| { |
| "metadata": { |
| "total_size": 1488822730 |
| }, |
| "weight_map": { |
| "model.embed_tokens.biases": "model.safetensors", |
| "model.embed_tokens.scales": "model.safetensors", |
| "model.embed_tokens.weight": "model.safetensors", |
| "model.layers.0.input_layernorm.weight": "model.safetensors", |
| "model.layers.0.mlp.experts.down_proj.bias": "model.safetensors", |
| "model.layers.0.mlp.experts.down_proj.biases": "model.safetensors", |
| "model.layers.0.mlp.experts.down_proj.scales": "model.safetensors", |
| "model.layers.0.mlp.experts.down_proj.weight": "model.safetensors", |
| "model.layers.0.mlp.experts.gate_proj.bias": "model.safetensors", |
| "model.layers.0.mlp.experts.gate_proj.biases": "model.safetensors", |
| "model.layers.0.mlp.experts.gate_proj.scales": "model.safetensors", |
| "model.layers.0.mlp.experts.gate_proj.weight": "model.safetensors", |
| "model.layers.0.mlp.experts.up_proj.bias": "model.safetensors", |
| "model.layers.0.mlp.experts.up_proj.biases": "model.safetensors", |
| "model.layers.0.mlp.experts.up_proj.scales": "model.safetensors", |
| "model.layers.0.mlp.experts.up_proj.weight": "model.safetensors", |
| "model.layers.0.mlp.router.bias": "model.safetensors", |
| "model.layers.0.mlp.router.biases": "model.safetensors", |
| "model.layers.0.mlp.router.scales": "model.safetensors", |
| "model.layers.0.mlp.router.weight": "model.safetensors", |
| "model.layers.0.post_attention_layernorm.weight": "model.safetensors", |
| "model.layers.0.self_attn.k_proj.bias": "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.bias": "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_proj.bias": "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.sinks": "model.safetensors", |
| "model.layers.0.self_attn.v_proj.bias": "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.input_layernorm.weight": "model.safetensors", |
| "model.layers.1.mlp.experts.down_proj.bias": "model.safetensors", |
| "model.layers.1.mlp.experts.down_proj.biases": "model.safetensors", |
| "model.layers.1.mlp.experts.down_proj.scales": "model.safetensors", |
| "model.layers.1.mlp.experts.down_proj.weight": "model.safetensors", |
| "model.layers.1.mlp.experts.gate_proj.bias": "model.safetensors", |
| "model.layers.1.mlp.experts.gate_proj.biases": "model.safetensors", |
| "model.layers.1.mlp.experts.gate_proj.scales": "model.safetensors", |
| "model.layers.1.mlp.experts.gate_proj.weight": "model.safetensors", |
| "model.layers.1.mlp.experts.up_proj.bias": "model.safetensors", |
| "model.layers.1.mlp.experts.up_proj.biases": "model.safetensors", |
| "model.layers.1.mlp.experts.up_proj.scales": "model.safetensors", |
| "model.layers.1.mlp.experts.up_proj.weight": "model.safetensors", |
| "model.layers.1.mlp.router.bias": "model.safetensors", |
| "model.layers.1.mlp.router.biases": "model.safetensors", |
| "model.layers.1.mlp.router.scales": "model.safetensors", |
| "model.layers.1.mlp.router.weight": "model.safetensors", |
| "model.layers.1.post_attention_layernorm.weight": "model.safetensors", |
| "model.layers.1.self_attn.k_proj.bias": "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.bias": "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_proj.bias": "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.sinks": "model.safetensors", |
| "model.layers.1.self_attn.v_proj.bias": "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.2.input_layernorm.weight": "model.safetensors", |
| "model.layers.2.mlp.experts.down_proj.bias": "model.safetensors", |
| "model.layers.2.mlp.experts.down_proj.biases": "model.safetensors", |
| "model.layers.2.mlp.experts.down_proj.scales": "model.safetensors", |
| "model.layers.2.mlp.experts.down_proj.weight": "model.safetensors", |
| "model.layers.2.mlp.experts.gate_proj.bias": "model.safetensors", |
| "model.layers.2.mlp.experts.gate_proj.biases": "model.safetensors", |
| "model.layers.2.mlp.experts.gate_proj.scales": "model.safetensors", |
| "model.layers.2.mlp.experts.gate_proj.weight": "model.safetensors", |
| "model.layers.2.mlp.experts.up_proj.bias": "model.safetensors", |
| "model.layers.2.mlp.experts.up_proj.biases": "model.safetensors", |
| "model.layers.2.mlp.experts.up_proj.scales": "model.safetensors", |
| "model.layers.2.mlp.experts.up_proj.weight": "model.safetensors", |
| "model.layers.2.mlp.router.bias": "model.safetensors", |
| "model.layers.2.mlp.router.biases": "model.safetensors", |
| "model.layers.2.mlp.router.scales": "model.safetensors", |
| "model.layers.2.mlp.router.weight": "model.safetensors", |
| "model.layers.2.post_attention_layernorm.weight": "model.safetensors", |
| "model.layers.2.self_attn.k_proj.bias": "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.bias": "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_proj.bias": "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.sinks": "model.safetensors", |
| "model.layers.2.self_attn.v_proj.bias": "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.input_layernorm.weight": "model.safetensors", |
| "model.layers.3.mlp.experts.down_proj.bias": "model.safetensors", |
| "model.layers.3.mlp.experts.down_proj.biases": "model.safetensors", |
| "model.layers.3.mlp.experts.down_proj.scales": "model.safetensors", |
| "model.layers.3.mlp.experts.down_proj.weight": "model.safetensors", |
| "model.layers.3.mlp.experts.gate_proj.bias": "model.safetensors", |
| "model.layers.3.mlp.experts.gate_proj.biases": "model.safetensors", |
| "model.layers.3.mlp.experts.gate_proj.scales": "model.safetensors", |
| "model.layers.3.mlp.experts.gate_proj.weight": "model.safetensors", |
| "model.layers.3.mlp.experts.up_proj.bias": "model.safetensors", |
| "model.layers.3.mlp.experts.up_proj.biases": "model.safetensors", |
| "model.layers.3.mlp.experts.up_proj.scales": "model.safetensors", |
| "model.layers.3.mlp.experts.up_proj.weight": "model.safetensors", |
| "model.layers.3.mlp.router.bias": "model.safetensors", |
| "model.layers.3.mlp.router.biases": "model.safetensors", |
| "model.layers.3.mlp.router.scales": "model.safetensors", |
| "model.layers.3.mlp.router.weight": "model.safetensors", |
| "model.layers.3.post_attention_layernorm.weight": "model.safetensors", |
| "model.layers.3.self_attn.k_proj.bias": "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.bias": "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_proj.bias": "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.sinks": "model.safetensors", |
| "model.layers.3.self_attn.v_proj.bias": "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.input_layernorm.weight": "model.safetensors", |
| "model.layers.4.mlp.experts.down_proj.bias": "model.safetensors", |
| "model.layers.4.mlp.experts.down_proj.biases": "model.safetensors", |
| "model.layers.4.mlp.experts.down_proj.scales": "model.safetensors", |
| "model.layers.4.mlp.experts.down_proj.weight": "model.safetensors", |
| "model.layers.4.mlp.experts.gate_proj.bias": "model.safetensors", |
| "model.layers.4.mlp.experts.gate_proj.biases": "model.safetensors", |
| "model.layers.4.mlp.experts.gate_proj.scales": "model.safetensors", |
| "model.layers.4.mlp.experts.gate_proj.weight": "model.safetensors", |
| "model.layers.4.mlp.experts.up_proj.bias": "model.safetensors", |
| "model.layers.4.mlp.experts.up_proj.biases": "model.safetensors", |
| "model.layers.4.mlp.experts.up_proj.scales": "model.safetensors", |
| "model.layers.4.mlp.experts.up_proj.weight": "model.safetensors", |
| "model.layers.4.mlp.router.bias": "model.safetensors", |
| "model.layers.4.mlp.router.biases": "model.safetensors", |
| "model.layers.4.mlp.router.scales": "model.safetensors", |
| "model.layers.4.mlp.router.weight": "model.safetensors", |
| "model.layers.4.post_attention_layernorm.weight": "model.safetensors", |
| "model.layers.4.self_attn.k_proj.bias": "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.bias": "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_proj.bias": "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.sinks": "model.safetensors", |
| "model.layers.4.self_attn.v_proj.bias": "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.input_layernorm.weight": "model.safetensors", |
| "model.layers.5.mlp.experts.down_proj.bias": "model.safetensors", |
| "model.layers.5.mlp.experts.down_proj.biases": "model.safetensors", |
| "model.layers.5.mlp.experts.down_proj.scales": "model.safetensors", |
| "model.layers.5.mlp.experts.down_proj.weight": "model.safetensors", |
| "model.layers.5.mlp.experts.gate_proj.bias": "model.safetensors", |
| "model.layers.5.mlp.experts.gate_proj.biases": "model.safetensors", |
| "model.layers.5.mlp.experts.gate_proj.scales": "model.safetensors", |
| "model.layers.5.mlp.experts.gate_proj.weight": "model.safetensors", |
| "model.layers.5.mlp.experts.up_proj.bias": "model.safetensors", |
| "model.layers.5.mlp.experts.up_proj.biases": "model.safetensors", |
| "model.layers.5.mlp.experts.up_proj.scales": "model.safetensors", |
| "model.layers.5.mlp.experts.up_proj.weight": "model.safetensors", |
| "model.layers.5.mlp.router.bias": "model.safetensors", |
| "model.layers.5.mlp.router.biases": "model.safetensors", |
| "model.layers.5.mlp.router.scales": "model.safetensors", |
| "model.layers.5.mlp.router.weight": "model.safetensors", |
| "model.layers.5.post_attention_layernorm.weight": "model.safetensors", |
| "model.layers.5.self_attn.k_proj.bias": "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.bias": "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_proj.bias": "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.sinks": "model.safetensors", |
| "model.layers.5.self_attn.v_proj.bias": "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.input_layernorm.weight": "model.safetensors", |
| "model.layers.6.mlp.experts.down_proj.bias": "model.safetensors", |
| "model.layers.6.mlp.experts.down_proj.biases": "model.safetensors", |
| "model.layers.6.mlp.experts.down_proj.scales": "model.safetensors", |
| "model.layers.6.mlp.experts.down_proj.weight": "model.safetensors", |
| "model.layers.6.mlp.experts.gate_proj.bias": "model.safetensors", |
| "model.layers.6.mlp.experts.gate_proj.biases": "model.safetensors", |
| "model.layers.6.mlp.experts.gate_proj.scales": "model.safetensors", |
| "model.layers.6.mlp.experts.gate_proj.weight": "model.safetensors", |
| "model.layers.6.mlp.experts.up_proj.bias": "model.safetensors", |
| "model.layers.6.mlp.experts.up_proj.biases": "model.safetensors", |
| "model.layers.6.mlp.experts.up_proj.scales": "model.safetensors", |
| "model.layers.6.mlp.experts.up_proj.weight": "model.safetensors", |
| "model.layers.6.mlp.router.bias": "model.safetensors", |
| "model.layers.6.mlp.router.biases": "model.safetensors", |
| "model.layers.6.mlp.router.scales": "model.safetensors", |
| "model.layers.6.mlp.router.weight": "model.safetensors", |
| "model.layers.6.post_attention_layernorm.weight": "model.safetensors", |
| "model.layers.6.self_attn.k_proj.bias": "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.bias": "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_proj.bias": "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.sinks": "model.safetensors", |
| "model.layers.6.self_attn.v_proj.bias": "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.input_layernorm.weight": "model.safetensors", |
| "model.layers.7.mlp.experts.down_proj.bias": "model.safetensors", |
| "model.layers.7.mlp.experts.down_proj.biases": "model.safetensors", |
| "model.layers.7.mlp.experts.down_proj.scales": "model.safetensors", |
| "model.layers.7.mlp.experts.down_proj.weight": "model.safetensors", |
| "model.layers.7.mlp.experts.gate_proj.bias": "model.safetensors", |
| "model.layers.7.mlp.experts.gate_proj.biases": "model.safetensors", |
| "model.layers.7.mlp.experts.gate_proj.scales": "model.safetensors", |
| "model.layers.7.mlp.experts.gate_proj.weight": "model.safetensors", |
| "model.layers.7.mlp.experts.up_proj.bias": "model.safetensors", |
| "model.layers.7.mlp.experts.up_proj.biases": "model.safetensors", |
| "model.layers.7.mlp.experts.up_proj.scales": "model.safetensors", |
| "model.layers.7.mlp.experts.up_proj.weight": "model.safetensors", |
| "model.layers.7.mlp.router.bias": "model.safetensors", |
| "model.layers.7.mlp.router.biases": "model.safetensors", |
| "model.layers.7.mlp.router.scales": "model.safetensors", |
| "model.layers.7.mlp.router.weight": "model.safetensors", |
| "model.layers.7.post_attention_layernorm.weight": "model.safetensors", |
| "model.layers.7.self_attn.k_proj.bias": "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.bias": "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_proj.bias": "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.sinks": "model.safetensors", |
| "model.layers.7.self_attn.v_proj.bias": "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.norm.weight": "model.safetensors", |
| "score.bias": "model.safetensors", |
| "score.biases": "model.safetensors", |
| "score.scales": "model.safetensors", |
| "score.weight": "model.safetensors" |
| } |
| } |
