| { | |
| "metadata": { | |
| "total_size": 11148920768 | |
| }, | |
| "weight_map": { | |
| "model.embed_tokens.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.audio_projection.speech.0.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.audio_projection.speech.0.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.audio_projection.speech.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.audio_projection.speech.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.audio_projection.vision.0.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.audio_projection.vision.0.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.audio_projection.vision.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.audio_projection.vision.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.embed.conv.0.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.embed.conv.0.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.embed.conv.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.embed.conv.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.embed.conv.3.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.embed.conv.3.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.embed.conv.5.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.embed.conv.5.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.embed.conv.6.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.embed.conv.6.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.embed.out.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.embed.out.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoder_embedding.global_invstd": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoder_embedding.global_mean": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.conv.dw_sep_conv_1d.dw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.conv.dw_sep_conv_1d.dw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.conv.dw_sep_conv_1d.pw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.conv.dw_sep_conv_1d.pw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.conv.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.conv.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.conv.glu.b1": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.conv.glu.b2": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.conv.glu.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.conv.glu.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.conv.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.conv.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.feed_forward_in.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.feed_forward_in.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.feed_forward_in.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.feed_forward_in.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.feed_forward_in.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.feed_forward_in.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.feed_forward_out.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.feed_forward_out.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.feed_forward_out.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.feed_forward_out.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.feed_forward_out.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.feed_forward_out.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.layer_norm_att.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.layer_norm_att.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.self_attn.linear_k.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.self_attn.linear_k.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.self_attn.linear_out.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.self_attn.linear_out.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.self_attn.linear_q.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.self_attn.linear_q.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.self_attn.linear_v.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.0.self_attn.linear_v.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.conv.dw_sep_conv_1d.dw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.conv.dw_sep_conv_1d.dw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.conv.dw_sep_conv_1d.pw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.conv.dw_sep_conv_1d.pw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.conv.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.conv.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.conv.glu.b1": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.conv.glu.b2": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.conv.glu.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.conv.glu.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.conv.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.conv.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.feed_forward_in.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.feed_forward_in.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.feed_forward_in.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.feed_forward_in.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.feed_forward_in.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.feed_forward_in.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.feed_forward_out.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.feed_forward_out.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.feed_forward_out.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.feed_forward_out.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.feed_forward_out.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.feed_forward_out.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.layer_norm_att.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.layer_norm_att.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.self_attn.linear_k.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.self_attn.linear_k.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.self_attn.linear_out.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.self_attn.linear_out.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.self_attn.linear_q.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.self_attn.linear_q.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.self_attn.linear_v.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.1.self_attn.linear_v.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.conv.dw_sep_conv_1d.dw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.conv.dw_sep_conv_1d.dw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.conv.dw_sep_conv_1d.pw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.conv.dw_sep_conv_1d.pw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.conv.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.conv.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.conv.glu.b1": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.conv.glu.b2": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.conv.glu.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.conv.glu.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.conv.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.conv.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.feed_forward_in.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.feed_forward_in.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.feed_forward_in.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.feed_forward_in.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.feed_forward_in.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.feed_forward_in.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.feed_forward_out.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.feed_forward_out.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.feed_forward_out.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.feed_forward_out.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.feed_forward_out.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.feed_forward_out.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.layer_norm_att.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.layer_norm_att.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.self_attn.linear_k.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.self_attn.linear_k.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.self_attn.linear_out.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.self_attn.linear_out.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.self_attn.linear_q.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.self_attn.linear_q.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.self_attn.linear_v.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.10.self_attn.linear_v.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.conv.dw_sep_conv_1d.dw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.conv.dw_sep_conv_1d.dw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.conv.dw_sep_conv_1d.pw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.conv.dw_sep_conv_1d.pw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.conv.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.conv.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.conv.glu.b1": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.conv.glu.b2": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.conv.glu.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.conv.glu.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.conv.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.conv.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.feed_forward_in.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.feed_forward_in.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.feed_forward_in.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.feed_forward_in.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.feed_forward_in.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.feed_forward_in.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.feed_forward_out.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.feed_forward_out.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.feed_forward_out.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.feed_forward_out.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.feed_forward_out.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.feed_forward_out.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.layer_norm_att.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.layer_norm_att.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.self_attn.linear_k.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.self_attn.linear_k.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.self_attn.linear_out.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.self_attn.linear_out.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.self_attn.linear_q.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.self_attn.linear_q.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.self_attn.linear_v.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.11.self_attn.linear_v.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.conv.dw_sep_conv_1d.dw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.conv.dw_sep_conv_1d.dw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.conv.dw_sep_conv_1d.pw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.conv.dw_sep_conv_1d.pw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.conv.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.conv.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.conv.glu.b1": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.conv.glu.b2": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.conv.glu.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.conv.glu.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.conv.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.conv.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.feed_forward_in.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.feed_forward_in.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.feed_forward_in.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.feed_forward_in.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.feed_forward_in.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.feed_forward_in.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.feed_forward_out.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.feed_forward_out.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.feed_forward_out.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.feed_forward_out.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.feed_forward_out.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.feed_forward_out.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.layer_norm_att.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.layer_norm_att.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.self_attn.linear_k.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.self_attn.linear_k.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.self_attn.linear_out.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.self_attn.linear_out.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.self_attn.linear_q.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.self_attn.linear_q.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.self_attn.linear_v.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.12.self_attn.linear_v.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.conv.dw_sep_conv_1d.dw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.conv.dw_sep_conv_1d.dw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.conv.dw_sep_conv_1d.pw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.conv.dw_sep_conv_1d.pw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.conv.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.conv.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.conv.glu.b1": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.conv.glu.b2": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.conv.glu.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.conv.glu.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.conv.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.conv.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.feed_forward_in.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.feed_forward_in.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.feed_forward_in.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.feed_forward_in.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.feed_forward_in.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.feed_forward_in.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.feed_forward_out.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.feed_forward_out.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.feed_forward_out.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.feed_forward_out.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.feed_forward_out.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.feed_forward_out.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.layer_norm_att.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.layer_norm_att.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.self_attn.linear_k.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.self_attn.linear_k.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.self_attn.linear_out.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.self_attn.linear_out.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.self_attn.linear_q.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.self_attn.linear_q.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.self_attn.linear_v.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.13.self_attn.linear_v.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.conv.dw_sep_conv_1d.dw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.conv.dw_sep_conv_1d.dw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.conv.dw_sep_conv_1d.pw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.conv.dw_sep_conv_1d.pw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.conv.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.conv.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.conv.glu.b1": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.conv.glu.b2": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.conv.glu.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.conv.glu.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.conv.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.conv.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.feed_forward_in.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.feed_forward_in.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.feed_forward_in.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.feed_forward_in.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.feed_forward_in.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.feed_forward_in.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.feed_forward_out.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.feed_forward_out.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.feed_forward_out.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.feed_forward_out.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.feed_forward_out.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.feed_forward_out.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.layer_norm_att.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.layer_norm_att.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.self_attn.linear_k.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.self_attn.linear_k.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.self_attn.linear_out.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.self_attn.linear_out.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.self_attn.linear_q.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.self_attn.linear_q.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.self_attn.linear_v.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.14.self_attn.linear_v.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.conv.dw_sep_conv_1d.dw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.conv.dw_sep_conv_1d.dw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.conv.dw_sep_conv_1d.pw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.conv.dw_sep_conv_1d.pw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.conv.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.conv.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.conv.glu.b1": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.conv.glu.b2": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.conv.glu.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.conv.glu.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.conv.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.conv.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.feed_forward_in.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.feed_forward_in.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.feed_forward_in.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.feed_forward_in.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.feed_forward_in.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.feed_forward_in.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.feed_forward_out.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.feed_forward_out.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.feed_forward_out.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.feed_forward_out.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.feed_forward_out.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.feed_forward_out.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.layer_norm_att.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.layer_norm_att.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.self_attn.linear_k.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.self_attn.linear_k.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.self_attn.linear_out.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.self_attn.linear_out.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.self_attn.linear_q.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.self_attn.linear_q.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.self_attn.linear_v.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.15.self_attn.linear_v.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.conv.dw_sep_conv_1d.dw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.conv.dw_sep_conv_1d.dw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.conv.dw_sep_conv_1d.pw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.conv.dw_sep_conv_1d.pw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.conv.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.conv.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.conv.glu.b1": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.conv.glu.b2": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.conv.glu.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.conv.glu.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.conv.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.conv.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.feed_forward_in.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.feed_forward_in.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.feed_forward_in.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.feed_forward_in.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.feed_forward_in.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.feed_forward_in.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.feed_forward_out.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.feed_forward_out.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.feed_forward_out.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.feed_forward_out.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.feed_forward_out.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.feed_forward_out.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.layer_norm_att.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.layer_norm_att.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.self_attn.linear_k.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.self_attn.linear_k.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.self_attn.linear_out.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.self_attn.linear_out.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.self_attn.linear_q.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.self_attn.linear_q.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.self_attn.linear_v.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.16.self_attn.linear_v.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.conv.dw_sep_conv_1d.dw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.conv.dw_sep_conv_1d.dw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.conv.dw_sep_conv_1d.pw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.conv.dw_sep_conv_1d.pw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.conv.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.conv.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.conv.glu.b1": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.conv.glu.b2": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.conv.glu.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.conv.glu.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.conv.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.conv.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.feed_forward_in.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.feed_forward_in.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.feed_forward_in.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.feed_forward_in.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.feed_forward_in.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.feed_forward_in.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.feed_forward_out.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.feed_forward_out.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.feed_forward_out.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.feed_forward_out.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.feed_forward_out.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.feed_forward_out.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.layer_norm_att.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.layer_norm_att.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.self_attn.linear_k.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.self_attn.linear_k.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.self_attn.linear_out.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.self_attn.linear_out.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.self_attn.linear_q.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.self_attn.linear_q.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.self_attn.linear_v.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.17.self_attn.linear_v.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.conv.dw_sep_conv_1d.dw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.conv.dw_sep_conv_1d.dw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.conv.dw_sep_conv_1d.pw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.conv.dw_sep_conv_1d.pw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.conv.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.conv.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.conv.glu.b1": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.conv.glu.b2": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.conv.glu.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.conv.glu.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.conv.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.conv.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.feed_forward_in.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.feed_forward_in.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.feed_forward_in.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.feed_forward_in.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.feed_forward_in.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.feed_forward_in.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.feed_forward_out.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.feed_forward_out.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.feed_forward_out.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.feed_forward_out.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.feed_forward_out.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.feed_forward_out.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.layer_norm_att.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.layer_norm_att.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.self_attn.linear_k.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.self_attn.linear_k.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.self_attn.linear_out.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.self_attn.linear_out.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.self_attn.linear_q.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.self_attn.linear_q.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.self_attn.linear_v.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.18.self_attn.linear_v.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.conv.dw_sep_conv_1d.dw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.conv.dw_sep_conv_1d.dw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.conv.dw_sep_conv_1d.pw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.conv.dw_sep_conv_1d.pw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.conv.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.conv.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.conv.glu.b1": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.conv.glu.b2": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.conv.glu.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.conv.glu.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.conv.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.conv.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.feed_forward_in.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.feed_forward_in.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.feed_forward_in.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.feed_forward_in.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.feed_forward_in.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.feed_forward_in.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.feed_forward_out.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.feed_forward_out.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.feed_forward_out.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.feed_forward_out.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.feed_forward_out.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.feed_forward_out.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.layer_norm_att.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.layer_norm_att.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.self_attn.linear_k.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.self_attn.linear_k.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.self_attn.linear_out.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.self_attn.linear_out.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.self_attn.linear_q.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.self_attn.linear_q.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.self_attn.linear_v.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.19.self_attn.linear_v.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.conv.dw_sep_conv_1d.dw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.conv.dw_sep_conv_1d.dw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.conv.dw_sep_conv_1d.pw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.conv.dw_sep_conv_1d.pw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.conv.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.conv.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.conv.glu.b1": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.conv.glu.b2": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.conv.glu.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.conv.glu.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.conv.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.conv.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.feed_forward_in.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.feed_forward_in.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.feed_forward_in.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.feed_forward_in.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.feed_forward_in.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.feed_forward_in.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.feed_forward_out.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.feed_forward_out.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.feed_forward_out.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.feed_forward_out.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.feed_forward_out.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.feed_forward_out.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.layer_norm_att.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.layer_norm_att.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.self_attn.linear_k.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.self_attn.linear_k.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.self_attn.linear_out.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.self_attn.linear_out.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.self_attn.linear_q.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.self_attn.linear_q.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.self_attn.linear_v.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.2.self_attn.linear_v.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.conv.dw_sep_conv_1d.dw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.conv.dw_sep_conv_1d.dw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.conv.dw_sep_conv_1d.pw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.conv.dw_sep_conv_1d.pw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.conv.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.conv.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.conv.glu.b1": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.conv.glu.b2": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.conv.glu.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.conv.glu.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.conv.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.conv.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.feed_forward_in.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.feed_forward_in.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.feed_forward_in.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.feed_forward_in.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.feed_forward_in.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.feed_forward_in.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.feed_forward_out.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.feed_forward_out.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.feed_forward_out.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.feed_forward_out.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.feed_forward_out.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.feed_forward_out.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.layer_norm_att.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.layer_norm_att.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.self_attn.linear_k.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.self_attn.linear_k.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.self_attn.linear_out.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.self_attn.linear_out.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.self_attn.linear_q.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.self_attn.linear_q.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.self_attn.linear_v.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.20.self_attn.linear_v.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.conv.dw_sep_conv_1d.dw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.conv.dw_sep_conv_1d.dw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.conv.dw_sep_conv_1d.pw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.conv.dw_sep_conv_1d.pw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.conv.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.conv.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.conv.glu.b1": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.conv.glu.b2": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.conv.glu.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.conv.glu.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.conv.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.conv.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.feed_forward_in.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.feed_forward_in.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.feed_forward_in.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.feed_forward_in.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.feed_forward_in.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.feed_forward_in.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.feed_forward_out.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.feed_forward_out.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.feed_forward_out.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.feed_forward_out.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.feed_forward_out.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.feed_forward_out.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.layer_norm_att.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.layer_norm_att.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.self_attn.linear_k.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.self_attn.linear_k.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.self_attn.linear_out.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.self_attn.linear_out.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.self_attn.linear_q.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.self_attn.linear_q.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.self_attn.linear_v.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.21.self_attn.linear_v.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.conv.dw_sep_conv_1d.dw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.conv.dw_sep_conv_1d.dw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.conv.dw_sep_conv_1d.pw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.conv.dw_sep_conv_1d.pw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.conv.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.conv.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.conv.glu.b1": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.conv.glu.b2": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.conv.glu.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.conv.glu.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.conv.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.conv.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.feed_forward_in.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.feed_forward_in.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.feed_forward_in.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.feed_forward_in.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.feed_forward_in.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.feed_forward_in.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.feed_forward_out.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.feed_forward_out.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.feed_forward_out.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.feed_forward_out.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.feed_forward_out.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.feed_forward_out.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.layer_norm_att.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.layer_norm_att.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.self_attn.linear_k.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.self_attn.linear_k.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.self_attn.linear_out.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.self_attn.linear_out.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.self_attn.linear_q.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.self_attn.linear_q.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.self_attn.linear_v.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.22.self_attn.linear_v.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.conv.dw_sep_conv_1d.dw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.conv.dw_sep_conv_1d.dw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.conv.dw_sep_conv_1d.pw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.conv.dw_sep_conv_1d.pw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.conv.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.conv.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.conv.glu.b1": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.conv.glu.b2": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.conv.glu.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.conv.glu.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.conv.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.conv.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.feed_forward_in.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.feed_forward_in.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.feed_forward_in.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.feed_forward_in.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.feed_forward_in.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.feed_forward_in.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.feed_forward_out.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.feed_forward_out.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.feed_forward_out.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.feed_forward_out.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.feed_forward_out.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.feed_forward_out.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.layer_norm_att.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.layer_norm_att.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.self_attn.linear_k.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.self_attn.linear_k.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.self_attn.linear_out.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.self_attn.linear_out.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.self_attn.linear_q.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.self_attn.linear_q.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.self_attn.linear_v.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.23.self_attn.linear_v.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.conv.dw_sep_conv_1d.dw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.conv.dw_sep_conv_1d.dw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.conv.dw_sep_conv_1d.pw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.conv.dw_sep_conv_1d.pw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.conv.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.conv.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.conv.glu.b1": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.conv.glu.b2": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.conv.glu.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.conv.glu.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.conv.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.conv.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.feed_forward_in.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.feed_forward_in.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.feed_forward_in.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.feed_forward_in.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.feed_forward_in.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.feed_forward_in.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.feed_forward_out.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.feed_forward_out.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.feed_forward_out.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.feed_forward_out.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.feed_forward_out.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.feed_forward_out.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.layer_norm_att.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.layer_norm_att.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.self_attn.linear_k.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.self_attn.linear_k.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.self_attn.linear_out.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.self_attn.linear_out.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.self_attn.linear_q.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.self_attn.linear_q.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.self_attn.linear_v.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.3.self_attn.linear_v.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.conv.dw_sep_conv_1d.dw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.conv.dw_sep_conv_1d.dw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.conv.dw_sep_conv_1d.pw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.conv.dw_sep_conv_1d.pw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.conv.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.conv.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.conv.glu.b1": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.conv.glu.b2": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.conv.glu.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.conv.glu.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.conv.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.conv.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.feed_forward_in.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.feed_forward_in.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.feed_forward_in.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.feed_forward_in.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.feed_forward_in.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.feed_forward_in.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.feed_forward_out.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.feed_forward_out.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.feed_forward_out.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.feed_forward_out.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.feed_forward_out.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.feed_forward_out.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.layer_norm_att.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.layer_norm_att.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.self_attn.linear_k.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.self_attn.linear_k.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.self_attn.linear_out.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.self_attn.linear_out.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.self_attn.linear_q.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.self_attn.linear_q.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.self_attn.linear_v.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.4.self_attn.linear_v.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.conv.dw_sep_conv_1d.dw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.conv.dw_sep_conv_1d.dw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.conv.dw_sep_conv_1d.pw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.conv.dw_sep_conv_1d.pw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.conv.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.conv.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.conv.glu.b1": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.conv.glu.b2": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.conv.glu.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.conv.glu.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.conv.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.conv.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.feed_forward_in.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.feed_forward_in.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.feed_forward_in.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.feed_forward_in.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.feed_forward_in.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.feed_forward_in.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.feed_forward_out.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.feed_forward_out.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.feed_forward_out.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.feed_forward_out.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.feed_forward_out.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.feed_forward_out.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.layer_norm_att.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.layer_norm_att.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.self_attn.linear_k.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.self_attn.linear_k.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.self_attn.linear_out.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.self_attn.linear_out.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.self_attn.linear_q.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.self_attn.linear_q.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.self_attn.linear_v.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.5.self_attn.linear_v.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.conv.dw_sep_conv_1d.dw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.conv.dw_sep_conv_1d.dw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.conv.dw_sep_conv_1d.pw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.conv.dw_sep_conv_1d.pw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.conv.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.conv.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.conv.glu.b1": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.conv.glu.b2": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.conv.glu.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.conv.glu.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.conv.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.conv.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.feed_forward_in.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.feed_forward_in.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.feed_forward_in.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.feed_forward_in.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.feed_forward_in.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.feed_forward_in.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.feed_forward_out.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.feed_forward_out.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.feed_forward_out.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.feed_forward_out.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.feed_forward_out.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.feed_forward_out.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.layer_norm_att.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.layer_norm_att.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.self_attn.linear_k.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.self_attn.linear_k.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.self_attn.linear_out.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.self_attn.linear_out.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.self_attn.linear_q.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.self_attn.linear_q.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.self_attn.linear_v.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.6.self_attn.linear_v.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.conv.dw_sep_conv_1d.dw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.conv.dw_sep_conv_1d.dw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.conv.dw_sep_conv_1d.pw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.conv.dw_sep_conv_1d.pw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.conv.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.conv.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.conv.glu.b1": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.conv.glu.b2": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.conv.glu.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.conv.glu.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.conv.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.conv.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.feed_forward_in.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.feed_forward_in.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.feed_forward_in.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.feed_forward_in.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.feed_forward_in.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.feed_forward_in.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.feed_forward_out.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.feed_forward_out.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.feed_forward_out.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.feed_forward_out.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.feed_forward_out.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.feed_forward_out.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.layer_norm_att.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.layer_norm_att.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.self_attn.linear_k.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.self_attn.linear_k.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.self_attn.linear_out.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.self_attn.linear_out.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.self_attn.linear_q.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.self_attn.linear_q.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.self_attn.linear_v.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.7.self_attn.linear_v.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.conv.dw_sep_conv_1d.dw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.conv.dw_sep_conv_1d.dw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.conv.dw_sep_conv_1d.pw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.conv.dw_sep_conv_1d.pw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.conv.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.conv.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.conv.glu.b1": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.conv.glu.b2": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.conv.glu.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.conv.glu.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.conv.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.conv.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.feed_forward_in.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.feed_forward_in.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.feed_forward_in.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.feed_forward_in.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.feed_forward_in.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.feed_forward_in.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.feed_forward_out.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.feed_forward_out.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.feed_forward_out.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.feed_forward_out.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.feed_forward_out.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.feed_forward_out.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.layer_norm_att.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.layer_norm_att.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.self_attn.linear_k.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.self_attn.linear_k.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.self_attn.linear_out.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.self_attn.linear_out.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.self_attn.linear_q.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.self_attn.linear_q.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.self_attn.linear_v.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.8.self_attn.linear_v.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.conv.dw_sep_conv_1d.dw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.conv.dw_sep_conv_1d.dw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.conv.dw_sep_conv_1d.pw_conv.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.conv.dw_sep_conv_1d.pw_conv.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.conv.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.conv.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.conv.glu.b1": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.conv.glu.b2": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.conv.glu.ext_pw_conv_1d.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.conv.glu.ext_pw_conv_1d.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.conv.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.conv.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.feed_forward_in.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.feed_forward_in.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.feed_forward_in.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.feed_forward_in.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.feed_forward_in.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.feed_forward_in.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.feed_forward_out.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.feed_forward_out.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.feed_forward_out.net.0.linear.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.feed_forward_out.net.0.linear.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.feed_forward_out.net.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.feed_forward_out.net.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.layer_norm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.layer_norm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.layer_norm_att.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.layer_norm_att.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.self_attn.linear_k.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.self_attn.linear_k.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.self_attn.linear_out.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.self_attn.linear_out.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.self_attn.linear_q.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.self_attn.linear_q.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.self_attn.linear_v.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.encoders.9.self_attn.linear_v.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.audio_embed.encoder.relative_attention_bias_layer.bias_values.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.glb_GN": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.embeddings.patch_embedding.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.embeddings.patch_embedding.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.embeddings.position_embedding.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.0.layer_norm1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.0.layer_norm1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.0.layer_norm2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.0.layer_norm2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.1.layer_norm1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.1.layer_norm1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.1.layer_norm2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.1.layer_norm2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.10.layer_norm1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.10.layer_norm1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.10.layer_norm2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.10.layer_norm2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.11.layer_norm1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.11.layer_norm1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.11.layer_norm2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.11.layer_norm2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.12.layer_norm1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.12.layer_norm1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.12.layer_norm2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.12.layer_norm2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.13.layer_norm1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.13.layer_norm1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.13.layer_norm2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.13.layer_norm2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.14.layer_norm1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.14.layer_norm1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.14.layer_norm2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.14.layer_norm2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.15.layer_norm1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.15.layer_norm1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.15.layer_norm2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.15.layer_norm2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.16.layer_norm1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.16.layer_norm1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.16.layer_norm2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.16.layer_norm2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.17.layer_norm1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.17.layer_norm1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.17.layer_norm2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.17.layer_norm2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.18.layer_norm1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.18.layer_norm1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.18.layer_norm2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.18.layer_norm2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.19.layer_norm1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.19.layer_norm1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.19.layer_norm2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.19.layer_norm2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.2.layer_norm1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.2.layer_norm1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.2.layer_norm2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.2.layer_norm2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.20.layer_norm1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.20.layer_norm1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.20.layer_norm2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.20.layer_norm2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.21.layer_norm1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.21.layer_norm1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.21.layer_norm2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.21.layer_norm2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.22.layer_norm1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.22.layer_norm1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.22.layer_norm2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.22.layer_norm2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.23.layer_norm1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.23.layer_norm1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.23.layer_norm2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.23.layer_norm2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.24.layer_norm1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.24.layer_norm1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.24.layer_norm2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.24.layer_norm2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.25.layer_norm1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.25.layer_norm1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.25.layer_norm2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.25.layer_norm2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.26.layer_norm1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.26.layer_norm1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.26.layer_norm2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.26.layer_norm2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.3.layer_norm1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.3.layer_norm1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.3.layer_norm2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.3.layer_norm2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.4.layer_norm1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.4.layer_norm1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.4.layer_norm2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.4.layer_norm2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.5.layer_norm1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.5.layer_norm1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.5.layer_norm2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.5.layer_norm2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.6.layer_norm1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.6.layer_norm1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.6.layer_norm2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.6.layer_norm2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.7.layer_norm1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.7.layer_norm1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.7.layer_norm2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.7.layer_norm2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.8.layer_norm1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.8.layer_norm1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.8.layer_norm2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.8.layer_norm2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.9.layer_norm1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.9.layer_norm1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.9.layer_norm2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.9.layer_norm2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.head.attention.in_proj_bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.head.attention.in_proj_weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.head.attention.out_proj.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.head.attention.out_proj.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.head.layernorm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.head.layernorm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.head.mlp.fc1.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.head.mlp.fc1.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.head.mlp.fc2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.head.mlp.fc2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.head.probe": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.post_layernorm.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_processor.post_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_projection.0.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_projection.0.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_projection.2.bias": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.img_projection.2.weight": "model-00001-of-00003.safetensors", | |
| "model.embed_tokens_extend.image_embed.sub_GN": "model-00001-of-00003.safetensors", | |
| "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.0.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.0.mlp.down_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.0.mlp.down_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.0.mlp.down_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.0.mlp.down_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.0.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.0.mlp.gate_up_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.0.mlp.gate_up_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.0.mlp.gate_up_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.0.mlp.gate_up_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.0.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.0.self_attn.o_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.0.self_attn.o_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.0.self_attn.o_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.0.self_attn.o_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.0.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.0.self_attn.qkv_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.0.self_attn.qkv_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.0.self_attn.qkv_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.0.self_attn.qkv_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.1.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.1.mlp.down_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.1.mlp.down_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.1.mlp.down_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.1.mlp.down_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.1.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.1.mlp.gate_up_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.1.mlp.gate_up_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.1.mlp.gate_up_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.1.mlp.gate_up_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.1.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.1.self_attn.o_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.1.self_attn.o_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.1.self_attn.o_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.1.self_attn.o_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.1.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.1.self_attn.qkv_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.1.self_attn.qkv_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.1.self_attn.qkv_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.1.self_attn.qkv_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.10.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.10.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.10.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.10.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.10.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.10.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.10.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.10.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.10.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.10.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.10.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.10.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.10.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.10.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.10.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.10.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.10.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.10.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.10.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.10.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.11.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.11.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.11.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.11.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.11.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.11.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.11.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.11.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.11.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.11.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.11.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.11.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.11.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.11.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.11.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.11.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.11.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.11.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.11.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.11.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.12.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.12.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.12.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.12.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.12.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.12.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.12.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.12.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.12.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.12.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.12.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.12.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.12.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.12.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.12.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.12.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.12.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.12.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.12.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.12.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.13.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.13.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.13.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.13.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.13.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.13.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.13.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.13.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.13.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.13.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.13.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.13.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.13.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.13.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.13.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.13.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.13.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.13.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.13.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.13.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.14.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.14.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.14.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.14.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.14.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.14.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.14.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.14.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.14.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.14.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.14.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.14.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.14.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.14.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.14.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.14.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.14.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.14.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.14.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.14.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.15.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.15.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.15.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.15.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.15.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.15.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.15.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.15.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.15.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.15.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.15.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.15.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.15.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.15.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.15.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.15.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.15.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.15.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.15.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.15.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.16.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.16.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.16.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.16.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.16.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.16.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.16.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.16.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.16.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.16.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.16.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.16.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.16.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.16.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.16.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.16.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.16.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.16.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.16.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.16.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.17.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.17.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.17.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.17.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.17.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.17.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.17.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.17.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.17.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.17.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.17.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.17.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.17.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.17.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.17.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.17.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.17.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.17.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.17.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.17.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.18.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.18.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.18.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.18.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.18.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.18.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.18.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.18.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.18.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.18.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.18.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.18.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.18.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.18.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.18.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.18.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.18.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.18.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.18.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.18.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.19.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.19.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.19.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.19.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.19.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.19.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.19.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.19.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.19.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.19.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.19.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.19.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.19.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.19.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.19.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.19.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.19.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.19.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.19.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.19.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.2.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.2.mlp.down_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.2.mlp.down_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.2.mlp.down_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.2.mlp.down_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.2.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.2.mlp.gate_up_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.2.mlp.gate_up_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.2.mlp.gate_up_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.2.mlp.gate_up_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.2.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.2.self_attn.o_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.2.self_attn.o_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.2.self_attn.o_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.2.self_attn.o_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.2.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.2.self_attn.qkv_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.2.self_attn.qkv_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.2.self_attn.qkv_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.2.self_attn.qkv_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.20.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.20.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.20.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.20.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.20.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.20.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.20.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.20.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.20.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.20.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.20.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.20.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.20.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.20.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.20.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.20.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.20.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.20.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.20.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.20.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.21.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.21.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.21.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.21.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.21.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.21.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.21.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.21.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.21.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.21.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.21.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.21.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.21.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.21.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.21.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.21.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.21.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.21.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.21.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.21.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.22.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.22.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.22.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.22.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.22.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.22.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.22.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.22.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.22.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.22.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.22.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.22.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.22.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.22.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.22.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.22.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.22.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.22.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.22.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.22.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.23.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.23.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.23.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.23.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.23.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.23.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.23.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.23.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.23.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.23.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.23.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.23.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.23.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.23.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.23.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.23.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.23.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.23.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.23.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.23.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.24.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.24.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.24.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.24.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.24.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.24.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.24.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.24.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.24.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.24.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.24.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.24.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.24.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.24.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.24.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.24.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.24.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.24.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.24.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.24.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.25.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.25.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.25.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.25.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.25.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.25.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.25.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.25.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.25.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.25.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.25.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.25.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.25.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.25.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.25.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.25.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.25.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.25.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.25.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.25.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.26.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.26.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.26.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.26.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.26.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.26.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.26.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.26.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.26.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.26.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.26.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.26.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.26.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.26.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.26.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.26.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.26.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.26.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.26.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.26.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.27.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.27.mlp.down_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.27.mlp.down_proj.lora_A.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.27.mlp.down_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.27.mlp.down_proj.lora_B.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.27.mlp.gate_up_proj.base_layer.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.27.mlp.gate_up_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.27.mlp.gate_up_proj.lora_A.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.27.mlp.gate_up_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.27.mlp.gate_up_proj.lora_B.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.27.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.27.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.27.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.27.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.27.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.27.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.27.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.27.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.27.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.27.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.28.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.28.mlp.down_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.28.mlp.down_proj.lora_A.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.28.mlp.down_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.28.mlp.down_proj.lora_B.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.28.mlp.gate_up_proj.base_layer.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.28.mlp.gate_up_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.28.mlp.gate_up_proj.lora_A.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.28.mlp.gate_up_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.28.mlp.gate_up_proj.lora_B.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.28.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.28.self_attn.o_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.28.self_attn.o_proj.lora_A.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.28.self_attn.o_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.28.self_attn.o_proj.lora_B.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.28.self_attn.qkv_proj.base_layer.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.28.self_attn.qkv_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.28.self_attn.qkv_proj.lora_A.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.28.self_attn.qkv_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.28.self_attn.qkv_proj.lora_B.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.29.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.29.mlp.down_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.29.mlp.down_proj.lora_A.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.29.mlp.down_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.29.mlp.down_proj.lora_B.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.29.mlp.gate_up_proj.base_layer.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.29.mlp.gate_up_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.29.mlp.gate_up_proj.lora_A.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.29.mlp.gate_up_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.29.mlp.gate_up_proj.lora_B.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.29.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.29.self_attn.o_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.29.self_attn.o_proj.lora_A.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.29.self_attn.o_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.29.self_attn.o_proj.lora_B.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.29.self_attn.qkv_proj.base_layer.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.29.self_attn.qkv_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.29.self_attn.qkv_proj.lora_A.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.29.self_attn.qkv_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.29.self_attn.qkv_proj.lora_B.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.3.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.3.mlp.down_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.3.mlp.down_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.3.mlp.down_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.3.mlp.down_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.3.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.3.mlp.gate_up_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.3.mlp.gate_up_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.3.mlp.gate_up_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.3.mlp.gate_up_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.3.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.3.self_attn.o_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.3.self_attn.o_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.3.self_attn.o_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.3.self_attn.o_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.3.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.3.self_attn.qkv_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.3.self_attn.qkv_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.3.self_attn.qkv_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.3.self_attn.qkv_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.30.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.30.mlp.down_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.30.mlp.down_proj.lora_A.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.30.mlp.down_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.30.mlp.down_proj.lora_B.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.30.mlp.gate_up_proj.base_layer.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.30.mlp.gate_up_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.30.mlp.gate_up_proj.lora_A.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.30.mlp.gate_up_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.30.mlp.gate_up_proj.lora_B.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.30.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.30.self_attn.o_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.30.self_attn.o_proj.lora_A.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.30.self_attn.o_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.30.self_attn.o_proj.lora_B.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.30.self_attn.qkv_proj.base_layer.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.30.self_attn.qkv_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.30.self_attn.qkv_proj.lora_A.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.30.self_attn.qkv_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.30.self_attn.qkv_proj.lora_B.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.31.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.31.mlp.down_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.31.mlp.down_proj.lora_A.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.31.mlp.down_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.31.mlp.down_proj.lora_B.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.31.mlp.gate_up_proj.base_layer.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.31.mlp.gate_up_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.31.mlp.gate_up_proj.lora_A.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.31.mlp.gate_up_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.31.mlp.gate_up_proj.lora_B.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.31.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.31.self_attn.o_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.31.self_attn.o_proj.lora_A.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.31.self_attn.o_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.31.self_attn.o_proj.lora_B.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.31.self_attn.qkv_proj.base_layer.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.31.self_attn.qkv_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.31.self_attn.qkv_proj.lora_A.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.31.self_attn.qkv_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.31.self_attn.qkv_proj.lora_B.vision.weight": "model-00003-of-00003.safetensors", | |
| "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.4.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.4.mlp.down_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.4.mlp.down_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.4.mlp.down_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.4.mlp.down_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.4.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.4.mlp.gate_up_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.4.mlp.gate_up_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.4.mlp.gate_up_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.4.mlp.gate_up_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.4.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.4.self_attn.o_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.4.self_attn.o_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.4.self_attn.o_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.4.self_attn.o_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.4.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.4.self_attn.qkv_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.4.self_attn.qkv_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.4.self_attn.qkv_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.4.self_attn.qkv_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.5.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.5.mlp.down_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.5.mlp.down_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.5.mlp.down_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.5.mlp.down_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.5.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.5.mlp.gate_up_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.5.mlp.gate_up_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.5.mlp.gate_up_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.5.mlp.gate_up_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.5.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.5.self_attn.o_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.5.self_attn.o_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.5.self_attn.o_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.5.self_attn.o_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.5.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.5.self_attn.qkv_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.5.self_attn.qkv_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.5.self_attn.qkv_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.5.self_attn.qkv_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.6.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.6.mlp.down_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.6.mlp.down_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.6.mlp.down_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.6.mlp.down_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.6.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.6.mlp.gate_up_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.6.mlp.gate_up_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.6.mlp.gate_up_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.6.mlp.gate_up_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.6.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.6.self_attn.o_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.6.self_attn.o_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.6.self_attn.o_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.6.self_attn.o_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.6.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.6.self_attn.qkv_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.6.self_attn.qkv_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.6.self_attn.qkv_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.6.self_attn.qkv_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.7.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.7.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.7.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.7.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.7.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.7.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.7.mlp.gate_up_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.7.mlp.gate_up_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.7.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.7.mlp.gate_up_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.7.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.7.self_attn.o_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.7.self_attn.o_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.7.self_attn.o_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.7.self_attn.o_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.7.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.7.self_attn.qkv_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.7.self_attn.qkv_proj.lora_A.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.7.self_attn.qkv_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.7.self_attn.qkv_proj.lora_B.vision.weight": "model-00001-of-00003.safetensors", | |
| "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.8.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.8.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.8.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.8.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.8.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.8.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.8.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.8.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.8.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.8.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.8.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.8.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.8.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.8.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.8.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.8.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.8.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.8.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.8.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.8.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.9.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.9.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.9.mlp.down_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.9.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.9.mlp.down_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.9.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.9.mlp.gate_up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.9.mlp.gate_up_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.9.mlp.gate_up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.9.mlp.gate_up_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.9.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.9.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.9.self_attn.o_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.9.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.9.self_attn.o_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.9.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.9.self_attn.qkv_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.9.self_attn.qkv_proj.lora_A.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.9.self_attn.qkv_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors", | |
| "model.layers.9.self_attn.qkv_proj.lora_B.vision.weight": "model-00002-of-00003.safetensors", | |
| "model.norm.weight": "model-00003-of-00003.safetensors" | |
| } | |
| } | |