| { |
| "metadata": { |
| "total_size": 269662528, |
| "total_parameters": 438349392 |
| }, |
| "weight_map": { |
| "model.embed_tokens.biases": "model.safetensors", |
| "model.embed_tokens.scales": "model.safetensors", |
| "model.embed_tokens.weight": "model.safetensors", |
| "model.layers.0.attention_layernorm.weight": "model.safetensors", |
| "model.layers.0.feedforward_layernorm.weight": "model.safetensors", |
| "model.layers.0.mlp.act_fn.alpha_n": "model.safetensors", |
| "model.layers.0.mlp.act_fn.alpha_p": "model.safetensors", |
| "model.layers.0.mlp.act_fn.beta": "model.safetensors", |
| "model.layers.0.mlp.act_fn.eps": "model.safetensors", |
| "model.layers.0.mlp.down_proj.biases": "model.safetensors", |
| "model.layers.0.mlp.down_proj.scales": "model.safetensors", |
| "model.layers.0.mlp.down_proj.weight": "model.safetensors", |
| "model.layers.0.mlp.up_proj.biases": "model.safetensors", |
| "model.layers.0.mlp.up_proj.scales": "model.safetensors", |
| "model.layers.0.mlp.up_proj.weight": "model.safetensors", |
| "model.layers.0.self_attn.k_norm.weight": "model.safetensors", |
| "model.layers.0.self_attn.k_proj.biases": "model.safetensors", |
| "model.layers.0.self_attn.k_proj.scales": "model.safetensors", |
| "model.layers.0.self_attn.k_proj.weight": "model.safetensors", |
| "model.layers.0.self_attn.o_proj.biases": "model.safetensors", |
| "model.layers.0.self_attn.o_proj.scales": "model.safetensors", |
| "model.layers.0.self_attn.o_proj.weight": "model.safetensors", |
| "model.layers.0.self_attn.q_norm.weight": "model.safetensors", |
| "model.layers.0.self_attn.q_proj.biases": "model.safetensors", |
| "model.layers.0.self_attn.q_proj.scales": "model.safetensors", |
| "model.layers.0.self_attn.q_proj.weight": "model.safetensors", |
| "model.layers.0.self_attn.v_proj.biases": "model.safetensors", |
| "model.layers.0.self_attn.v_proj.scales": "model.safetensors", |
| "model.layers.0.self_attn.v_proj.weight": "model.safetensors", |
| "model.layers.1.attention_layernorm.weight": "model.safetensors", |
| "model.layers.1.feedforward_layernorm.weight": "model.safetensors", |
| "model.layers.1.mlp.act_fn.alpha_n": "model.safetensors", |
| "model.layers.1.mlp.act_fn.alpha_p": "model.safetensors", |
| "model.layers.1.mlp.act_fn.beta": "model.safetensors", |
| "model.layers.1.mlp.act_fn.eps": "model.safetensors", |
| "model.layers.1.mlp.down_proj.biases": "model.safetensors", |
| "model.layers.1.mlp.down_proj.scales": "model.safetensors", |
| "model.layers.1.mlp.down_proj.weight": "model.safetensors", |
| "model.layers.1.mlp.up_proj.biases": "model.safetensors", |
| "model.layers.1.mlp.up_proj.scales": "model.safetensors", |
| "model.layers.1.mlp.up_proj.weight": "model.safetensors", |
| "model.layers.1.self_attn.k_norm.weight": "model.safetensors", |
| "model.layers.1.self_attn.k_proj.biases": "model.safetensors", |
| "model.layers.1.self_attn.k_proj.scales": "model.safetensors", |
| "model.layers.1.self_attn.k_proj.weight": "model.safetensors", |
| "model.layers.1.self_attn.o_proj.biases": "model.safetensors", |
| "model.layers.1.self_attn.o_proj.scales": "model.safetensors", |
| "model.layers.1.self_attn.o_proj.weight": "model.safetensors", |
| "model.layers.1.self_attn.q_norm.weight": "model.safetensors", |
| "model.layers.1.self_attn.q_proj.biases": "model.safetensors", |
| "model.layers.1.self_attn.q_proj.scales": "model.safetensors", |
| "model.layers.1.self_attn.q_proj.weight": "model.safetensors", |
| "model.layers.1.self_attn.v_proj.biases": "model.safetensors", |
| "model.layers.1.self_attn.v_proj.scales": "model.safetensors", |
| "model.layers.1.self_attn.v_proj.weight": "model.safetensors", |
| "model.layers.10.attention_layernorm.weight": "model.safetensors", |
| "model.layers.10.feedforward_layernorm.weight": "model.safetensors", |
| "model.layers.10.mlp.act_fn.alpha_n": "model.safetensors", |
| "model.layers.10.mlp.act_fn.alpha_p": "model.safetensors", |
| "model.layers.10.mlp.act_fn.beta": "model.safetensors", |
| "model.layers.10.mlp.act_fn.eps": "model.safetensors", |
| "model.layers.10.mlp.down_proj.biases": "model.safetensors", |
| "model.layers.10.mlp.down_proj.scales": "model.safetensors", |
| "model.layers.10.mlp.down_proj.weight": "model.safetensors", |
| "model.layers.10.mlp.up_proj.biases": "model.safetensors", |
| "model.layers.10.mlp.up_proj.scales": "model.safetensors", |
| "model.layers.10.mlp.up_proj.weight": "model.safetensors", |
| "model.layers.10.self_attn.k_norm.weight": "model.safetensors", |
| "model.layers.10.self_attn.k_proj.biases": "model.safetensors", |
| "model.layers.10.self_attn.k_proj.scales": "model.safetensors", |
| "model.layers.10.self_attn.k_proj.weight": "model.safetensors", |
| "model.layers.10.self_attn.o_proj.biases": "model.safetensors", |
| "model.layers.10.self_attn.o_proj.scales": "model.safetensors", |
| "model.layers.10.self_attn.o_proj.weight": "model.safetensors", |
| "model.layers.10.self_attn.q_norm.weight": "model.safetensors", |
| "model.layers.10.self_attn.q_proj.biases": "model.safetensors", |
| "model.layers.10.self_attn.q_proj.scales": "model.safetensors", |
| "model.layers.10.self_attn.q_proj.weight": "model.safetensors", |
| "model.layers.10.self_attn.v_proj.biases": "model.safetensors", |
| "model.layers.10.self_attn.v_proj.scales": "model.safetensors", |
| "model.layers.10.self_attn.v_proj.weight": "model.safetensors", |
| "model.layers.11.attention_layernorm.weight": "model.safetensors", |
| "model.layers.11.feedforward_layernorm.weight": "model.safetensors", |
| "model.layers.11.mlp.act_fn.alpha_n": "model.safetensors", |
| "model.layers.11.mlp.act_fn.alpha_p": "model.safetensors", |
| "model.layers.11.mlp.act_fn.beta": "model.safetensors", |
| "model.layers.11.mlp.act_fn.eps": "model.safetensors", |
| "model.layers.11.mlp.down_proj.biases": "model.safetensors", |
| "model.layers.11.mlp.down_proj.scales": "model.safetensors", |
| "model.layers.11.mlp.down_proj.weight": "model.safetensors", |
| "model.layers.11.mlp.up_proj.biases": "model.safetensors", |
| "model.layers.11.mlp.up_proj.scales": "model.safetensors", |
| "model.layers.11.mlp.up_proj.weight": "model.safetensors", |
| "model.layers.11.self_attn.k_norm.weight": "model.safetensors", |
| "model.layers.11.self_attn.k_proj.biases": "model.safetensors", |
| "model.layers.11.self_attn.k_proj.scales": "model.safetensors", |
| "model.layers.11.self_attn.k_proj.weight": "model.safetensors", |
| "model.layers.11.self_attn.o_proj.biases": "model.safetensors", |
| "model.layers.11.self_attn.o_proj.scales": "model.safetensors", |
| "model.layers.11.self_attn.o_proj.weight": "model.safetensors", |
| "model.layers.11.self_attn.q_norm.weight": "model.safetensors", |
| "model.layers.11.self_attn.q_proj.biases": "model.safetensors", |
| "model.layers.11.self_attn.q_proj.scales": "model.safetensors", |
| "model.layers.11.self_attn.q_proj.weight": "model.safetensors", |
| "model.layers.11.self_attn.v_proj.biases": "model.safetensors", |
| "model.layers.11.self_attn.v_proj.scales": "model.safetensors", |
| "model.layers.11.self_attn.v_proj.weight": "model.safetensors", |
| "model.layers.12.attention_layernorm.weight": "model.safetensors", |
| "model.layers.12.feedforward_layernorm.weight": "model.safetensors", |
| "model.layers.12.mlp.act_fn.alpha_n": "model.safetensors", |
| "model.layers.12.mlp.act_fn.alpha_p": "model.safetensors", |
| "model.layers.12.mlp.act_fn.beta": "model.safetensors", |
| "model.layers.12.mlp.act_fn.eps": "model.safetensors", |
| "model.layers.12.mlp.down_proj.biases": "model.safetensors", |
| "model.layers.12.mlp.down_proj.scales": "model.safetensors", |
| "model.layers.12.mlp.down_proj.weight": "model.safetensors", |
| "model.layers.12.mlp.up_proj.biases": "model.safetensors", |
| "model.layers.12.mlp.up_proj.scales": "model.safetensors", |
| "model.layers.12.mlp.up_proj.weight": "model.safetensors", |
| "model.layers.12.self_attn.k_norm.weight": "model.safetensors", |
| "model.layers.12.self_attn.k_proj.biases": "model.safetensors", |
| "model.layers.12.self_attn.k_proj.scales": "model.safetensors", |
| "model.layers.12.self_attn.k_proj.weight": "model.safetensors", |
| "model.layers.12.self_attn.o_proj.biases": "model.safetensors", |
| "model.layers.12.self_attn.o_proj.scales": "model.safetensors", |
| "model.layers.12.self_attn.o_proj.weight": "model.safetensors", |
| "model.layers.12.self_attn.q_norm.weight": "model.safetensors", |
| "model.layers.12.self_attn.q_proj.biases": "model.safetensors", |
| "model.layers.12.self_attn.q_proj.scales": "model.safetensors", |
| "model.layers.12.self_attn.q_proj.weight": "model.safetensors", |
| "model.layers.12.self_attn.v_proj.biases": "model.safetensors", |
| "model.layers.12.self_attn.v_proj.scales": "model.safetensors", |
| "model.layers.12.self_attn.v_proj.weight": "model.safetensors", |
| "model.layers.13.attention_layernorm.weight": "model.safetensors", |
| "model.layers.13.feedforward_layernorm.weight": "model.safetensors", |
| "model.layers.13.mlp.act_fn.alpha_n": "model.safetensors", |
| "model.layers.13.mlp.act_fn.alpha_p": "model.safetensors", |
| "model.layers.13.mlp.act_fn.beta": "model.safetensors", |
| "model.layers.13.mlp.act_fn.eps": "model.safetensors", |
| "model.layers.13.mlp.down_proj.biases": "model.safetensors", |
| "model.layers.13.mlp.down_proj.scales": "model.safetensors", |
| "model.layers.13.mlp.down_proj.weight": "model.safetensors", |
| "model.layers.13.mlp.up_proj.biases": "model.safetensors", |
| "model.layers.13.mlp.up_proj.scales": "model.safetensors", |
| "model.layers.13.mlp.up_proj.weight": "model.safetensors", |
| "model.layers.13.self_attn.k_norm.weight": "model.safetensors", |
| "model.layers.13.self_attn.k_proj.biases": "model.safetensors", |
| "model.layers.13.self_attn.k_proj.scales": "model.safetensors", |
| "model.layers.13.self_attn.k_proj.weight": "model.safetensors", |
| "model.layers.13.self_attn.o_proj.biases": "model.safetensors", |
| "model.layers.13.self_attn.o_proj.scales": "model.safetensors", |
| "model.layers.13.self_attn.o_proj.weight": "model.safetensors", |
| "model.layers.13.self_attn.q_norm.weight": "model.safetensors", |
| "model.layers.13.self_attn.q_proj.biases": "model.safetensors", |
| "model.layers.13.self_attn.q_proj.scales": "model.safetensors", |
| "model.layers.13.self_attn.q_proj.weight": "model.safetensors", |
| "model.layers.13.self_attn.v_proj.biases": "model.safetensors", |
| "model.layers.13.self_attn.v_proj.scales": "model.safetensors", |
| "model.layers.13.self_attn.v_proj.weight": "model.safetensors", |
| "model.layers.14.attention_layernorm.weight": "model.safetensors", |
| "model.layers.14.feedforward_layernorm.weight": "model.safetensors", |
| "model.layers.14.mlp.act_fn.alpha_n": "model.safetensors", |
| "model.layers.14.mlp.act_fn.alpha_p": "model.safetensors", |
| "model.layers.14.mlp.act_fn.beta": "model.safetensors", |
| "model.layers.14.mlp.act_fn.eps": "model.safetensors", |
| "model.layers.14.mlp.down_proj.biases": "model.safetensors", |
| "model.layers.14.mlp.down_proj.scales": "model.safetensors", |
| "model.layers.14.mlp.down_proj.weight": "model.safetensors", |
| "model.layers.14.mlp.up_proj.biases": "model.safetensors", |
| "model.layers.14.mlp.up_proj.scales": "model.safetensors", |
| "model.layers.14.mlp.up_proj.weight": "model.safetensors", |
| "model.layers.14.self_attn.k_norm.weight": "model.safetensors", |
| "model.layers.14.self_attn.k_proj.biases": "model.safetensors", |
| "model.layers.14.self_attn.k_proj.scales": "model.safetensors", |
| "model.layers.14.self_attn.k_proj.weight": "model.safetensors", |
| "model.layers.14.self_attn.o_proj.biases": "model.safetensors", |
| "model.layers.14.self_attn.o_proj.scales": "model.safetensors", |
| "model.layers.14.self_attn.o_proj.weight": "model.safetensors", |
| "model.layers.14.self_attn.q_norm.weight": "model.safetensors", |
| "model.layers.14.self_attn.q_proj.biases": "model.safetensors", |
| "model.layers.14.self_attn.q_proj.scales": "model.safetensors", |
| "model.layers.14.self_attn.q_proj.weight": "model.safetensors", |
| "model.layers.14.self_attn.v_proj.biases": "model.safetensors", |
| "model.layers.14.self_attn.v_proj.scales": "model.safetensors", |
| "model.layers.14.self_attn.v_proj.weight": "model.safetensors", |
| "model.layers.15.attention_layernorm.weight": "model.safetensors", |
| "model.layers.15.feedforward_layernorm.weight": "model.safetensors", |
| "model.layers.15.mlp.act_fn.alpha_n": "model.safetensors", |
| "model.layers.15.mlp.act_fn.alpha_p": "model.safetensors", |
| "model.layers.15.mlp.act_fn.beta": "model.safetensors", |
| "model.layers.15.mlp.act_fn.eps": "model.safetensors", |
| "model.layers.15.mlp.down_proj.biases": "model.safetensors", |
| "model.layers.15.mlp.down_proj.scales": "model.safetensors", |
| "model.layers.15.mlp.down_proj.weight": "model.safetensors", |
| "model.layers.15.mlp.up_proj.biases": "model.safetensors", |
| "model.layers.15.mlp.up_proj.scales": "model.safetensors", |
| "model.layers.15.mlp.up_proj.weight": "model.safetensors", |
| "model.layers.15.self_attn.k_norm.weight": "model.safetensors", |
| "model.layers.15.self_attn.k_proj.biases": "model.safetensors", |
| "model.layers.15.self_attn.k_proj.scales": "model.safetensors", |
| "model.layers.15.self_attn.k_proj.weight": "model.safetensors", |
| "model.layers.15.self_attn.o_proj.biases": "model.safetensors", |
| "model.layers.15.self_attn.o_proj.scales": "model.safetensors", |
| "model.layers.15.self_attn.o_proj.weight": "model.safetensors", |
| "model.layers.15.self_attn.q_norm.weight": "model.safetensors", |
| "model.layers.15.self_attn.q_proj.biases": "model.safetensors", |
| "model.layers.15.self_attn.q_proj.scales": "model.safetensors", |
| "model.layers.15.self_attn.q_proj.weight": "model.safetensors", |
| "model.layers.15.self_attn.v_proj.biases": "model.safetensors", |
| "model.layers.15.self_attn.v_proj.scales": "model.safetensors", |
| "model.layers.15.self_attn.v_proj.weight": "model.safetensors", |
| "model.layers.16.attention_layernorm.weight": "model.safetensors", |
| "model.layers.16.feedforward_layernorm.weight": "model.safetensors", |
| "model.layers.16.mlp.act_fn.alpha_n": "model.safetensors", |
| "model.layers.16.mlp.act_fn.alpha_p": "model.safetensors", |
| "model.layers.16.mlp.act_fn.beta": "model.safetensors", |
| "model.layers.16.mlp.act_fn.eps": "model.safetensors", |
| "model.layers.16.mlp.down_proj.biases": "model.safetensors", |
| "model.layers.16.mlp.down_proj.scales": "model.safetensors", |
| "model.layers.16.mlp.down_proj.weight": "model.safetensors", |
| "model.layers.16.mlp.up_proj.biases": "model.safetensors", |
| "model.layers.16.mlp.up_proj.scales": "model.safetensors", |
| "model.layers.16.mlp.up_proj.weight": "model.safetensors", |
| "model.layers.16.self_attn.k_norm.weight": "model.safetensors", |
| "model.layers.16.self_attn.k_proj.biases": "model.safetensors", |
| "model.layers.16.self_attn.k_proj.scales": "model.safetensors", |
| "model.layers.16.self_attn.k_proj.weight": "model.safetensors", |
| "model.layers.16.self_attn.o_proj.biases": "model.safetensors", |
| "model.layers.16.self_attn.o_proj.scales": "model.safetensors", |
| "model.layers.16.self_attn.o_proj.weight": "model.safetensors", |
| "model.layers.16.self_attn.q_norm.weight": "model.safetensors", |
| "model.layers.16.self_attn.q_proj.biases": "model.safetensors", |
| "model.layers.16.self_attn.q_proj.scales": "model.safetensors", |
| "model.layers.16.self_attn.q_proj.weight": "model.safetensors", |
| "model.layers.16.self_attn.v_proj.biases": "model.safetensors", |
| "model.layers.16.self_attn.v_proj.scales": "model.safetensors", |
| "model.layers.16.self_attn.v_proj.weight": "model.safetensors", |
| "model.layers.17.attention_layernorm.weight": "model.safetensors", |
| "model.layers.17.feedforward_layernorm.weight": "model.safetensors", |
| "model.layers.17.mlp.act_fn.alpha_n": "model.safetensors", |
| "model.layers.17.mlp.act_fn.alpha_p": "model.safetensors", |
| "model.layers.17.mlp.act_fn.beta": "model.safetensors", |
| "model.layers.17.mlp.act_fn.eps": "model.safetensors", |
| "model.layers.17.mlp.down_proj.biases": "model.safetensors", |
| "model.layers.17.mlp.down_proj.scales": "model.safetensors", |
| "model.layers.17.mlp.down_proj.weight": "model.safetensors", |
| "model.layers.17.mlp.up_proj.biases": "model.safetensors", |
| "model.layers.17.mlp.up_proj.scales": "model.safetensors", |
| "model.layers.17.mlp.up_proj.weight": "model.safetensors", |
| "model.layers.17.self_attn.k_norm.weight": "model.safetensors", |
| "model.layers.17.self_attn.k_proj.biases": "model.safetensors", |
| "model.layers.17.self_attn.k_proj.scales": "model.safetensors", |
| "model.layers.17.self_attn.k_proj.weight": "model.safetensors", |
| "model.layers.17.self_attn.o_proj.biases": "model.safetensors", |
| "model.layers.17.self_attn.o_proj.scales": "model.safetensors", |
| "model.layers.17.self_attn.o_proj.weight": "model.safetensors", |
| "model.layers.17.self_attn.q_norm.weight": "model.safetensors", |
| "model.layers.17.self_attn.q_proj.biases": "model.safetensors", |
| "model.layers.17.self_attn.q_proj.scales": "model.safetensors", |
| "model.layers.17.self_attn.q_proj.weight": "model.safetensors", |
| "model.layers.17.self_attn.v_proj.biases": "model.safetensors", |
| "model.layers.17.self_attn.v_proj.scales": "model.safetensors", |
| "model.layers.17.self_attn.v_proj.weight": "model.safetensors", |
| "model.layers.18.attention_layernorm.weight": "model.safetensors", |
| "model.layers.18.feedforward_layernorm.weight": "model.safetensors", |
| "model.layers.18.mlp.act_fn.alpha_n": "model.safetensors", |
| "model.layers.18.mlp.act_fn.alpha_p": "model.safetensors", |
| "model.layers.18.mlp.act_fn.beta": "model.safetensors", |
| "model.layers.18.mlp.act_fn.eps": "model.safetensors", |
| "model.layers.18.mlp.down_proj.biases": "model.safetensors", |
| "model.layers.18.mlp.down_proj.scales": "model.safetensors", |
| "model.layers.18.mlp.down_proj.weight": "model.safetensors", |
| "model.layers.18.mlp.up_proj.biases": "model.safetensors", |
| "model.layers.18.mlp.up_proj.scales": "model.safetensors", |
| "model.layers.18.mlp.up_proj.weight": "model.safetensors", |
| "model.layers.18.self_attn.k_norm.weight": "model.safetensors", |
| "model.layers.18.self_attn.k_proj.biases": "model.safetensors", |
| "model.layers.18.self_attn.k_proj.scales": "model.safetensors", |
| "model.layers.18.self_attn.k_proj.weight": "model.safetensors", |
| "model.layers.18.self_attn.o_proj.biases": "model.safetensors", |
| "model.layers.18.self_attn.o_proj.scales": "model.safetensors", |
| "model.layers.18.self_attn.o_proj.weight": "model.safetensors", |
| "model.layers.18.self_attn.q_norm.weight": "model.safetensors", |
| "model.layers.18.self_attn.q_proj.biases": "model.safetensors", |
| "model.layers.18.self_attn.q_proj.scales": "model.safetensors", |
| "model.layers.18.self_attn.q_proj.weight": "model.safetensors", |
| "model.layers.18.self_attn.v_proj.biases": "model.safetensors", |
| "model.layers.18.self_attn.v_proj.scales": "model.safetensors", |
| "model.layers.18.self_attn.v_proj.weight": "model.safetensors", |
| "model.layers.19.attention_layernorm.weight": "model.safetensors", |
| "model.layers.19.feedforward_layernorm.weight": "model.safetensors", |
| "model.layers.19.mlp.act_fn.alpha_n": "model.safetensors", |
| "model.layers.19.mlp.act_fn.alpha_p": "model.safetensors", |
| "model.layers.19.mlp.act_fn.beta": "model.safetensors", |
| "model.layers.19.mlp.act_fn.eps": "model.safetensors", |
| "model.layers.19.mlp.down_proj.biases": "model.safetensors", |
| "model.layers.19.mlp.down_proj.scales": "model.safetensors", |
| "model.layers.19.mlp.down_proj.weight": "model.safetensors", |
| "model.layers.19.mlp.up_proj.biases": "model.safetensors", |
| "model.layers.19.mlp.up_proj.scales": "model.safetensors", |
| "model.layers.19.mlp.up_proj.weight": "model.safetensors", |
| "model.layers.19.self_attn.k_norm.weight": "model.safetensors", |
| "model.layers.19.self_attn.k_proj.biases": "model.safetensors", |
| "model.layers.19.self_attn.k_proj.scales": "model.safetensors", |
| "model.layers.19.self_attn.k_proj.weight": "model.safetensors", |
| "model.layers.19.self_attn.o_proj.biases": "model.safetensors", |
| "model.layers.19.self_attn.o_proj.scales": "model.safetensors", |
| "model.layers.19.self_attn.o_proj.weight": "model.safetensors", |
| "model.layers.19.self_attn.q_norm.weight": "model.safetensors", |
| "model.layers.19.self_attn.q_proj.biases": "model.safetensors", |
| "model.layers.19.self_attn.q_proj.scales": "model.safetensors", |
| "model.layers.19.self_attn.q_proj.weight": "model.safetensors", |
| "model.layers.19.self_attn.v_proj.biases": "model.safetensors", |
| "model.layers.19.self_attn.v_proj.scales": "model.safetensors", |
| "model.layers.19.self_attn.v_proj.weight": "model.safetensors", |
| "model.layers.2.attention_layernorm.weight": "model.safetensors", |
| "model.layers.2.feedforward_layernorm.weight": "model.safetensors", |
| "model.layers.2.mlp.act_fn.alpha_n": "model.safetensors", |
| "model.layers.2.mlp.act_fn.alpha_p": "model.safetensors", |
| "model.layers.2.mlp.act_fn.beta": "model.safetensors", |
| "model.layers.2.mlp.act_fn.eps": "model.safetensors", |
| "model.layers.2.mlp.down_proj.biases": "model.safetensors", |
| "model.layers.2.mlp.down_proj.scales": "model.safetensors", |
| "model.layers.2.mlp.down_proj.weight": "model.safetensors", |
| "model.layers.2.mlp.up_proj.biases": "model.safetensors", |
| "model.layers.2.mlp.up_proj.scales": "model.safetensors", |
| "model.layers.2.mlp.up_proj.weight": "model.safetensors", |
| "model.layers.2.self_attn.k_norm.weight": "model.safetensors", |
| "model.layers.2.self_attn.k_proj.biases": "model.safetensors", |
| "model.layers.2.self_attn.k_proj.scales": "model.safetensors", |
| "model.layers.2.self_attn.k_proj.weight": "model.safetensors", |
| "model.layers.2.self_attn.o_proj.biases": "model.safetensors", |
| "model.layers.2.self_attn.o_proj.scales": "model.safetensors", |
| "model.layers.2.self_attn.o_proj.weight": "model.safetensors", |
| "model.layers.2.self_attn.q_norm.weight": "model.safetensors", |
| "model.layers.2.self_attn.q_proj.biases": "model.safetensors", |
| "model.layers.2.self_attn.q_proj.scales": "model.safetensors", |
| "model.layers.2.self_attn.q_proj.weight": "model.safetensors", |
| "model.layers.2.self_attn.v_proj.biases": "model.safetensors", |
| "model.layers.2.self_attn.v_proj.scales": "model.safetensors", |
| "model.layers.2.self_attn.v_proj.weight": "model.safetensors", |
| "model.layers.3.attention_layernorm.weight": "model.safetensors", |
| "model.layers.3.feedforward_layernorm.weight": "model.safetensors", |
| "model.layers.3.mlp.act_fn.alpha_n": "model.safetensors", |
| "model.layers.3.mlp.act_fn.alpha_p": "model.safetensors", |
| "model.layers.3.mlp.act_fn.beta": "model.safetensors", |
| "model.layers.3.mlp.act_fn.eps": "model.safetensors", |
| "model.layers.3.mlp.down_proj.biases": "model.safetensors", |
| "model.layers.3.mlp.down_proj.scales": "model.safetensors", |
| "model.layers.3.mlp.down_proj.weight": "model.safetensors", |
| "model.layers.3.mlp.up_proj.biases": "model.safetensors", |
| "model.layers.3.mlp.up_proj.scales": "model.safetensors", |
| "model.layers.3.mlp.up_proj.weight": "model.safetensors", |
| "model.layers.3.self_attn.k_norm.weight": "model.safetensors", |
| "model.layers.3.self_attn.k_proj.biases": "model.safetensors", |
| "model.layers.3.self_attn.k_proj.scales": "model.safetensors", |
| "model.layers.3.self_attn.k_proj.weight": "model.safetensors", |
| "model.layers.3.self_attn.o_proj.biases": "model.safetensors", |
| "model.layers.3.self_attn.o_proj.scales": "model.safetensors", |
| "model.layers.3.self_attn.o_proj.weight": "model.safetensors", |
| "model.layers.3.self_attn.q_norm.weight": "model.safetensors", |
| "model.layers.3.self_attn.q_proj.biases": "model.safetensors", |
| "model.layers.3.self_attn.q_proj.scales": "model.safetensors", |
| "model.layers.3.self_attn.q_proj.weight": "model.safetensors", |
| "model.layers.3.self_attn.v_proj.biases": "model.safetensors", |
| "model.layers.3.self_attn.v_proj.scales": "model.safetensors", |
| "model.layers.3.self_attn.v_proj.weight": "model.safetensors", |
| "model.layers.4.attention_layernorm.weight": "model.safetensors", |
| "model.layers.4.feedforward_layernorm.weight": "model.safetensors", |
| "model.layers.4.mlp.act_fn.alpha_n": "model.safetensors", |
| "model.layers.4.mlp.act_fn.alpha_p": "model.safetensors", |
| "model.layers.4.mlp.act_fn.beta": "model.safetensors", |
| "model.layers.4.mlp.act_fn.eps": "model.safetensors", |
| "model.layers.4.mlp.down_proj.biases": "model.safetensors", |
| "model.layers.4.mlp.down_proj.scales": "model.safetensors", |
| "model.layers.4.mlp.down_proj.weight": "model.safetensors", |
| "model.layers.4.mlp.up_proj.biases": "model.safetensors", |
| "model.layers.4.mlp.up_proj.scales": "model.safetensors", |
| "model.layers.4.mlp.up_proj.weight": "model.safetensors", |
| "model.layers.4.self_attn.k_norm.weight": "model.safetensors", |
| "model.layers.4.self_attn.k_proj.biases": "model.safetensors", |
| "model.layers.4.self_attn.k_proj.scales": "model.safetensors", |
| "model.layers.4.self_attn.k_proj.weight": "model.safetensors", |
| "model.layers.4.self_attn.o_proj.biases": "model.safetensors", |
| "model.layers.4.self_attn.o_proj.scales": "model.safetensors", |
| "model.layers.4.self_attn.o_proj.weight": "model.safetensors", |
| "model.layers.4.self_attn.q_norm.weight": "model.safetensors", |
| "model.layers.4.self_attn.q_proj.biases": "model.safetensors", |
| "model.layers.4.self_attn.q_proj.scales": "model.safetensors", |
| "model.layers.4.self_attn.q_proj.weight": "model.safetensors", |
| "model.layers.4.self_attn.v_proj.biases": "model.safetensors", |
| "model.layers.4.self_attn.v_proj.scales": "model.safetensors", |
| "model.layers.4.self_attn.v_proj.weight": "model.safetensors", |
| "model.layers.5.attention_layernorm.weight": "model.safetensors", |
| "model.layers.5.feedforward_layernorm.weight": "model.safetensors", |
| "model.layers.5.mlp.act_fn.alpha_n": "model.safetensors", |
| "model.layers.5.mlp.act_fn.alpha_p": "model.safetensors", |
| "model.layers.5.mlp.act_fn.beta": "model.safetensors", |
| "model.layers.5.mlp.act_fn.eps": "model.safetensors", |
| "model.layers.5.mlp.down_proj.biases": "model.safetensors", |
| "model.layers.5.mlp.down_proj.scales": "model.safetensors", |
| "model.layers.5.mlp.down_proj.weight": "model.safetensors", |
| "model.layers.5.mlp.up_proj.biases": "model.safetensors", |
| "model.layers.5.mlp.up_proj.scales": "model.safetensors", |
| "model.layers.5.mlp.up_proj.weight": "model.safetensors", |
| "model.layers.5.self_attn.k_norm.weight": "model.safetensors", |
| "model.layers.5.self_attn.k_proj.biases": "model.safetensors", |
| "model.layers.5.self_attn.k_proj.scales": "model.safetensors", |
| "model.layers.5.self_attn.k_proj.weight": "model.safetensors", |
| "model.layers.5.self_attn.o_proj.biases": "model.safetensors", |
| "model.layers.5.self_attn.o_proj.scales": "model.safetensors", |
| "model.layers.5.self_attn.o_proj.weight": "model.safetensors", |
| "model.layers.5.self_attn.q_norm.weight": "model.safetensors", |
| "model.layers.5.self_attn.q_proj.biases": "model.safetensors", |
| "model.layers.5.self_attn.q_proj.scales": "model.safetensors", |
| "model.layers.5.self_attn.q_proj.weight": "model.safetensors", |
| "model.layers.5.self_attn.v_proj.biases": "model.safetensors", |
| "model.layers.5.self_attn.v_proj.scales": "model.safetensors", |
| "model.layers.5.self_attn.v_proj.weight": "model.safetensors", |
| "model.layers.6.attention_layernorm.weight": "model.safetensors", |
| "model.layers.6.feedforward_layernorm.weight": "model.safetensors", |
| "model.layers.6.mlp.act_fn.alpha_n": "model.safetensors", |
| "model.layers.6.mlp.act_fn.alpha_p": "model.safetensors", |
| "model.layers.6.mlp.act_fn.beta": "model.safetensors", |
| "model.layers.6.mlp.act_fn.eps": "model.safetensors", |
| "model.layers.6.mlp.down_proj.biases": "model.safetensors", |
| "model.layers.6.mlp.down_proj.scales": "model.safetensors", |
| "model.layers.6.mlp.down_proj.weight": "model.safetensors", |
| "model.layers.6.mlp.up_proj.biases": "model.safetensors", |
| "model.layers.6.mlp.up_proj.scales": "model.safetensors", |
| "model.layers.6.mlp.up_proj.weight": "model.safetensors", |
| "model.layers.6.self_attn.k_norm.weight": "model.safetensors", |
| "model.layers.6.self_attn.k_proj.biases": "model.safetensors", |
| "model.layers.6.self_attn.k_proj.scales": "model.safetensors", |
| "model.layers.6.self_attn.k_proj.weight": "model.safetensors", |
| "model.layers.6.self_attn.o_proj.biases": "model.safetensors", |
| "model.layers.6.self_attn.o_proj.scales": "model.safetensors", |
| "model.layers.6.self_attn.o_proj.weight": "model.safetensors", |
| "model.layers.6.self_attn.q_norm.weight": "model.safetensors", |
| "model.layers.6.self_attn.q_proj.biases": "model.safetensors", |
| "model.layers.6.self_attn.q_proj.scales": "model.safetensors", |
| "model.layers.6.self_attn.q_proj.weight": "model.safetensors", |
| "model.layers.6.self_attn.v_proj.biases": "model.safetensors", |
| "model.layers.6.self_attn.v_proj.scales": "model.safetensors", |
| "model.layers.6.self_attn.v_proj.weight": "model.safetensors", |
| "model.layers.7.attention_layernorm.weight": "model.safetensors", |
| "model.layers.7.feedforward_layernorm.weight": "model.safetensors", |
| "model.layers.7.mlp.act_fn.alpha_n": "model.safetensors", |
| "model.layers.7.mlp.act_fn.alpha_p": "model.safetensors", |
| "model.layers.7.mlp.act_fn.beta": "model.safetensors", |
| "model.layers.7.mlp.act_fn.eps": "model.safetensors", |
| "model.layers.7.mlp.down_proj.biases": "model.safetensors", |
| "model.layers.7.mlp.down_proj.scales": "model.safetensors", |
| "model.layers.7.mlp.down_proj.weight": "model.safetensors", |
| "model.layers.7.mlp.up_proj.biases": "model.safetensors", |
| "model.layers.7.mlp.up_proj.scales": "model.safetensors", |
| "model.layers.7.mlp.up_proj.weight": "model.safetensors", |
| "model.layers.7.self_attn.k_norm.weight": "model.safetensors", |
| "model.layers.7.self_attn.k_proj.biases": "model.safetensors", |
| "model.layers.7.self_attn.k_proj.scales": "model.safetensors", |
| "model.layers.7.self_attn.k_proj.weight": "model.safetensors", |
| "model.layers.7.self_attn.o_proj.biases": "model.safetensors", |
| "model.layers.7.self_attn.o_proj.scales": "model.safetensors", |
| "model.layers.7.self_attn.o_proj.weight": "model.safetensors", |
| "model.layers.7.self_attn.q_norm.weight": "model.safetensors", |
| "model.layers.7.self_attn.q_proj.biases": "model.safetensors", |
| "model.layers.7.self_attn.q_proj.scales": "model.safetensors", |
| "model.layers.7.self_attn.q_proj.weight": "model.safetensors", |
| "model.layers.7.self_attn.v_proj.biases": "model.safetensors", |
| "model.layers.7.self_attn.v_proj.scales": "model.safetensors", |
| "model.layers.7.self_attn.v_proj.weight": "model.safetensors", |
| "model.layers.8.attention_layernorm.weight": "model.safetensors", |
| "model.layers.8.feedforward_layernorm.weight": "model.safetensors", |
| "model.layers.8.mlp.act_fn.alpha_n": "model.safetensors", |
| "model.layers.8.mlp.act_fn.alpha_p": "model.safetensors", |
| "model.layers.8.mlp.act_fn.beta": "model.safetensors", |
| "model.layers.8.mlp.act_fn.eps": "model.safetensors", |
| "model.layers.8.mlp.down_proj.biases": "model.safetensors", |
| "model.layers.8.mlp.down_proj.scales": "model.safetensors", |
| "model.layers.8.mlp.down_proj.weight": "model.safetensors", |
| "model.layers.8.mlp.up_proj.biases": "model.safetensors", |
| "model.layers.8.mlp.up_proj.scales": "model.safetensors", |
| "model.layers.8.mlp.up_proj.weight": "model.safetensors", |
| "model.layers.8.self_attn.k_norm.weight": "model.safetensors", |
| "model.layers.8.self_attn.k_proj.biases": "model.safetensors", |
| "model.layers.8.self_attn.k_proj.scales": "model.safetensors", |
| "model.layers.8.self_attn.k_proj.weight": "model.safetensors", |
| "model.layers.8.self_attn.o_proj.biases": "model.safetensors", |
| "model.layers.8.self_attn.o_proj.scales": "model.safetensors", |
| "model.layers.8.self_attn.o_proj.weight": "model.safetensors", |
| "model.layers.8.self_attn.q_norm.weight": "model.safetensors", |
| "model.layers.8.self_attn.q_proj.biases": "model.safetensors", |
| "model.layers.8.self_attn.q_proj.scales": "model.safetensors", |
| "model.layers.8.self_attn.q_proj.weight": "model.safetensors", |
| "model.layers.8.self_attn.v_proj.biases": "model.safetensors", |
| "model.layers.8.self_attn.v_proj.scales": "model.safetensors", |
| "model.layers.8.self_attn.v_proj.weight": "model.safetensors", |
| "model.layers.9.attention_layernorm.weight": "model.safetensors", |
| "model.layers.9.feedforward_layernorm.weight": "model.safetensors", |
| "model.layers.9.mlp.act_fn.alpha_n": "model.safetensors", |
| "model.layers.9.mlp.act_fn.alpha_p": "model.safetensors", |
| "model.layers.9.mlp.act_fn.beta": "model.safetensors", |
| "model.layers.9.mlp.act_fn.eps": "model.safetensors", |
| "model.layers.9.mlp.down_proj.biases": "model.safetensors", |
| "model.layers.9.mlp.down_proj.scales": "model.safetensors", |
| "model.layers.9.mlp.down_proj.weight": "model.safetensors", |
| "model.layers.9.mlp.up_proj.biases": "model.safetensors", |
| "model.layers.9.mlp.up_proj.scales": "model.safetensors", |
| "model.layers.9.mlp.up_proj.weight": "model.safetensors", |
| "model.layers.9.self_attn.k_norm.weight": "model.safetensors", |
| "model.layers.9.self_attn.k_proj.biases": "model.safetensors", |
| "model.layers.9.self_attn.k_proj.scales": "model.safetensors", |
| "model.layers.9.self_attn.k_proj.weight": "model.safetensors", |
| "model.layers.9.self_attn.o_proj.biases": "model.safetensors", |
| "model.layers.9.self_attn.o_proj.scales": "model.safetensors", |
| "model.layers.9.self_attn.o_proj.weight": "model.safetensors", |
| "model.layers.9.self_attn.q_norm.weight": "model.safetensors", |
| "model.layers.9.self_attn.q_proj.biases": "model.safetensors", |
| "model.layers.9.self_attn.q_proj.scales": "model.safetensors", |
| "model.layers.9.self_attn.q_proj.weight": "model.safetensors", |
| "model.layers.9.self_attn.v_proj.biases": "model.safetensors", |
| "model.layers.9.self_attn.v_proj.scales": "model.safetensors", |
| "model.layers.9.self_attn.v_proj.weight": "model.safetensors", |
| "model.norm.weight": "model.safetensors" |
| } |
| } |
