| { |
| "metadata": { |
| "total_size": 1947685252, |
| "total_parameters": 887785217 |
| }, |
| "weight_map": { |
| "audio_vae.decoder.blocks.layers.0.conv_t.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.0.conv_t.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.0.res1.conv1.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.0.res1.conv1.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.0.res1.conv2.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.0.res1.conv2.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.0.res1.snake1.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.0.res1.snake2.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.0.res2.conv1.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.0.res2.conv1.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.0.res2.conv2.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.0.res2.conv2.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.0.res2.snake1.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.0.res2.snake2.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.0.res3.conv1.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.0.res3.conv1.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.0.res3.conv2.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.0.res3.conv2.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.0.res3.snake1.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.0.res3.snake2.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.0.snake.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.1.conv_t.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.1.conv_t.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.1.res1.conv1.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.1.res1.conv1.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.1.res1.conv2.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.1.res1.conv2.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.1.res1.snake1.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.1.res1.snake2.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.1.res2.conv1.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.1.res2.conv1.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.1.res2.conv2.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.1.res2.conv2.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.1.res2.snake1.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.1.res2.snake2.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.1.res3.conv1.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.1.res3.conv1.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.1.res3.conv2.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.1.res3.conv2.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.1.res3.snake1.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.1.res3.snake2.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.1.snake.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.2.conv_t.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.2.conv_t.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.2.res1.conv1.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.2.res1.conv1.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.2.res1.conv2.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.2.res1.conv2.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.2.res1.snake1.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.2.res1.snake2.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.2.res2.conv1.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.2.res2.conv1.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.2.res2.conv2.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.2.res2.conv2.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.2.res2.snake1.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.2.res2.snake2.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.2.res3.conv1.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.2.res3.conv1.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.2.res3.conv2.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.2.res3.conv2.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.2.res3.snake1.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.2.res3.snake2.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.2.snake.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.3.conv_t.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.3.conv_t.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.3.res1.conv1.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.3.res1.conv1.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.3.res1.conv2.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.3.res1.conv2.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.3.res1.snake1.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.3.res1.snake2.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.3.res2.conv1.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.3.res2.conv1.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.3.res2.conv2.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.3.res2.conv2.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.3.res2.snake1.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.3.res2.snake2.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.3.res3.conv1.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.3.res3.conv1.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.3.res3.conv2.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.3.res3.conv2.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.3.res3.snake1.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.3.res3.snake2.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.3.snake.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.4.conv_t.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.4.conv_t.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.4.res1.conv1.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.4.res1.conv1.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.4.res1.conv2.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.4.res1.conv2.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.4.res1.snake1.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.4.res1.snake2.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.4.res2.conv1.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.4.res2.conv1.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.4.res2.conv2.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.4.res2.conv2.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.4.res2.snake1.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.4.res2.snake2.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.4.res3.conv1.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.4.res3.conv1.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.4.res3.conv2.bias": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.4.res3.conv2.weight": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.4.res3.snake1.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.4.res3.snake2.alpha": "model.safetensors", |
| "audio_vae.decoder.blocks.layers.4.snake.alpha": "model.safetensors", |
| "audio_vae.decoder.conv_in.layers.0.bias": "model.safetensors", |
| "audio_vae.decoder.conv_in.layers.0.weight": "model.safetensors", |
| "audio_vae.decoder.conv_in.layers.1.bias": "model.safetensors", |
| "audio_vae.decoder.conv_in.layers.1.weight": "model.safetensors", |
| "audio_vae.decoder.conv_out.bias": "model.safetensors", |
| "audio_vae.decoder.conv_out.weight": "model.safetensors", |
| "audio_vae.decoder.snake_out.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.0.conv.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.0.conv.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.0.res1.conv1.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.0.res1.conv1.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.0.res1.conv2.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.0.res1.conv2.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.0.res1.snake1.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.0.res1.snake2.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.0.res2.conv1.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.0.res2.conv1.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.0.res2.conv2.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.0.res2.conv2.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.0.res2.snake1.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.0.res2.snake2.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.0.res3.conv1.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.0.res3.conv1.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.0.res3.conv2.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.0.res3.conv2.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.0.res3.snake1.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.0.res3.snake2.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.0.snake.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.1.conv.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.1.conv.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.1.res1.conv1.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.1.res1.conv1.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.1.res1.conv2.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.1.res1.conv2.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.1.res1.snake1.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.1.res1.snake2.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.1.res2.conv1.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.1.res2.conv1.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.1.res2.conv2.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.1.res2.conv2.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.1.res2.snake1.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.1.res2.snake2.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.1.res3.conv1.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.1.res3.conv1.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.1.res3.conv2.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.1.res3.conv2.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.1.res3.snake1.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.1.res3.snake2.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.1.snake.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.2.conv.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.2.conv.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.2.res1.conv1.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.2.res1.conv1.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.2.res1.conv2.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.2.res1.conv2.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.2.res1.snake1.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.2.res1.snake2.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.2.res2.conv1.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.2.res2.conv1.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.2.res2.conv2.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.2.res2.conv2.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.2.res2.snake1.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.2.res2.snake2.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.2.res3.conv1.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.2.res3.conv1.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.2.res3.conv2.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.2.res3.conv2.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.2.res3.snake1.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.2.res3.snake2.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.2.snake.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.3.conv.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.3.conv.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.3.res1.conv1.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.3.res1.conv1.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.3.res1.conv2.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.3.res1.conv2.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.3.res1.snake1.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.3.res1.snake2.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.3.res2.conv1.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.3.res2.conv1.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.3.res2.conv2.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.3.res2.conv2.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.3.res2.snake1.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.3.res2.snake2.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.3.res3.conv1.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.3.res3.conv1.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.3.res3.conv2.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.3.res3.conv2.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.3.res3.snake1.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.3.res3.snake2.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.3.snake.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.4.conv.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.4.conv.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.4.res1.conv1.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.4.res1.conv1.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.4.res1.conv2.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.4.res1.conv2.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.4.res1.snake1.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.4.res1.snake2.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.4.res2.conv1.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.4.res2.conv1.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.4.res2.conv2.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.4.res2.conv2.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.4.res2.snake1.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.4.res2.snake2.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.4.res3.conv1.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.4.res3.conv1.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.4.res3.conv2.bias": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.4.res3.conv2.weight": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.4.res3.snake1.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.4.res3.snake2.alpha": "model.safetensors", |
| "audio_vae.encoder.blocks.layers.4.snake.alpha": "model.safetensors", |
| "audio_vae.encoder.conv_in.bias": "model.safetensors", |
| "audio_vae.encoder.conv_in.weight": "model.safetensors", |
| "audio_vae.encoder.fc_mu.bias": "model.safetensors", |
| "audio_vae.encoder.fc_mu.weight": "model.safetensors", |
| "base_lm.embed_tokens.weight": "model.safetensors", |
| "base_lm.layers.0.input_layernorm.weight": "model.safetensors", |
| "base_lm.layers.0.mlp.down_proj.weight": "model.safetensors", |
| "base_lm.layers.0.mlp.gate_proj.weight": "model.safetensors", |
| "base_lm.layers.0.mlp.up_proj.weight": "model.safetensors", |
| "base_lm.layers.0.post_attention_layernorm.weight": "model.safetensors", |
| "base_lm.layers.0.self_attn.k_proj.weight": "model.safetensors", |
| "base_lm.layers.0.self_attn.o_proj.weight": "model.safetensors", |
| "base_lm.layers.0.self_attn.q_proj.weight": "model.safetensors", |
| "base_lm.layers.0.self_attn.v_proj.weight": "model.safetensors", |
| "base_lm.layers.1.input_layernorm.weight": "model.safetensors", |
| "base_lm.layers.1.mlp.down_proj.weight": "model.safetensors", |
| "base_lm.layers.1.mlp.gate_proj.weight": "model.safetensors", |
| "base_lm.layers.1.mlp.up_proj.weight": "model.safetensors", |
| "base_lm.layers.1.post_attention_layernorm.weight": "model.safetensors", |
| "base_lm.layers.1.self_attn.k_proj.weight": "model.safetensors", |
| "base_lm.layers.1.self_attn.o_proj.weight": "model.safetensors", |
| "base_lm.layers.1.self_attn.q_proj.weight": "model.safetensors", |
| "base_lm.layers.1.self_attn.v_proj.weight": "model.safetensors", |
| "base_lm.layers.10.input_layernorm.weight": "model.safetensors", |
| "base_lm.layers.10.mlp.down_proj.weight": "model.safetensors", |
| "base_lm.layers.10.mlp.gate_proj.weight": "model.safetensors", |
| "base_lm.layers.10.mlp.up_proj.weight": "model.safetensors", |
| "base_lm.layers.10.post_attention_layernorm.weight": "model.safetensors", |
| "base_lm.layers.10.self_attn.k_proj.weight": "model.safetensors", |
| "base_lm.layers.10.self_attn.o_proj.weight": "model.safetensors", |
| "base_lm.layers.10.self_attn.q_proj.weight": "model.safetensors", |
| "base_lm.layers.10.self_attn.v_proj.weight": "model.safetensors", |
| "base_lm.layers.11.input_layernorm.weight": "model.safetensors", |
| "base_lm.layers.11.mlp.down_proj.weight": "model.safetensors", |
| "base_lm.layers.11.mlp.gate_proj.weight": "model.safetensors", |
| "base_lm.layers.11.mlp.up_proj.weight": "model.safetensors", |
| "base_lm.layers.11.post_attention_layernorm.weight": "model.safetensors", |
| "base_lm.layers.11.self_attn.k_proj.weight": "model.safetensors", |
| "base_lm.layers.11.self_attn.o_proj.weight": "model.safetensors", |
| "base_lm.layers.11.self_attn.q_proj.weight": "model.safetensors", |
| "base_lm.layers.11.self_attn.v_proj.weight": "model.safetensors", |
| "base_lm.layers.12.input_layernorm.weight": "model.safetensors", |
| "base_lm.layers.12.mlp.down_proj.weight": "model.safetensors", |
| "base_lm.layers.12.mlp.gate_proj.weight": "model.safetensors", |
| "base_lm.layers.12.mlp.up_proj.weight": "model.safetensors", |
| "base_lm.layers.12.post_attention_layernorm.weight": "model.safetensors", |
| "base_lm.layers.12.self_attn.k_proj.weight": "model.safetensors", |
| "base_lm.layers.12.self_attn.o_proj.weight": "model.safetensors", |
| "base_lm.layers.12.self_attn.q_proj.weight": "model.safetensors", |
| "base_lm.layers.12.self_attn.v_proj.weight": "model.safetensors", |
| "base_lm.layers.13.input_layernorm.weight": "model.safetensors", |
| "base_lm.layers.13.mlp.down_proj.weight": "model.safetensors", |
| "base_lm.layers.13.mlp.gate_proj.weight": "model.safetensors", |
| "base_lm.layers.13.mlp.up_proj.weight": "model.safetensors", |
| "base_lm.layers.13.post_attention_layernorm.weight": "model.safetensors", |
| "base_lm.layers.13.self_attn.k_proj.weight": "model.safetensors", |
| "base_lm.layers.13.self_attn.o_proj.weight": "model.safetensors", |
| "base_lm.layers.13.self_attn.q_proj.weight": "model.safetensors", |
| "base_lm.layers.13.self_attn.v_proj.weight": "model.safetensors", |
| "base_lm.layers.14.input_layernorm.weight": "model.safetensors", |
| "base_lm.layers.14.mlp.down_proj.weight": "model.safetensors", |
| "base_lm.layers.14.mlp.gate_proj.weight": "model.safetensors", |
| "base_lm.layers.14.mlp.up_proj.weight": "model.safetensors", |
| "base_lm.layers.14.post_attention_layernorm.weight": "model.safetensors", |
| "base_lm.layers.14.self_attn.k_proj.weight": "model.safetensors", |
| "base_lm.layers.14.self_attn.o_proj.weight": "model.safetensors", |
| "base_lm.layers.14.self_attn.q_proj.weight": "model.safetensors", |
| "base_lm.layers.14.self_attn.v_proj.weight": "model.safetensors", |
| "base_lm.layers.15.input_layernorm.weight": "model.safetensors", |
| "base_lm.layers.15.mlp.down_proj.weight": "model.safetensors", |
| "base_lm.layers.15.mlp.gate_proj.weight": "model.safetensors", |
| "base_lm.layers.15.mlp.up_proj.weight": "model.safetensors", |
| "base_lm.layers.15.post_attention_layernorm.weight": "model.safetensors", |
| "base_lm.layers.15.self_attn.k_proj.weight": "model.safetensors", |
| "base_lm.layers.15.self_attn.o_proj.weight": "model.safetensors", |
| "base_lm.layers.15.self_attn.q_proj.weight": "model.safetensors", |
| "base_lm.layers.15.self_attn.v_proj.weight": "model.safetensors", |
| "base_lm.layers.16.input_layernorm.weight": "model.safetensors", |
| "base_lm.layers.16.mlp.down_proj.weight": "model.safetensors", |
| "base_lm.layers.16.mlp.gate_proj.weight": "model.safetensors", |
| "base_lm.layers.16.mlp.up_proj.weight": "model.safetensors", |
| "base_lm.layers.16.post_attention_layernorm.weight": "model.safetensors", |
| "base_lm.layers.16.self_attn.k_proj.weight": "model.safetensors", |
| "base_lm.layers.16.self_attn.o_proj.weight": "model.safetensors", |
| "base_lm.layers.16.self_attn.q_proj.weight": "model.safetensors", |
| "base_lm.layers.16.self_attn.v_proj.weight": "model.safetensors", |
| "base_lm.layers.17.input_layernorm.weight": "model.safetensors", |
| "base_lm.layers.17.mlp.down_proj.weight": "model.safetensors", |
| "base_lm.layers.17.mlp.gate_proj.weight": "model.safetensors", |
| "base_lm.layers.17.mlp.up_proj.weight": "model.safetensors", |
| "base_lm.layers.17.post_attention_layernorm.weight": "model.safetensors", |
| "base_lm.layers.17.self_attn.k_proj.weight": "model.safetensors", |
| "base_lm.layers.17.self_attn.o_proj.weight": "model.safetensors", |
| "base_lm.layers.17.self_attn.q_proj.weight": "model.safetensors", |
| "base_lm.layers.17.self_attn.v_proj.weight": "model.safetensors", |
| "base_lm.layers.18.input_layernorm.weight": "model.safetensors", |
| "base_lm.layers.18.mlp.down_proj.weight": "model.safetensors", |
| "base_lm.layers.18.mlp.gate_proj.weight": "model.safetensors", |
| "base_lm.layers.18.mlp.up_proj.weight": "model.safetensors", |
| "base_lm.layers.18.post_attention_layernorm.weight": "model.safetensors", |
| "base_lm.layers.18.self_attn.k_proj.weight": "model.safetensors", |
| "base_lm.layers.18.self_attn.o_proj.weight": "model.safetensors", |
| "base_lm.layers.18.self_attn.q_proj.weight": "model.safetensors", |
| "base_lm.layers.18.self_attn.v_proj.weight": "model.safetensors", |
| "base_lm.layers.19.input_layernorm.weight": "model.safetensors", |
| "base_lm.layers.19.mlp.down_proj.weight": "model.safetensors", |
| "base_lm.layers.19.mlp.gate_proj.weight": "model.safetensors", |
| "base_lm.layers.19.mlp.up_proj.weight": "model.safetensors", |
| "base_lm.layers.19.post_attention_layernorm.weight": "model.safetensors", |
| "base_lm.layers.19.self_attn.k_proj.weight": "model.safetensors", |
| "base_lm.layers.19.self_attn.o_proj.weight": "model.safetensors", |
| "base_lm.layers.19.self_attn.q_proj.weight": "model.safetensors", |
| "base_lm.layers.19.self_attn.v_proj.weight": "model.safetensors", |
| "base_lm.layers.2.input_layernorm.weight": "model.safetensors", |
| "base_lm.layers.2.mlp.down_proj.weight": "model.safetensors", |
| "base_lm.layers.2.mlp.gate_proj.weight": "model.safetensors", |
| "base_lm.layers.2.mlp.up_proj.weight": "model.safetensors", |
| "base_lm.layers.2.post_attention_layernorm.weight": "model.safetensors", |
| "base_lm.layers.2.self_attn.k_proj.weight": "model.safetensors", |
| "base_lm.layers.2.self_attn.o_proj.weight": "model.safetensors", |
| "base_lm.layers.2.self_attn.q_proj.weight": "model.safetensors", |
| "base_lm.layers.2.self_attn.v_proj.weight": "model.safetensors", |
| "base_lm.layers.20.input_layernorm.weight": "model.safetensors", |
| "base_lm.layers.20.mlp.down_proj.weight": "model.safetensors", |
| "base_lm.layers.20.mlp.gate_proj.weight": "model.safetensors", |
| "base_lm.layers.20.mlp.up_proj.weight": "model.safetensors", |
| "base_lm.layers.20.post_attention_layernorm.weight": "model.safetensors", |
| "base_lm.layers.20.self_attn.k_proj.weight": "model.safetensors", |
| "base_lm.layers.20.self_attn.o_proj.weight": "model.safetensors", |
| "base_lm.layers.20.self_attn.q_proj.weight": "model.safetensors", |
| "base_lm.layers.20.self_attn.v_proj.weight": "model.safetensors", |
| "base_lm.layers.21.input_layernorm.weight": "model.safetensors", |
| "base_lm.layers.21.mlp.down_proj.weight": "model.safetensors", |
| "base_lm.layers.21.mlp.gate_proj.weight": "model.safetensors", |
| "base_lm.layers.21.mlp.up_proj.weight": "model.safetensors", |
| "base_lm.layers.21.post_attention_layernorm.weight": "model.safetensors", |
| "base_lm.layers.21.self_attn.k_proj.weight": "model.safetensors", |
| "base_lm.layers.21.self_attn.o_proj.weight": "model.safetensors", |
| "base_lm.layers.21.self_attn.q_proj.weight": "model.safetensors", |
| "base_lm.layers.21.self_attn.v_proj.weight": "model.safetensors", |
| "base_lm.layers.22.input_layernorm.weight": "model.safetensors", |
| "base_lm.layers.22.mlp.down_proj.weight": "model.safetensors", |
| "base_lm.layers.22.mlp.gate_proj.weight": "model.safetensors", |
| "base_lm.layers.22.mlp.up_proj.weight": "model.safetensors", |
| "base_lm.layers.22.post_attention_layernorm.weight": "model.safetensors", |
| "base_lm.layers.22.self_attn.k_proj.weight": "model.safetensors", |
| "base_lm.layers.22.self_attn.o_proj.weight": "model.safetensors", |
| "base_lm.layers.22.self_attn.q_proj.weight": "model.safetensors", |
| "base_lm.layers.22.self_attn.v_proj.weight": "model.safetensors", |
| "base_lm.layers.23.input_layernorm.weight": "model.safetensors", |
| "base_lm.layers.23.mlp.down_proj.weight": "model.safetensors", |
| "base_lm.layers.23.mlp.gate_proj.weight": "model.safetensors", |
| "base_lm.layers.23.mlp.up_proj.weight": "model.safetensors", |
| "base_lm.layers.23.post_attention_layernorm.weight": "model.safetensors", |
| "base_lm.layers.23.self_attn.k_proj.weight": "model.safetensors", |
| "base_lm.layers.23.self_attn.o_proj.weight": "model.safetensors", |
| "base_lm.layers.23.self_attn.q_proj.weight": "model.safetensors", |
| "base_lm.layers.23.self_attn.v_proj.weight": "model.safetensors", |
| "base_lm.layers.3.input_layernorm.weight": "model.safetensors", |
| "base_lm.layers.3.mlp.down_proj.weight": "model.safetensors", |
| "base_lm.layers.3.mlp.gate_proj.weight": "model.safetensors", |
| "base_lm.layers.3.mlp.up_proj.weight": "model.safetensors", |
| "base_lm.layers.3.post_attention_layernorm.weight": "model.safetensors", |
| "base_lm.layers.3.self_attn.k_proj.weight": "model.safetensors", |
| "base_lm.layers.3.self_attn.o_proj.weight": "model.safetensors", |
| "base_lm.layers.3.self_attn.q_proj.weight": "model.safetensors", |
| "base_lm.layers.3.self_attn.v_proj.weight": "model.safetensors", |
| "base_lm.layers.4.input_layernorm.weight": "model.safetensors", |
| "base_lm.layers.4.mlp.down_proj.weight": "model.safetensors", |
| "base_lm.layers.4.mlp.gate_proj.weight": "model.safetensors", |
| "base_lm.layers.4.mlp.up_proj.weight": "model.safetensors", |
| "base_lm.layers.4.post_attention_layernorm.weight": "model.safetensors", |
| "base_lm.layers.4.self_attn.k_proj.weight": "model.safetensors", |
| "base_lm.layers.4.self_attn.o_proj.weight": "model.safetensors", |
| "base_lm.layers.4.self_attn.q_proj.weight": "model.safetensors", |
| "base_lm.layers.4.self_attn.v_proj.weight": "model.safetensors", |
| "base_lm.layers.5.input_layernorm.weight": "model.safetensors", |
| "base_lm.layers.5.mlp.down_proj.weight": "model.safetensors", |
| "base_lm.layers.5.mlp.gate_proj.weight": "model.safetensors", |
| "base_lm.layers.5.mlp.up_proj.weight": "model.safetensors", |
| "base_lm.layers.5.post_attention_layernorm.weight": "model.safetensors", |
| "base_lm.layers.5.self_attn.k_proj.weight": "model.safetensors", |
| "base_lm.layers.5.self_attn.o_proj.weight": "model.safetensors", |
| "base_lm.layers.5.self_attn.q_proj.weight": "model.safetensors", |
| "base_lm.layers.5.self_attn.v_proj.weight": "model.safetensors", |
| "base_lm.layers.6.input_layernorm.weight": "model.safetensors", |
| "base_lm.layers.6.mlp.down_proj.weight": "model.safetensors", |
| "base_lm.layers.6.mlp.gate_proj.weight": "model.safetensors", |
| "base_lm.layers.6.mlp.up_proj.weight": "model.safetensors", |
| "base_lm.layers.6.post_attention_layernorm.weight": "model.safetensors", |
| "base_lm.layers.6.self_attn.k_proj.weight": "model.safetensors", |
| "base_lm.layers.6.self_attn.o_proj.weight": "model.safetensors", |
| "base_lm.layers.6.self_attn.q_proj.weight": "model.safetensors", |
| "base_lm.layers.6.self_attn.v_proj.weight": "model.safetensors", |
| "base_lm.layers.7.input_layernorm.weight": "model.safetensors", |
| "base_lm.layers.7.mlp.down_proj.weight": "model.safetensors", |
| "base_lm.layers.7.mlp.gate_proj.weight": "model.safetensors", |
| "base_lm.layers.7.mlp.up_proj.weight": "model.safetensors", |
| "base_lm.layers.7.post_attention_layernorm.weight": "model.safetensors", |
| "base_lm.layers.7.self_attn.k_proj.weight": "model.safetensors", |
| "base_lm.layers.7.self_attn.o_proj.weight": "model.safetensors", |
| "base_lm.layers.7.self_attn.q_proj.weight": "model.safetensors", |
| "base_lm.layers.7.self_attn.v_proj.weight": "model.safetensors", |
| "base_lm.layers.8.input_layernorm.weight": "model.safetensors", |
| "base_lm.layers.8.mlp.down_proj.weight": "model.safetensors", |
| "base_lm.layers.8.mlp.gate_proj.weight": "model.safetensors", |
| "base_lm.layers.8.mlp.up_proj.weight": "model.safetensors", |
| "base_lm.layers.8.post_attention_layernorm.weight": "model.safetensors", |
| "base_lm.layers.8.self_attn.k_proj.weight": "model.safetensors", |
| "base_lm.layers.8.self_attn.o_proj.weight": "model.safetensors", |
| "base_lm.layers.8.self_attn.q_proj.weight": "model.safetensors", |
| "base_lm.layers.8.self_attn.v_proj.weight": "model.safetensors", |
| "base_lm.layers.9.input_layernorm.weight": "model.safetensors", |
| "base_lm.layers.9.mlp.down_proj.weight": "model.safetensors", |
| "base_lm.layers.9.mlp.gate_proj.weight": "model.safetensors", |
| "base_lm.layers.9.mlp.up_proj.weight": "model.safetensors", |
| "base_lm.layers.9.post_attention_layernorm.weight": "model.safetensors", |
| "base_lm.layers.9.self_attn.k_proj.weight": "model.safetensors", |
| "base_lm.layers.9.self_attn.o_proj.weight": "model.safetensors", |
| "base_lm.layers.9.self_attn.q_proj.weight": "model.safetensors", |
| "base_lm.layers.9.self_attn.v_proj.weight": "model.safetensors", |
| "base_lm.norm.weight": "model.safetensors", |
| "base_lm.rope.inv_freq": "model.safetensors", |
| "base_lm.rope.long_factor": "model.safetensors", |
| "base_lm.rope.short_factor": "model.safetensors", |
| "enc_to_lm_proj.bias": "model.safetensors", |
| "enc_to_lm_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.cond_proj.bias": "model.safetensors", |
| "feat_decoder.estimator.cond_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.0.input_layernorm.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.0.mlp.down_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.0.mlp.gate_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.0.mlp.up_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.0.post_attention_layernorm.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.0.self_attn.k_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.0.self_attn.o_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.0.self_attn.q_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.0.self_attn.v_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.1.input_layernorm.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.1.mlp.down_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.1.mlp.gate_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.1.mlp.up_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.1.post_attention_layernorm.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.1.self_attn.k_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.1.self_attn.o_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.1.self_attn.q_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.1.self_attn.v_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.2.input_layernorm.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.2.mlp.down_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.2.mlp.gate_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.2.mlp.up_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.2.post_attention_layernorm.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.2.self_attn.k_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.2.self_attn.o_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.2.self_attn.q_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.2.self_attn.v_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.3.input_layernorm.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.3.mlp.down_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.3.mlp.gate_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.3.mlp.up_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.3.post_attention_layernorm.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.3.self_attn.k_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.3.self_attn.o_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.3.self_attn.q_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.3.self_attn.v_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.4.input_layernorm.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.4.mlp.down_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.4.mlp.gate_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.4.mlp.up_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.4.post_attention_layernorm.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.4.self_attn.k_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.4.self_attn.o_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.4.self_attn.q_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.4.self_attn.v_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.5.input_layernorm.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.5.mlp.down_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.5.mlp.gate_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.5.mlp.up_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.5.post_attention_layernorm.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.5.self_attn.k_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.5.self_attn.o_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.5.self_attn.q_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.5.self_attn.v_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.6.input_layernorm.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.6.mlp.down_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.6.mlp.gate_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.6.mlp.up_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.6.post_attention_layernorm.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.6.self_attn.k_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.6.self_attn.o_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.6.self_attn.q_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.6.self_attn.v_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.7.input_layernorm.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.7.mlp.down_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.7.mlp.gate_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.7.mlp.up_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.7.post_attention_layernorm.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.7.self_attn.k_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.7.self_attn.o_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.7.self_attn.q_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.layers.7.self_attn.v_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.norm.weight": "model.safetensors", |
| "feat_decoder.estimator.decoder.rope.inv_freq": "model.safetensors", |
| "feat_decoder.estimator.decoder.rope.long_factor": "model.safetensors", |
| "feat_decoder.estimator.decoder.rope.short_factor": "model.safetensors", |
| "feat_decoder.estimator.delta_time_mlp.linear_1.bias": "model.safetensors", |
| "feat_decoder.estimator.delta_time_mlp.linear_1.weight": "model.safetensors", |
| "feat_decoder.estimator.delta_time_mlp.linear_2.bias": "model.safetensors", |
| "feat_decoder.estimator.delta_time_mlp.linear_2.weight": "model.safetensors", |
| "feat_decoder.estimator.in_proj.bias": "model.safetensors", |
| "feat_decoder.estimator.in_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.out_proj.bias": "model.safetensors", |
| "feat_decoder.estimator.out_proj.weight": "model.safetensors", |
| "feat_decoder.estimator.time_mlp.linear_1.bias": "model.safetensors", |
| "feat_decoder.estimator.time_mlp.linear_1.weight": "model.safetensors", |
| "feat_decoder.estimator.time_mlp.linear_2.bias": "model.safetensors", |
| "feat_decoder.estimator.time_mlp.linear_2.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.0.input_layernorm.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.0.mlp.down_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.0.mlp.gate_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.0.mlp.up_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.0.post_attention_layernorm.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.0.self_attn.k_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.0.self_attn.o_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.0.self_attn.q_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.0.self_attn.v_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.1.input_layernorm.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.1.mlp.down_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.1.mlp.gate_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.1.mlp.up_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.1.post_attention_layernorm.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.1.self_attn.k_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.1.self_attn.o_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.1.self_attn.q_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.1.self_attn.v_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.2.input_layernorm.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.2.mlp.down_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.2.mlp.gate_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.2.mlp.up_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.2.post_attention_layernorm.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.2.self_attn.k_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.2.self_attn.o_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.2.self_attn.q_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.2.self_attn.v_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.3.input_layernorm.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.3.mlp.down_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.3.mlp.gate_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.3.mlp.up_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.3.post_attention_layernorm.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.3.self_attn.k_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.3.self_attn.o_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.3.self_attn.q_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.3.self_attn.v_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.4.input_layernorm.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.4.mlp.down_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.4.mlp.gate_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.4.mlp.up_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.4.post_attention_layernorm.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.4.self_attn.k_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.4.self_attn.o_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.4.self_attn.q_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.4.self_attn.v_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.5.input_layernorm.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.5.mlp.down_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.5.mlp.gate_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.5.mlp.up_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.5.post_attention_layernorm.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.5.self_attn.k_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.5.self_attn.o_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.5.self_attn.q_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.5.self_attn.v_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.6.input_layernorm.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.6.mlp.down_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.6.mlp.gate_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.6.mlp.up_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.6.post_attention_layernorm.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.6.self_attn.k_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.6.self_attn.o_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.6.self_attn.q_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.6.self_attn.v_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.7.input_layernorm.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.7.mlp.down_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.7.mlp.gate_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.7.mlp.up_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.7.post_attention_layernorm.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.7.self_attn.k_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.7.self_attn.o_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.7.self_attn.q_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.layers.7.self_attn.v_proj.weight": "model.safetensors", |
| "feat_encoder.encoder.norm.weight": "model.safetensors", |
| "feat_encoder.encoder.rope.inv_freq": "model.safetensors", |
| "feat_encoder.encoder.rope.long_factor": "model.safetensors", |
| "feat_encoder.encoder.rope.short_factor": "model.safetensors", |
| "feat_encoder.in_proj.bias": "model.safetensors", |
| "feat_encoder.in_proj.weight": "model.safetensors", |
| "feat_encoder.special_token": "model.safetensors", |
| "fsq_layer.in_proj.bias": "model.safetensors", |
| "fsq_layer.in_proj.weight": "model.safetensors", |
| "fsq_layer.out_proj.bias": "model.safetensors", |
| "fsq_layer.out_proj.weight": "model.safetensors", |
| "lm_to_dit_proj.bias": "model.safetensors", |
| "lm_to_dit_proj.weight": "model.safetensors", |
| "res_to_dit_proj.bias": "model.safetensors", |
| "res_to_dit_proj.weight": "model.safetensors", |
| "residual_lm.layers.0.input_layernorm.weight": "model.safetensors", |
| "residual_lm.layers.0.mlp.down_proj.weight": "model.safetensors", |
| "residual_lm.layers.0.mlp.gate_proj.weight": "model.safetensors", |
| "residual_lm.layers.0.mlp.up_proj.weight": "model.safetensors", |
| "residual_lm.layers.0.post_attention_layernorm.weight": "model.safetensors", |
| "residual_lm.layers.0.self_attn.k_proj.weight": "model.safetensors", |
| "residual_lm.layers.0.self_attn.o_proj.weight": "model.safetensors", |
| "residual_lm.layers.0.self_attn.q_proj.weight": "model.safetensors", |
| "residual_lm.layers.0.self_attn.v_proj.weight": "model.safetensors", |
| "residual_lm.layers.1.input_layernorm.weight": "model.safetensors", |
| "residual_lm.layers.1.mlp.down_proj.weight": "model.safetensors", |
| "residual_lm.layers.1.mlp.gate_proj.weight": "model.safetensors", |
| "residual_lm.layers.1.mlp.up_proj.weight": "model.safetensors", |
| "residual_lm.layers.1.post_attention_layernorm.weight": "model.safetensors", |
| "residual_lm.layers.1.self_attn.k_proj.weight": "model.safetensors", |
| "residual_lm.layers.1.self_attn.o_proj.weight": "model.safetensors", |
| "residual_lm.layers.1.self_attn.q_proj.weight": "model.safetensors", |
| "residual_lm.layers.1.self_attn.v_proj.weight": "model.safetensors", |
| "residual_lm.layers.2.input_layernorm.weight": "model.safetensors", |
| "residual_lm.layers.2.mlp.down_proj.weight": "model.safetensors", |
| "residual_lm.layers.2.mlp.gate_proj.weight": "model.safetensors", |
| "residual_lm.layers.2.mlp.up_proj.weight": "model.safetensors", |
| "residual_lm.layers.2.post_attention_layernorm.weight": "model.safetensors", |
| "residual_lm.layers.2.self_attn.k_proj.weight": "model.safetensors", |
| "residual_lm.layers.2.self_attn.o_proj.weight": "model.safetensors", |
| "residual_lm.layers.2.self_attn.q_proj.weight": "model.safetensors", |
| "residual_lm.layers.2.self_attn.v_proj.weight": "model.safetensors", |
| "residual_lm.layers.3.input_layernorm.weight": "model.safetensors", |
| "residual_lm.layers.3.mlp.down_proj.weight": "model.safetensors", |
| "residual_lm.layers.3.mlp.gate_proj.weight": "model.safetensors", |
| "residual_lm.layers.3.mlp.up_proj.weight": "model.safetensors", |
| "residual_lm.layers.3.post_attention_layernorm.weight": "model.safetensors", |
| "residual_lm.layers.3.self_attn.k_proj.weight": "model.safetensors", |
| "residual_lm.layers.3.self_attn.o_proj.weight": "model.safetensors", |
| "residual_lm.layers.3.self_attn.q_proj.weight": "model.safetensors", |
| "residual_lm.layers.3.self_attn.v_proj.weight": "model.safetensors", |
| "residual_lm.layers.4.input_layernorm.weight": "model.safetensors", |
| "residual_lm.layers.4.mlp.down_proj.weight": "model.safetensors", |
| "residual_lm.layers.4.mlp.gate_proj.weight": "model.safetensors", |
| "residual_lm.layers.4.mlp.up_proj.weight": "model.safetensors", |
| "residual_lm.layers.4.post_attention_layernorm.weight": "model.safetensors", |
| "residual_lm.layers.4.self_attn.k_proj.weight": "model.safetensors", |
| "residual_lm.layers.4.self_attn.o_proj.weight": "model.safetensors", |
| "residual_lm.layers.4.self_attn.q_proj.weight": "model.safetensors", |
| "residual_lm.layers.4.self_attn.v_proj.weight": "model.safetensors", |
| "residual_lm.layers.5.input_layernorm.weight": "model.safetensors", |
| "residual_lm.layers.5.mlp.down_proj.weight": "model.safetensors", |
| "residual_lm.layers.5.mlp.gate_proj.weight": "model.safetensors", |
| "residual_lm.layers.5.mlp.up_proj.weight": "model.safetensors", |
| "residual_lm.layers.5.post_attention_layernorm.weight": "model.safetensors", |
| "residual_lm.layers.5.self_attn.k_proj.weight": "model.safetensors", |
| "residual_lm.layers.5.self_attn.o_proj.weight": "model.safetensors", |
| "residual_lm.layers.5.self_attn.q_proj.weight": "model.safetensors", |
| "residual_lm.layers.5.self_attn.v_proj.weight": "model.safetensors", |
| "residual_lm.layers.6.input_layernorm.weight": "model.safetensors", |
| "residual_lm.layers.6.mlp.down_proj.weight": "model.safetensors", |
| "residual_lm.layers.6.mlp.gate_proj.weight": "model.safetensors", |
| "residual_lm.layers.6.mlp.up_proj.weight": "model.safetensors", |
| "residual_lm.layers.6.post_attention_layernorm.weight": "model.safetensors", |
| "residual_lm.layers.6.self_attn.k_proj.weight": "model.safetensors", |
| "residual_lm.layers.6.self_attn.o_proj.weight": "model.safetensors", |
| "residual_lm.layers.6.self_attn.q_proj.weight": "model.safetensors", |
| "residual_lm.layers.6.self_attn.v_proj.weight": "model.safetensors", |
| "residual_lm.layers.7.input_layernorm.weight": "model.safetensors", |
| "residual_lm.layers.7.mlp.down_proj.weight": "model.safetensors", |
| "residual_lm.layers.7.mlp.gate_proj.weight": "model.safetensors", |
| "residual_lm.layers.7.mlp.up_proj.weight": "model.safetensors", |
| "residual_lm.layers.7.post_attention_layernorm.weight": "model.safetensors", |
| "residual_lm.layers.7.self_attn.k_proj.weight": "model.safetensors", |
| "residual_lm.layers.7.self_attn.o_proj.weight": "model.safetensors", |
| "residual_lm.layers.7.self_attn.q_proj.weight": "model.safetensors", |
| "residual_lm.layers.7.self_attn.v_proj.weight": "model.safetensors", |
| "residual_lm.norm.weight": "model.safetensors", |
| "residual_lm.rope.inv_freq": "model.safetensors", |
| "residual_lm.rope.long_factor": "model.safetensors", |
| "residual_lm.rope.short_factor": "model.safetensors", |
| "stop_head.weight": "model.safetensors", |
| "stop_proj.bias": "model.safetensors", |
| "stop_proj.weight": "model.safetensors" |
| } |
| } |
