in.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.feed_forward_in.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.feed_forward_in.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.feed_forward_in.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.feed_forward_in.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.self_attn.linear_q.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.self_attn.linear_q.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.self_attn.linear_k.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.self_attn.linear_k.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.self_attn.linear_v.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.self_attn.linear_v.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.self_attn.linear_out.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.self_attn.linear_out.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.conv.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.conv.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.conv.glu.b1 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.conv.glu.b2 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.conv.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.conv.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.feed_forward_out.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.feed_forward_out.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.feed_forward_out.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.feed_forward_out.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.feed_forward_out.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.feed_forward_out.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.layer_norm_att.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.layer_norm_att.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.9._checkpoint_wrapped_module.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.feed_forward_in.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.feed_forward_in.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.feed_forward_in.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.feed_forward_in.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.feed_forward_in.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.feed_forward_in.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.self_attn.linear_q.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.self_attn.linear_q.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.self_attn.linear_k.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.self_attn.linear_k.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.self_attn.linear_v.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.self_attn.linear_v.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.self_attn.linear_out.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.self_attn.linear_out.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.conv.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.conv.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.conv.glu.b1 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.conv.glu.b2 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.conv.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.conv.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.feed_forward_out.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.feed_forward_out.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.feed_forward_out.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.feed_forward_out.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.feed_forward_out.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.feed_forward_out.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.layer_norm_att.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.layer_norm_att.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.10._checkpoint_wrapped_module.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.feed_forward_in.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.feed_forward_in.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.feed_forward_in.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.feed_forward_in.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.feed_forward_in.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.feed_forward_in.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.self_attn.linear_q.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.self_attn.linear_q.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.self_attn.linear_k.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.self_attn.linear_k.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.self_attn.linear_v.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.self_attn.linear_v.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.self_attn.linear_out.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.self_attn.linear_out.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.conv.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.conv.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.conv.glu.b1 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.conv.glu.b2 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.conv.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.conv.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.feed_forward_out.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.feed_forward_out.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.feed_forward_out.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.feed_forward_out.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.feed_forward_out.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.feed_forward_out.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.layer_norm_att.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.layer_norm_att.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.11._checkpoint_wrapped_module.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.feed_forward_in.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.feed_forward_in.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.feed_forward_in.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.feed_forward_in.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.feed_forward_in.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.feed_forward_in.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.self_attn.linear_q.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.self_attn.linear_q.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.self_attn.linear_k.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.self_attn.linear_k.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.self_attn.linear_v.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.self_attn.linear_v.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.self_attn.linear_out.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.self_attn.linear_out.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.conv.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.conv.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.conv.glu.b1 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.conv.glu.b2 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.conv.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.conv.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.feed_forward_out.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.feed_forward_out.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.feed_forward_out.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.feed_forward_out.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.feed_forward_out.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.feed_forward_out.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.layer_norm_att.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.layer_norm_att.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.12._checkpoint_wrapped_module.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.feed_forward_in.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.feed_forward_in.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.feed_forward_in.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.feed_forward_in.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.feed_forward_in.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.feed_forward_in.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.self_attn.linear_q.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.self_attn.linear_q.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.self_attn.linear_k.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.self_attn.linear_k.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.self_attn.linear_v.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.self_attn.linear_v.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.self_attn.linear_out.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.self_attn.linear_out.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.conv.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.conv.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.conv.glu.b1 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.conv.glu.b2 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.conv.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.conv.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.feed_forward_out.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.feed_forward_out.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.feed_forward_out.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.feed_forward_out.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.feed_forward_out.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.feed_forward_out.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.layer_norm_att.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.layer_norm_att.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.13._checkpoint_wrapped_module.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.feed_forward_in.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.feed_forward_in.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.feed_forward_in.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.feed_forward_in.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.feed_forward_in.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.feed_forward_in.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.self_attn.linear_q.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.self_attn.linear_q.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.self_attn.linear_k.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.self_attn.linear_k.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.self_attn.linear_v.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.self_attn.linear_v.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.self_attn.linear_out.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.self_attn.linear_out.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.conv.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.conv.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.conv.glu.b1 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.conv.glu.b2 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.conv.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.conv.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.feed_forward_out.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.feed_forward_out.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.feed_forward_out.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.feed_forward_out.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.feed_forward_out.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.feed_forward_out.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.layer_norm_att.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.layer_norm_att.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.14._checkpoint_wrapped_module.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.feed_forward_in.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.feed_forward_in.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.feed_forward_in.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.feed_forward_in.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.feed_forward_in.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.feed_forward_in.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.self_attn.linear_q.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.self_attn.linear_q.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.self_attn.linear_k.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.self_attn.linear_k.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.self_attn.linear_v.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.self_attn.linear_v.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.self_attn.linear_out.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.self_attn.linear_out.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.conv.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.conv.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.conv.glu.b1 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.conv.glu.b2 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.conv.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.conv.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.feed_forward_out.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.feed_forward_out.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.feed_forward_out.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.feed_forward_out.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.feed_forward_out.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.feed_forward_out.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.layer_norm_att.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.layer_norm_att.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.15._checkpoint_wrapped_module.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.feed_forward_in.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.feed_forward_in.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.feed_forward_in.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.feed_forward_in.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.feed_forward_in.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.feed_forward_in.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.self_attn.linear_q.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.self_attn.linear_q.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.self_attn.linear_k.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.self_attn.linear_k.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.self_attn.linear_v.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.self_attn.linear_v.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.self_attn.linear_out.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.self_attn.linear_out.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.conv.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.conv.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.conv.glu.b1 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.conv.glu.b2 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.conv.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.conv.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.feed_forward_out.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.feed_forward_out.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.feed_forward_out.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.feed_forward_out.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.feed_forward_out.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.feed_forward_out.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.layer_norm_att.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.layer_norm_att.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.16._checkpoint_wrapped_module.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.feed_forward_in.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.feed_forward_in.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.feed_forward_in.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.feed_forward_in.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.feed_forward_in.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.feed_forward_in.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.self_attn.linear_q.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.self_attn.linear_q.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.self_attn.linear_k.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.self_attn.linear_k.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.self_attn.linear_v.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.self_attn.linear_v.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.self_attn.linear_out.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.self_attn.linear_out.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.conv.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.conv.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.conv.glu.b1 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.conv.glu.b2 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.conv.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.conv.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.feed_forward_out.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.feed_forward_out.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.feed_forward_out.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.feed_forward_out.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.feed_forward_out.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.feed_forward_out.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.layer_norm_att.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.layer_norm_att.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.17._checkpoint_wrapped_module.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.feed_forward_in.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.feed_forward_in.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.feed_forward_in.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.feed_forward_in.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.feed_forward_in.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.feed_forward_in.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.self_attn.linear_q.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.self_attn.linear_q.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.self_attn.linear_k.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.self_attn.linear_k.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.self_attn.linear_v.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.self_attn.linear_v.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.self_attn.linear_out.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.self_attn.linear_out.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.conv.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.conv.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.conv.glu.b1 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.conv.glu.b2 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.conv.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.conv.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.feed_forward_out.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.feed_forward_out.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.feed_forward_out.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.feed_forward_out.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.feed_forward_out.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.feed_forward_out.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.layer_norm_att.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.layer_norm_att.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.18._checkpoint_wrapped_module.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.feed_forward_in.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.feed_forward_in.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.feed_forward_in.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.feed_forward_in.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.feed_forward_in.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.feed_forward_in.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.self_attn.linear_q.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.self_attn.linear_q.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.self_attn.linear_k.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.self_attn.linear_k.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.self_attn.linear_v.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.self_attn.linear_v.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.self_attn.linear_out.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.self_attn.linear_out.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.conv.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.conv.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.conv.glu.b1 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.conv.glu.b2 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.conv.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.conv.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.feed_forward_out.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.feed_forward_out.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.feed_forward_out.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.feed_forward_out.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.feed_forward_out.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.feed_forward_out.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.layer_norm_att.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.layer_norm_att.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.19._checkpoint_wrapped_module.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.feed_forward_in.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.feed_forward_in.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.feed_forward_in.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.feed_forward_in.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.feed_forward_in.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.feed_forward_in.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.self_attn.linear_q.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.self_attn.linear_q.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.self_attn.linear_k.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.self_attn.linear_k.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.self_attn.linear_v.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.self_attn.linear_v.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.self_attn.linear_out.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.self_attn.linear_out.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.conv.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.conv.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.conv.glu.b1 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.conv.glu.b2 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.conv.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.conv.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.feed_forward_out.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.feed_forward_out.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.feed_forward_out.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.feed_forward_out.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.feed_forward_out.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.feed_forward_out.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.layer_norm_att.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.layer_norm_att.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.20._checkpoint_wrapped_module.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.feed_forward_in.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.feed_forward_in.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.feed_forward_in.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.feed_forward_in.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.feed_forward_in.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.feed_forward_in.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.self_attn.linear_q.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.self_attn.linear_q.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.self_attn.linear_k.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.self_attn.linear_k.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.self_attn.linear_v.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.self_attn.linear_v.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.self_attn.linear_out.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.self_attn.linear_out.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.conv.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.conv.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.conv.glu.b1 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.conv.glu.b2 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.conv.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.conv.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.feed_forward_out.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.feed_forward_out.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.feed_forward_out.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.feed_forward_out.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.feed_forward_out.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.feed_forward_out.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.layer_norm_att.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.layer_norm_att.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.21._checkpoint_wrapped_module.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.feed_forward_in.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.feed_forward_in.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.feed_forward_in.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.feed_forward_in.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.feed_forward_in.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.feed_forward_in.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.self_attn.linear_q.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.self_attn.linear_q.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.self_attn.linear_k.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.self_attn.linear_k.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.self_attn.linear_v.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.self_attn.linear_v.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.self_attn.linear_out.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.self_attn.linear_out.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.conv.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.conv.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.conv.glu.b1 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.conv.glu.b2 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.conv.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.conv.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.feed_forward_out.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.feed_forward_out.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.feed_forward_out.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.feed_forward_out.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.feed_forward_out.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.feed_forward_out.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.layer_norm_att.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.layer_norm_att.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.22._checkpoint_wrapped_module.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.feed_forward_in.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.feed_forward_in.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.feed_forward_in.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.feed_forward_in.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.feed_forward_in.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.feed_forward_in.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.self_attn.linear_q.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.self_attn.linear_q.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.self_attn.linear_k.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.self_attn.linear_k.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.self_attn.linear_v.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.self_attn.linear_v.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.self_attn.linear_out.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.self_attn.linear_out.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.conv.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.conv.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.conv.glu.b1 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.conv.glu.b2 | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.conv.glu.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.conv.ext_pw_conv_1d.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.conv.ext_pw_conv_1d.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.conv.dw_sep_conv_1d.dw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.conv.dw_sep_conv_1d.pw_conv.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.feed_forward_out.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.feed_forward_out.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.feed_forward_out.net.0.linear.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.feed_forward_out.net.0.linear.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.feed_forward_out.net.2.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.feed_forward_out.net.2.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.layer_norm_att.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.layer_norm_att.bias | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.layer_norm.weight | |
| - model.embed_tokens_extend.audio_embed.encoder.encoders.23._checkpoint_wrapped_module.layer_norm.bias | |
| - model.embed_tokens_extend.audio_embed.audio_projection.speech.0.weight | |
| - model.embed_tokens_extend.audio_embed.audio_projection.speech.0.bias | |
| - model.embed_tokens_extend.audio_embed.audio_projection.speech.2.weight | |
| - model.embed_tokens_extend.audio_embed.audio_projection.speech.2.bias | |
| - model.embed_tokens_extend.audio_embed.audio_projection.vision.0.weight | |
| - model.embed_tokens_extend.audio_embed.audio_projection.vision.0.bias | |
| - model.embed_tokens_extend.audio_embed.audio_projection.vision.2.weight | |
| - model.embed_tokens_extend.audio_embed.audio_projection.vision.2.bias | |
| - model.layers.0.self_attn.o_proj.lora_A.vision.weight | |
| - model.layers.0.self_attn.o_proj.lora_A.speech.weight | |
| - model.layers.0.self_attn.o_proj.lora_B.vision.weight | |
| - model.layers.0.self_attn.o_proj.lora_B.speech.weight | |
| - model.layers.0.self_attn.qkv_proj.lora_A.vision.weight | |
| - model.layers.0.self_attn.qkv_proj.lora_A.speech.weight | |
| - model.layers.0.self_attn.qkv_proj.lora_B.vision.weight | |
| - model.layers.0.self_attn.qkv_proj.lora_B.speech.weight | |
| - model.layers.0.mlp.gate_up_proj.lora_A.vision.weight | |
| - model.layers.0.mlp.gate_up_proj.lora_A.speech.weight | |
| - model.layers.0.mlp.gate_up_proj.lora_B.vision.weight | |
| - model.layers.0.mlp.gate_up_proj.lora_B.speech.weight | |
| - model.layers.0.mlp.down_proj.lora_A.vision.weight | |
| - model.layers.0.mlp.down_proj.lora_A.speech.weight | |
| - model.layers.0.mlp.down_proj.lora_B.vision.weight | |
| - model.layers.0.mlp.down_proj.lora_B.speech.weight | |
| - model.layers.1.self_attn.o_proj.lora_A.vision.weight | |
| - model.layers.1.self_attn.o_proj.lora_A.speech.weight | |
| - model.layers.1.self_attn.o_proj.lora_B.vision.weight | |
| - model.layers.1.self_attn.o_proj.lora_B.speech.weight | |
| - model.layers.1.self_attn.qkv_proj.lora_A.vision.weight | |
| - model.layers.1.self_attn.qkv_proj.lora_A.speech.weight | |
| - model.layers.1.self_attn.qkv_proj.lora_B.vision.weight | |
| - model.layers.1.self_attn.qkv_proj.lora_B.speech.weight | |
| - model.layers.1.mlp.gate_up_proj.lora_A.vision.weight | |
| - model.layers.1.mlp.gate_up_proj.lora_A.speech.weight | |
| - model.layers.1.mlp.gate_up_proj.lora_B.vision.weight | |
| - model.layers.1.mlp.gate_up_proj.lora_B.speech.weight | |
| - model.layers.1.mlp.down_proj.lora_A.vision.weight | |
| - model.layers.1.mlp.down_proj.lora_A.speech.weight | |
| - model.layers.1.mlp.down_proj.lora_B.vision.weight | |
| - model.layers.1.mlp.down_proj.lora_B.speech.weight | |
| - model.layers.2.self_attn.o_proj.lora_A.vision.weight | |
| - model.layers.2.self_attn.o_proj.lora_A.speech.weight | |
| - model.layers.2.self_attn.o_proj.lora_B.vision.weight | |
| - model.layers.2.self_attn.o_proj.lora_B.speech.weight | |
| - model.layers.2.self_attn.qkv_proj.lora_A.vision.weight | |
| - model.layers.2.self_attn.qkv_proj.lora_A.speech.weight | |
| - model.layers.2.self_attn.qkv_proj.lora_B.vision.weight | |
| - model.layers.2.self_attn.qkv_proj.lora_B.speech.weight | |
| - model.layers.2.mlp.gate_up_proj.lora_A.vision.weight | |
| - model.layers.2.mlp.gate_up_proj.lora_A.speech.weight | |
| - model.layers.2.mlp.gate_up_proj.lora_B.vision.weight | |
| - model.layers.2.mlp.gate_up_proj.lora_B.speech.weight | |
| - model.layers.2.mlp.down_proj.lora_A.vision.weight | |
| - model.layers.2.mlp.down_proj.lora_A.speech.weight | |
| - model.layers.2.mlp.down_proj.lora_B.vision.weight | |
| - model.layers.2.mlp.down_proj.lora_B.speech.weight | |
| - model.layers.3.self_attn.o_proj.lora_A.vision.weight | |
| - model.layers.3.self_attn.o_proj.lora_A.speech.weight | |
| - model.layers.3.self_attn.o_proj.lora_B.vision.weight | |
| - model.layers.3.self_attn.o_proj.lora_B.speech.weight | |
| - model.layers.3.self_attn.qkv_proj.lora_A.vision.weight | |
| - model.layers.3.self_attn.qkv_proj.lora_A.speech.weight | |
| - model.layers.3.self_attn.qkv_proj.lora_B.vision.weight | |
| - model.layers.3.self_attn.qkv_proj.lora_B.speech.weight | |
| - model.layers.3.mlp.gate_up_proj.lora_A.vision.weight | |
| - model.layers.3.mlp.gate_up_proj.lora_A.speech.weight | |
| - model.layers.3.mlp.gate_up_proj.lora_B.vision.weight | |
| - model.layers.3.mlp.gate_up_proj.lora_B.speech.weight | |
| - model.layers.3.mlp.down_proj.lora_A.vision.weight | |
| - model.layers.3.mlp.down_proj.lora_A.speech.weight | |
| - model.layers.3.mlp.down_proj.lora_B.vision.weight | |
| - model.layers.3.mlp.down_proj.lora_B.speech.weight | |
| - model.layers.4.self_attn.o_proj.lora_A.vision.weight | |
| - model.layers.4.self_attn.o_proj.lora_A.speech.weight | |
| - model.layers.4.self_attn.o_proj.lora_B.vision.weight | |
| - model.layers.4.self_attn.o_proj.lora_B.speech.weight | |
| - model.layers.4.self_attn.qkv_proj.lora_A.vision.weight | |
| - model.layers.4.self_attn.qkv_proj.lora_A.speech.weight | |
| - model.layers.4.self_attn.qkv_proj.lora_B.vision.weight | |
| - model.layers.4.self_attn.qkv_proj.lora_B.speech.weight | |
| - model.layers.4.mlp.gate_up_proj.lora_A.vision.weight | |
| - model.layers.4.mlp.gate_up_proj.lora_A.speech.weight | |
| - model.layers.4.mlp.gate_up_proj.lora_B.vision.weight | |
| - model.layers.4.mlp.gate_up_proj.lora_B.speech.weight | |
| - model.layers.4.mlp.down_proj.lora_A.vision.weight | |
| - model.layers.4.mlp.down_proj.lora_A.speech.weight | |
| - model.layers.4.mlp.down_proj.lora_B.vision.weight | |
| - model.layers.4.mlp.down_proj.lora_B.speech.weight | |
| - model.layers.5.self_attn.o_proj.lora_A.vision.weight | |
| - model.layers.5.self_attn.o_proj.lora_A.speech.weight | |
| - model.layers.5.self_attn.o_proj.lora_B.vision.weight | |
| - model.layers.5.self_attn.o_proj.lora_B.speech.weight | |
| - model.layers.5.self_attn.qkv_proj.lora_A.vision.weight | |
| - model.layers.5.self_attn.qkv_proj.lora_A.speech.weight | |
| - model.layers.5.self_attn.qkv_proj.lora_B.vision.weight | |
| - model.layers.5.self_attn.qkv_proj.lora_B.speech.weight | |
| - model.layers.5.mlp.gate_up_proj.lora_A.vision.weight | |
| - model.layers.5.mlp.gate_up_proj.lora_A.speech.weight | |
| - model.layers.5.mlp.gate_up_proj.lora_B.vision.weight | |
| - model.layers.5.mlp.gate_up_proj.lora_B.speech.weight | |
| - model.layers.5.mlp.down_proj.lora_A.vision.weight | |
| - model.layers.5.mlp.down_proj.lora_A.speech.weight | |
| - model.layers.5.mlp.down_proj.lora_B.vision.weight | |
| - model.layers.5.mlp.down_proj.lora_B.speech.weight | |
| - model.layers.6.self_attn.o_proj.lora_A.vision.weight | |
| - model.layers.6.self_attn.o_proj.lora_A.speech.weight | |
| - model.layers.6.self_attn.o_proj.lora_B.vision.weight | |
| - model.layers.6.self_attn.o_proj.lora_B.speech.weight | |
| - model.layers.6.self_attn.qkv_proj.lora_A.vision.weight | |
| - model.layers.6.self_attn.qkv_proj.lora_A.speech.weight | |
| - model.layers.6.self_attn.qkv_proj.lora_B.vision.weight | |
| - model.layers.6.self_attn.qkv_proj.lora_B.speech.weight | |
| - model.layers.6.mlp.gate_up_proj.lora_A.vision.weight | |
| - model.layers.6.mlp.gate_up_proj.lora_A.speech.weight | |
| - model.layers.6.mlp.gate_up_proj.lora_B.vision.weight | |
| - model.layers.6.mlp.gate_up_proj.lora_B.speech.weight | |
| - model.layers.6.mlp.down_proj.lora_A.vision.weight | |
| - model.layers.6.mlp.down_proj.lora_A.speech.weight | |
| - model.layers.6.mlp.down_proj.lora_B.vision.weight | |
| - model.layers.6.mlp.down_proj.lora_B.speech.weight | |
| - model.layers.7.self_attn.o_proj.lora_A.vision.weight | |
| - model.layers.7.self_attn.o_proj.lora_A.speech.weight | |
| - model.layers.7.self_attn.o_proj.lora_B.vision.weight | |
| - model.layers.7.self_attn.o_proj.lora_B.speech.weight | |
| - model.layers.7.self_attn.qkv_proj.lora_A.vision.weight | |
| - model.layers.7.self_attn.qkv_proj.lora_A.speech.weight | |
| - model.layers.7.self_attn.qkv_proj.lora_B.vision.weight | |
| - model.layers.7.self_attn.qkv_proj.lora_B.speech.weight | |
| - model.layers.7.mlp.gate_up_proj.lora_A.vision.weight | |
| - model.layers.7.mlp.gate_up_proj.lora_A.speech.weight | |
| - model.layers.7.mlp.gate_up_proj.lora_B.vision.weight | |
| - model.layers.7.mlp.gate_up_proj.lora_B.speech.weight | |
| - model.layers.7.mlp.down_proj.lora_A.vision.weight | |
| - model.layers.7.mlp.down_proj.lora_A.speech.weight | |
| - model.layers.7.mlp.down_proj.lora_B.vision.weight | |
| - model.layers.7.mlp.down_proj.lora_B.speech.weight | |
| - model.layers.8.self_attn.o_proj.lora_A.vision.weight | |
| - model.layers.8.self_attn.o_proj.lora_A.speech.weight | |
| - model.layers.8.self_attn.o_proj.lora_B.vision.weight | |
| - model.layers.8.self_attn.o_proj.lora_B.speech.weight | |
| - model.layers.8.self_attn.qkv_proj.lora_A.vision.weight | |
| - model.layers.8.self_attn.qkv_proj.lora_A.speech.weight | |
| - model.layers.8.self_attn.qkv_proj.lora_B.vision.weight | |
| - model.layers.8.self_attn.qkv_proj.lora_B.speech.weight | |
| - model.layers.8.mlp.gate_up_proj.lora_A.vision.weight | |
| - model.layers.8.mlp.gate_up_proj.lora_A.speech.weight | |
| - model.layers.8.mlp.gate_up_proj.lora_B.vision.weight | |
| - model.layers.8.mlp.gate_up_proj.lora_B.speech.weight | |
| - model.layers.8.mlp.down_proj.lora_A.vision.weight | |
| - model.layers.8.mlp.down_proj.lora_A.speech.weight | |
| - model.layers.8.mlp.down_proj.lora_B.vision.weight | |
| - model.layers.8.mlp.down_proj.lora_B.speech.weight | |
| - model.layers.9.self_attn.o_proj.lora_A.vision.weight | |
| - model.layers.9.self_attn.o_proj.lora_A.speech.weight | |
| - model.layers.9.self_attn.o_proj.lora_B.vision.weight | |
| - model.layers.9.self_attn.o_proj.lora_B.speech.weight | |
| - model.layers.9.self_attn.qkv_proj.lora_A.vision.weight | |
| - model.layers.9.self_attn.qkv_proj.lora_A.speech.weight | |
| - model.layers.9.self_attn.qkv_proj.lora_B.vision.weight | |
| - model.layers.9.self_attn.qkv_proj.lora_B.speech.weight | |
| - model.layers.9.mlp.gate_up_proj.lora_A.vision.weight | |
| - model.layers.9.mlp.gate_up_proj.lora_A.speech.weight | |
| - model.layers.9.mlp.gate_up_proj.lora_B.vision.weight | |
| - model.layers.9.mlp.gate_up_proj.lora_B.speech.weight | |
| - model.layers.9.mlp.down_proj.lora_A.vision.weight | |
| - model.layers.9.mlp.down_proj.lora_A.speech.weight | |
| - model.layers.9.mlp.down_proj.lora_B.vision.weight | |
| - model.layers.9.mlp.down_proj.lora_B.speech.weight | |
| - model.layers.10.self_attn.o_proj.lora_A.vision.weight | |
| - model.layers.10.self_attn.o_proj.lora_A.speech.weight | |
| - model.layers.10.self_attn.o_proj.lora_B.vision.weight | |
| - model.layers.10.self_attn.o_proj.lora_B.speech.weight | |
| - model.layers.10.self_attn.qkv_proj.lora_A.vision.weight | |
| - model.layers.10.self_attn.qkv_proj.lora_A.speech.weight | |
| - model.layers.10.self_attn.qkv_proj.lora_B.vision.weight | |
| - model.layers.10.self_attn.qkv_proj.lora_B.speech.weight | |
| - model.layers.10.mlp.gate_up_proj.lora_A.vision.weight | |
| - model.layers.10.mlp.gate_up_proj.lora_A.speech.weight | |
| - model.layers.10.mlp.gate_up_proj.lora_B.vision.weight | |
| - model.layers.10.mlp.gate_up_proj.lora_B.speech.weight | |
| - model.layers.10.mlp.down_proj.lora_A.vision.weight | |
| - model.layers.10.mlp.down_proj.lora_A.speech.weight | |
| - model.layers.10.mlp.down_proj.lora_B.vision.weight | |
| - model.layers.10.mlp.down_proj.lora_B.speech.weight | |
| - model.layers.11.self_attn.o_proj.lora_A.vision.weight | |
| - model.layers.11.self_attn.o_proj.lora_A.speech.weight | |
| - model.layers.11.self_attn.o_proj.lora_B.vision.weight | |
| - model.layers.11.self_attn.o_proj.lora_B.speech.weight | |
| - model.layers.11.self_attn.qkv_proj.lora_A.vision.weight | |
| - model.layers.11.self_attn.qkv_proj.lora_A.speech.weight | |
| - model.layers.11.self_attn.qkv_proj.lora_B.vision.weight | |
| - model.layers.11.self_attn.qkv_proj.lora_B.speech.weight | |
| - model.layers.11.mlp.gate_up_proj.lora_A.vision.weight | |
| - model.layers.11.mlp.gate_up_proj.lora_A.speech.weight | |
| - model.layers.11.mlp.gate_up_proj.lora_B.vision.weight | |
| - model.layers.11.mlp.gate_up_proj.lora_B.speech.weight | |
| - model.layers.11.mlp.down_proj.lora_A.vision.weight | |
| - model.layers.11.mlp.down_proj.lora_A.speech.weight | |
| - model.layers.11.mlp.down_proj.lora_B.vision.weight | |
| - model.layers.11.mlp.down_proj.lora_B.speech.weight | |
| - model.layers.12.self_attn.o_proj.lora_A.vision.weight | |
| - model.layers.12.self_attn.o_proj.lora_A.speech.weight | |
| - model.layers.12.self_attn.o_proj.lora_B.vision.weight | |
| - model.layers.12.self_attn.o_proj.lora_B.speech.weight | |
| - model.layers.12.self_attn.qkv_proj.lora_A.vision.weight | |
| - model.layers.12.self_attn.qkv_proj.lora_A.speech.weight | |
| - model.layers.12.self_attn.qkv_proj.lora_B.vision.weight | |
| - model.layers.12.self_attn.qkv_proj.lora_B.speech.weight | |
| - model.layers.12.mlp.gate_up_proj.lora_A.vision.weight | |
| - model.layers.12.mlp.gate_up_proj.lora_A.speech.weight | |
| - model.layers.12.mlp.gate_up_proj.lora_B.vision.weight | |
| - model.layers.12.mlp.gate_up_proj.lora_B.speech.weight | |
| - model.layers.12.mlp.down_proj.lora_A.vision.weight | |
| - model.layers.12.mlp.down_proj.lora_A.speech.weight | |
| - model.layers.12.mlp.down_proj.lora_B.vision.weight | |
| - model.layers.12.mlp.down_proj.lora_B.speech.weight | |
| - model.layers.13.self_attn.o_proj.lora_A.vision.weight | |
| - model.layers.13.self_attn.o_proj.lora_A.speech.weight | |
| - model.layers.13.self_attn.o_proj.lora_B.vision.weight | |
| - model.layers.13.self_attn.o_proj.lora_B.speech.weight | |
| - model.layers.13.self_attn.qkv_proj.lora_A.vision.weight | |
| - model.layers.13.self_attn.qkv_proj.lora_A.speech.weight | |
| - model.layers.13.self_attn.qkv_proj.lora_B.vision.weight | |
| - model.layers.13.self_attn.qkv_proj.lora_B.speech.weight | |
| - model.layers.13.mlp.gate_up_proj.lora_A.vision.weight | |
| - model.layers.13.mlp.gate_up_proj.lora_A.speech.weight | |
| - model.layers.13.mlp.gate_up_proj.lora_B.vision.weight | |
| - model.layers.13.mlp.gate_up_proj.lora_B.speech.weight | |
| - model.layers.13.mlp.down_proj.lora_A.vision.weight | |
| - model.layers.13.mlp.down_proj.lora_A.speech.weight | |
| - model.layers.13.mlp.down_proj.lora_B.vision.weight | |
| - model.layers.13.mlp.down_proj.lora_B.speech.weight | |
| - model.layers.14.self_attn.o_proj.lora_A.vision.weight | |
| - model.layers.14.self_attn.o_proj.lora_A.speech.weight | |
| - model.layers.14.self_attn.o_proj.lora_B.vision.weight | |
| - model.layers.14.self_attn.o_proj.lora_B.speech.weight | |
| - model.layers.14.self_attn.qkv_proj.lora_A.vision.weight | |
| - model.layers.14.self_attn.qkv_proj.lora_A.speech.weight | |
| - model.layers.14.self_attn.qkv_proj.lora_B.vision.weight | |
| - model.layers.14.self_attn.qkv_proj.lora_B.speech.weight | |
| - model.layers.14.mlp.gate_up_proj.lora_A.vision.weight | |
| - model.layers.14.mlp.gate_up_proj.lora_A.speech.weight | |
| - model.layers.14.mlp.gate_up_proj.lora_B.vision.weight | |
| - model.layers.14.mlp.gate_up_proj.lora_B.speech.weight | |
| - model.layers.14.mlp.down_proj.lora_A.vision.weight | |
| - model.layers.14.mlp.down_proj.lora_A.speech.weight | |
| - model.layers.14.mlp.down_proj.lora_B.vision.weight | |
| - model.layers.14.mlp.down_proj.lora_B.speech.weight | |
| - model.layers.15.self_attn.o_proj.lora_A.vision.weight | |
| - model.layers.15.self_attn.o_proj.lora_A.speech.weight | |
| - model.layers.15.self_attn.o_proj.lora_B.vision.weight | |
| - model.layers.15.self_attn.o_proj.lora_B.speech.weight | |
| - model.layers.15.self_attn.qkv_proj.lora_A.vision.weight | |
| - model.layers.15.self_attn.qkv_proj.lora_A.speech.weight | |
| - model.layers.15.self_attn.qkv_proj.lora_B.vision.weight | |
| - model.layers.15.self_attn.qkv_proj.lora_B.speech.weight | |
| - model.layers.15.mlp.gate_up_proj.lora_A.vision.weight | |
| - model.layers.15.mlp.gate_up_proj.lora_A.speech.weight | |
| - model.layers.15.mlp.gate_up_proj.lora_B.vision.weight | |
| - model.layers.15.mlp.gate_up_proj.lora_B.speech.weight | |
| - model.layers.15.mlp.down_proj.lora_A.vision.weight | |
| - model.layers.15.mlp.down_proj.lora_A.speech.weight | |
| - model.layers.15.mlp.down_proj.lora_B.vision.weight | |
| - model.layers.15.mlp.down_proj.lora_B.speech.weight | |
| - model.layers.16.self_attn.o_proj.lora_A.vision.weight | |
| - model.layers.16.self_attn.o_proj.lora_A.speech.weight | |
| - model.layers.16.self_attn.o_proj.lora_B.vision.weight | |
| - model.layers.16.self_attn.o_proj.lora_B.speech.weight | |
| - model.layers.16.self_attn.qkv_proj.lora_A.vision.weight | |
| - model.layers.16.self_attn.qkv_proj.lora_A.speech.weight | |
| - model.layers.16.self_attn.qkv_proj.lora_B.vision.weight | |
| - model.layers.16.self_attn.qkv_proj.lora_B.speech.weight | |
| - model.layers.16.mlp.gate_up_proj.lora_A.vision.weight | |
| - model.layers.16.mlp.gate_up_proj.lora_A.speech.weight | |
| - model.layers.16.mlp.gate_up_proj.lora_B.vision.weight | |
| - model.layers.16.mlp.gate_up_proj.lora_B.speech.weight | |
| - model.layers.16.mlp.down_proj.lora_A.vision.weight | |
| - model.layers.16.mlp.down_proj.lora_A.speech.weight | |
| - model.layers.16.mlp.down_proj.lora_B.vision.weight | |
| - model.layers.16.mlp.down_proj.lora_B.speech.weight | |
| - model.layers.17.self_attn.o_proj.lora_A.vision.weight | |
| - model.layers.17.self_attn.o_proj.lora_A.speech.weight | |
| - model.layers.17.self_attn.o_proj.lora_B.vision.weight | |
| - model.layers.17.self_attn.o_proj.lora_B.speech.weight | |
| - model.layers.17.self_attn.qkv_proj.lora_A.vision.weight | |
| - model.layers.17.self_attn.qkv_proj.lora_A.speech.weight | |
| - model.layers.17.self_attn.qkv_proj.lora_B.vision.weight | |
| - model.layers.17.self_attn.qkv_proj.lora_B.speech.weight | |
| - model.layers.17.mlp.gate_up_proj.lora_A.vision.weight | |
| - model.layers.17.mlp.gate_up_proj.lora_A.speech.weight | |
| - model.layers.17.mlp.gate_up_proj.lora_B.vision.weight | |
| - model.layers.17.mlp.gate_up_proj.lora_B.speech.weight | |
| - model.layers.17.mlp.down_proj.lora_A.vision.weight | |
| - model.layers.17.mlp.down_proj.lora_A.speech.weight | |
| - model.layers.17.mlp.down_proj.lora_B.vision.weight | |
| - model.layers.17.mlp.down_proj.lora_B.speech.weight | |
| - model.layers.18.self_attn.o_proj.lora_A.vision.weight | |
| - model.layers.18.self_attn.o_proj.lora_A.speech.weight | |
| - model.layers.18.self_attn.o_proj.lora_B.vision.weight | |
| - model.layers.18.self_attn.o_proj.lora_B.speech.weight | |
| - model.layers.18.self_attn.qkv_proj.lora_A.vision.weight | |
| - model.layers.18.self_attn.qkv_proj.lora_A.speech.weight | |
| - model.layers.18.self_attn.qkv_proj.lora_B.vision.weight | |
| - model.layers.18.self_attn.qkv_proj.lora_B.speech.weight | |
| - model.layers.18.mlp.gate_up_proj.lora_A.vision.weight | |
| - model.layers.18.mlp.gate_up_proj.lora_A.speech.weight | |
| - model.layers.18.mlp.gate_up_proj.lora_B.vision.weight | |
| - model.layers.18.mlp.gate_up_proj.lora_B.speech.weight | |
| - model.layers.18.mlp.down_proj.lora_A.vision.weight | |
| - model.layers.18.mlp.down_proj.lora_A.speech.weight | |
| - model.layers.18.mlp.down_proj.lora_B.vision.weight | |
| - model.layers.18.mlp.down_proj.lora_B.speech.weight | |
| - model.layers.19.self_attn.o_proj.lora_A.vision.weight | |
| - model.layers.19.self_attn.o_proj.lora_A.speech.weight | |
| - model.layers.19.self_attn.o_proj.lora_B.vision.weight | |
| - model.layers.19.self_attn.o_proj.lora_B.speech.weight | |
| - model.layers.19.self_attn.qkv_proj.lora_A.vision.weight | |
| - model.layers.19.self_attn.qkv_proj.lora_A.speech.weight | |
| - model.layers.19.self_attn.qkv_proj.lora_B.vision.weight | |
| - model.layers.19.self_attn.qkv_proj.lora_B.speech.weight | |
| - model.layers.19.mlp.gate_up_proj.lora_A.vision.weight | |
| - model.layers.19.mlp.gate_up_proj.lora_A.speech.weight | |
| - model.layers.19.mlp.gate_up_proj.lora_B.vision.weight | |
| - model.layers.19.mlp.gate_up_proj.lora_B.speech.weight | |
| - model.layers.19.mlp.down_proj.lora_A.vision.weight | |
| - model.layers.19.mlp.down_proj.lora_A.speech.weight | |
| - model.layers.19.mlp.down_proj.lora_B.vision.weight | |
| - model.layers.19.mlp.down_proj.lora_B.speech.weight | |
| - model.layers.20.self_attn.o_proj.lora_A.vision.weight | |
| - model.layers.20.self_attn.o_proj.lora_A.speech.weight | |
| - model.layers.20.self_attn.o_proj.lora_B.vision.weight | |
| - model.layers.20.self_attn.o_proj.lora_B.speech.weight | |
| - model.layers.20.self_attn.qkv_proj.lora_A.vision.weight | |
| - model.layers.20.self_attn.qkv_proj.lora_A.speech.weight | |
| - model.layers.20.self_attn.qkv_proj.lora_B.vision.weight | |
| - model.layers.20.self_attn.qkv_proj.lora_B.speech.weight | |
| - model.layers.20.mlp.gate_up_proj.lora_A.vision.weight | |
| - model.layers.20.mlp.gate_up_proj.lora_A.speech.weight | |
| - model.layers.20.mlp.gate_up_proj.lora_B.vision.weight | |
| - model.layers.20.mlp.gate_up_proj.lora_B.speech.weight | |
| - model.layers.20.mlp.down_proj.lora_A.vision.weight | |
| - model.layers.20.mlp.down_proj.lora_A.speech.weight | |
| - model.layers.20.mlp.down_proj.lora_B.vision.weight | |
| - model.layers.20.mlp.down_proj.lora_B.speech.weight | |
| - model.layers.21.self_attn.o_proj.lora_A.vision.weight | |
| - model.layers.21.self_attn.o_proj.lora_A.speech.weight | |
| - model.layers.21.self_attn.o_proj.lora_B.vision.weight | |
| - model.layers.21.self_attn.o_proj.lora_B.speech.weight | |
| - model.layers.21.self_attn.qkv_proj.lora_A.vision.weight | |
| - model.layers.21.self_attn.qkv_proj.lora_A.speech.weight | |
| - model.layers.21.self_attn.qkv_proj.lora_B.vision.weight | |
| - model.layers.21.self_attn.qkv_proj.lora_B.speech.weight | |
| - model.layers.21.mlp.gate_up_proj.lora_A.vision.weight | |
| - model.layers.21.mlp.gate_up_proj.lora_A.speech.weight | |
| - model.layers.21.mlp.gate_up_proj.lora_B.vision.weight | |
| - model.layers.21.mlp.gate_up_proj.lora_B.speech.weight | |
| - model.layers.21.mlp.down_proj.lora_A.vision.weight | |
| - model.layers.21.mlp.down_proj.lora_A.speech.weight | |
| - model.layers.21.mlp.down_proj.lora_B.vision.weight | |
| - model.layers.21.mlp.down_proj.lora_B.speech.weight | |
| - model.layers.22.self_attn.o_proj.lora_A.vision.weight | |
| - model.layers.22.self_attn.o_proj.lora_A.speech.weight | |
| - model.layers.22.self_attn.o_proj.lora_B.vision.weight | |
| - model.layers.22.self_attn.o_proj.lora_B.speech.weight | |
| - model.layers.22.self_attn.qkv_proj.lora_A.vision.weight | |
| - model.layers.22.self_attn.qkv_proj.lora_A.speech.weight | |
| - model.layers.22.self_attn.qkv_proj.lora_B.vision.weight | |
| - model.layers.22.self_attn.qkv_proj.lora_B.speech.weight | |
| - model.layers.22.mlp.gate_up_proj.lora_A.vision.weight | |
| - model.layers.22.mlp.gate_up_proj.lora_A.speech.weight | |
| - model.layers.22.mlp.gate_up_proj.lora_B.vision.weight | |
| - model.layers.22.mlp.gate_up_proj.lora_B.speech.weight | |
| - model.layers.22.mlp.down_proj.lora_A.vision.weight | |
| - model.layers.22.mlp.down_proj.lora_A.speech.weight | |
| - model.layers.22.mlp.down_proj.lora_B.vision.weight | |
| - model.layers.22.mlp.down_proj.lora_B.speech.weight | |
| - model.layers.23.self_attn.o_proj.lora_A.vision.weight | |
| - model.layers.23.self_attn.o_proj.lora_A.speech.weight | |
| - model.layers.23.self_attn.o_proj.lora_B.vision.weight | |
| - model.layers.23.self_attn.o_proj.lora_B.speech.weight | |
| - model.layers.23.self_attn.qkv_proj.lora_A.vision.weight | |
| - model.layers.23.self_attn.qkv_proj.lora_A.speech.weight | |
| - model.layers.23.self_attn.qkv_proj.lora_B.vision.weight | |
| - model.layers.23.self_attn.qkv_proj.lora_B.speech.weight | |
| - model.layers.23.mlp.gate_up_proj.lora_A.vision.weight | |
| - model.layers.23.mlp.gate_up_proj.lora_A.speech.weight | |
| - model.layers.23.mlp.gate_up_proj.lora_B.vision.weight | |
| - model.layers.23.mlp.gate_up_proj.lora_B.speech.weight | |
| - model.layers.23.mlp.down_proj.lora_A.vision.weight | |
| - model.layers.23.mlp.down_proj.lora_A.speech.weight | |
| - model.layers.23.mlp.down_proj.lora_B.vision.weight | |
| - model.layers.23.mlp.down_proj.lora_B.speech.weight | |
| - model.layers.24.self_attn.o_proj.lora_A.vision.weight | |
| - model.layers.24.self_attn.o_proj.lora_A.speech.weight | |
| - model.layers.24.self_attn.o_proj.lora_B.vision.weight | |
| - model.layers.24.self_attn.o_proj.lora_B.speech.weight | |
| - model.layers.24.self_attn.qkv_proj.lora_A.vision.weight | |
| - model.layers.24.self_attn.qkv_proj.lora_A.speech.weight | |
| - model.layers.24.self_attn.qkv_proj.lora_B.vision.weight | |
| - model.layers.24.self_attn.qkv_proj.lora_B.speech.weight | |
| - model.layers.24.mlp.gate_up_proj.lora_A.vision.weight | |
| - model.layers.24.mlp.gate_up_proj.lora_A.speech.weight | |
| - model.layers.24.mlp.gate_up_proj.lora_B.vision.weight | |
| - model.layers.24.mlp.gate_up_proj.lora_B.speech.weight | |
| - model.layers.24.mlp.down_proj.lora_A.vision.weight | |
| - model.layers.24.mlp.down_proj.lora_A.speech.weight | |
| - model.layers.24.mlp.down_proj.lora_B.vision.weight | |
| - model.layers.24.mlp.down_proj.lora_B.speech.weight | |
| - model.layers.25.self_attn.o_proj.lora_A.vision.weight | |
| - model.layers.25.self_attn.o_proj.lora_A.speech.weight | |
| - model.layers.25.self_attn.o_proj.lora_B.vision.weight | |
| - model.layers.25.self_attn.o_proj.lora_B.speech.weight | |
| - model.layers.25.self_attn.qkv_proj.lora_A.vision.weight | |
| - model.layers.25.self_attn.qkv_proj.lora_A.speech.weight | |
| - model.layers.25.self_attn.qkv_proj.lora_B.vision.weight | |
| - model.layers.25.self_attn.qkv_proj.lora_B.speech.weight | |
| - model.layers.25.mlp.gate_up_proj.lora_A.vision.weight | |
| - model.layers.25.mlp.gate_up_proj.lora_A.speech.weight | |
| - model.layers.25.mlp.gate_up_proj.lora_B.vision.weight | |
| - model.layers.25.mlp.gate_up_proj.lora_B.speech.weight | |
| - model.layers.25.mlp.down_proj.lora_A.vision.weight | |
| - model.layers.25.mlp.down_proj.lora_A.speech.weight | |
| - model.layers.25.mlp.down_proj.lora_B.vision.weight | |
| - model.layers.25.mlp.down_proj.lora_B.speech.weight | |
| - model.layers.26.self_attn.o_proj.lora_A.vision.weight | |
| - model.layers.26.self_attn.o_proj.lora_A.speech.weight | |
| - model.layers.26.self_attn.o_proj.lora_B.vision.weight | |
| - model.layers.26.self_attn.o_proj.lora_B.speech.weight | |
| - model.layers.26.self_attn.qkv_proj.lora_A.vision.weight | |
| - model.layers.26.self_attn.qkv_proj.lora_A.speech.weight | |
| - model.layers.26.self_attn.qkv_proj.lora_B.vision.weight | |
| - model.layers.26.self_attn.qkv_proj.lora_B.speech.weight | |
| - model.layers.26.mlp.gate_up_proj.lora_A.vision.weight | |
| - model.layers.26.mlp.gate_up_proj.lora_A.speech.weight | |
| - model.layers.26.mlp.gate_up_proj.lora_B.vision.weight | |
| - model.layers.26.mlp.gate_up_proj.lora_B.speech.weight | |
| - model.layers.26.mlp.down_proj.lora_A.vision.weight | |
| - model.layers.26.mlp.down_proj.lora_A.speech.weight | |
| - model.layers.26.mlp.down_proj.lora_B.vision.weight | |
| - model.layers.26.mlp.down_proj.lora_B.speech.weight | |
| - model.layers.27.self_attn.o_proj.lora_A.vision.weight | |
| - model.layers.27.self_attn.o_proj.lora_A.speech.weight | |
| - model.layers.27.self_attn.o_proj.lora_B.vision.weight | |
| - model.layers.27.self_attn.o_proj.lora_B.speech.weight | |
| - model.layers.27.self_attn.qkv_proj.lora_A.vision.weight | |
| - model.layers.27.self_attn.qkv_proj.lora_A.speech.weight | |
| - model.layers.27.self_attn.qkv_proj.lora_B.vision.weight | |
| - model.layers.27.self_attn.qkv_proj.lora_B.speech.weight | |
| - model.layers.27.mlp.gate_up_proj.lora_A.vision.weight | |
| - model.layers.27.mlp.gate_up_proj.lora_A.speech.weight | |
| - model.layers.27.mlp.gate_up_proj.lora_B.vision.weight | |
| - model.layers.27.mlp.gate_up_proj.lora_B.speech.weight | |
| - model.layers.27.mlp.down_proj.lora_A.vision.weight | |
| - model.layers.27.mlp.down_proj.lora_A.speech.weight | |
| - model.layers.27.mlp.down_proj.lora_B.vision.weight | |
| - model.layers.27.mlp.down_proj.lora_B.speech.weight | |
| - model.layers.28.self_attn.o_proj.lora_A.vision.weight | |
| - model.layers.28.self_attn.o_proj.lora_A.speech.weight | |
| - model.layers.28.self_attn.o_proj.lora_B.vision.weight | |
| - model.layers.28.self_attn.o_proj.lora_B.speech.weight | |
| - model.layers.28.self_attn.qkv_proj.lora_A.vision.weight | |
| - model.layers.28.self_attn.qkv_proj.lora_A.speech.weight | |
| - model.layers.28.self_attn.qkv_proj.lora_B.vision.weight | |
| - model.layers.28.self_attn.qkv_proj.lora_B.speech.weight | |
| - model.layers.28.mlp.gate_up_proj.lora_A.vision.weight | |
| - model.layers.28.mlp.gate_up_proj.lora_A.speech.weight | |
| - model.layers.28.mlp.gate_up_proj.lora_B.vision.weight | |
| - model.layers.28.mlp.gate_up_proj.lora_B.speech.weight | |
| - model.layers.28.mlp.down_proj.lora_A.vision.weight | |
| - model.layers.28.mlp.down_proj.lora_A.speech.weight | |
| - model.layers.28.mlp.down_proj.lora_B.vision.weight | |
| - model.layers.28.mlp.down_proj.lora_B.speech.weight | |
| - model.layers.29.self_attn.o_proj.lora_A.vision.weight | |
| - model.layers.29.self_attn.o_proj.lora_A.speech.weight | |
| - model.layers.29.self_attn.o_proj.lora_B.vision.weight | |
| - model.layers.29.self_attn.o_proj.lora_B.speech.weight | |
| - model.layers.29.self_attn.qkv_proj.lora_A.vision.weight | |
| - model.layers.29.self_attn.qkv_proj.lora_A.speech.weight | |
| - model.layers.29.self_attn.qkv_proj.lora_B.vision.weight | |
| - model.layers.29.self_attn.qkv_proj.lora_B.speech.weight | |
| - model.layers.29.mlp.gate_up_proj.lora_A.vision.weight | |
| - model.layers.29.mlp.gate_up_proj.lora_A.speech.weight | |
| - model.layers.29.mlp.gate_up_proj.lora_B.vision.weight | |
| - model.layers.29.mlp.gate_up_proj.lora_B.speech.weight | |
| - model.layers.29.mlp.down_proj.lora_A.vision.weight | |
| - model.layers.29.mlp.down_proj.lora_A.speech.weight | |
| - model.layers.29.mlp.down_proj.lora_B.vision.weight | |
| - model.layers.29.mlp.down_proj.lora_B.speech.weight | |
| - model.layers.30.self_attn.o_proj.lora_A.vision.weight | |
| - model.layers.30.self_attn.o_proj.lora_A.speech.weight | |
| - model.layers.30.self_attn.o_proj.lora_B.vision.weight | |
| - model.layers.30.self_attn.o_proj.lora_B.speech.weight | |
| - model.layers.30.self_attn.qkv_proj.lora_A.vision.weight | |
| - model.layers.30.self_attn.qkv_proj.lora_A.speech.weight | |
| - model.layers.30.self_attn.qkv_proj.lora_B.vision.weight | |
| - model.layers.30.self_attn.qkv_proj.lora_B.speech.weight | |
| - model.layers.30.mlp.gate_up_proj.lora_A.vision.weight | |
| - model.layers.30.mlp.gate_up_proj.lora_A.speech.weight | |
| - model.layers.30.mlp.gate_up_proj.lora_B.vision.weight | |
| - model.layers.30.mlp.gate_up_proj.lora_B.speech.weight | |
| - model.layers.30.mlp.down_proj.lora_A.vision.weight | |
| - model.layers.30.mlp.down_proj.lora_A.speech.weight | |
| - model.layers.30.mlp.down_proj.lora_B.vision.weight | |
| - model.layers.30.mlp.down_proj.lora_B.speech.weight | |
| - model.layers.31.self_attn.o_proj.lora_A.vision.weight | |
| - model.layers.31.self_attn.o_proj.lora_A.speech.weight | |
| - model.layers.31.self_attn.o_proj.lora_B.vision.weight | |
| - model.layers.31.self_attn.o_proj.lora_B.speech.weight | |
| - model.layers.31.self_attn.qkv_proj.lora_A.vision.weight | |
| - model.layers.31.self_attn.qkv_proj.lora_A.speech.weight | |
| - model.layers.31.self_attn.qkv_proj.lora_B.vision.weight | |
| - model.layers.31.self_attn.qkv_proj.lora_B.speech.weight | |
| - model.layers.31.mlp.gate_up_proj.lora_A.vision.weight | |
| - model.layers.31.mlp.gate_up_proj.lora_A.speech.weight | |
| - model.layers.31.mlp.gate_up_proj.lora_B.vision.weight | |
| - model.layers.31.mlp.gate_up_proj.lora_B.speech.weight | |
| - model.layers.31.mlp.down_proj.lora_A.vision.weight | |
| - model.layers.31.mlp.down_proj.lora_A.speech.weight | |
| - model.layers.31.mlp.down_proj.lora_B.vision.weight | |
| - model.layers.31.mlp.down_proj.lora_B.speech.weight | |
| Components properly unfrozen ✅ | |
| Gradient accumulation steps: 1 | |
| Trainable params: 1296888448 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment