{ "metadata": { "total_size": 29629309504 }, "weight_map": { "tok_emb.weight": "model-00001-of-00006.safetensors", "layers.0.attn_norm.weight": "model-00001-of-00006.safetensors", "layers.0.attn.wq.weight": "model-00001-of-00006.safetensors", "layers.0.attn.wk.weight": "model-00001-of-00006.safetensors", "layers.0.attn.wv.weight": "model-00001-of-00006.safetensors", "layers.0.attn.wo.weight": "model-00001-of-00006.safetensors", "layers.0.ffn_norm.weight": "model-00001-of-00006.safetensors", "layers.0.ffn.expert_usage": "model-00001-of-00006.safetensors", "layers.0.ffn.expert_age": "model-00001-of-00006.safetensors", "layers.0.ffn.total_tokens_seen": "model-00001-of-00006.safetensors", "layers.0.ffn.router.gate.weight": "model-00001-of-00006.safetensors", "layers.0.ffn.ec_router.gate.weight": "model-00001-of-00006.safetensors", "layers.0.ffn.experts.0.w_gate.weight": "model-00001-of-00006.safetensors", "layers.0.ffn.experts.0.w_up.weight": "model-00001-of-00006.safetensors", "layers.0.ffn.experts.0.w_down.weight": "model-00001-of-00006.safetensors", "layers.0.ffn.experts.1.w_gate.weight": "model-00001-of-00006.safetensors", "layers.0.ffn.experts.1.w_up.weight": "model-00001-of-00006.safetensors", "layers.0.ffn.experts.1.w_down.weight": "model-00001-of-00006.safetensors", "layers.0.ffn.experts.2.w_gate.weight": "model-00001-of-00006.safetensors", "layers.0.ffn.experts.2.w_up.weight": "model-00001-of-00006.safetensors", "layers.0.ffn.experts.2.w_down.weight": "model-00001-of-00006.safetensors", "layers.0.ffn.experts.3.w_gate.weight": "model-00001-of-00006.safetensors", "layers.0.ffn.experts.3.w_up.weight": "model-00001-of-00006.safetensors", "layers.0.ffn.experts.3.w_down.weight": "model-00001-of-00006.safetensors", "layers.1.attn_norm.weight": "model-00001-of-00006.safetensors", "layers.1.attn.wq.weight": "model-00001-of-00006.safetensors", "layers.1.attn.wk.weight": "model-00001-of-00006.safetensors", "layers.1.attn.wv.weight": "model-00001-of-00006.safetensors", "layers.1.attn.wo.weight": "model-00001-of-00006.safetensors", "layers.1.ffn_norm.weight": "model-00001-of-00006.safetensors", "layers.1.ffn.expert_usage": "model-00001-of-00006.safetensors", "layers.1.ffn.expert_age": "model-00001-of-00006.safetensors", "layers.1.ffn.total_tokens_seen": "model-00001-of-00006.safetensors", "layers.1.ffn.router.gate.weight": "model-00001-of-00006.safetensors", "layers.1.ffn.ec_router.gate.weight": "model-00001-of-00006.safetensors", "layers.1.ffn.experts.0.w_gate.weight": "model-00001-of-00006.safetensors", "layers.1.ffn.experts.0.w_up.weight": "model-00001-of-00006.safetensors", "layers.1.ffn.experts.0.w_down.weight": "model-00001-of-00006.safetensors", "layers.1.ffn.experts.1.w_gate.weight": "model-00001-of-00006.safetensors", "layers.1.ffn.experts.1.w_up.weight": "model-00001-of-00006.safetensors", "layers.1.ffn.experts.1.w_down.weight": "model-00001-of-00006.safetensors", "layers.1.ffn.experts.2.w_gate.weight": "model-00001-of-00006.safetensors", "layers.1.ffn.experts.2.w_up.weight": "model-00001-of-00006.safetensors", "layers.1.ffn.experts.2.w_down.weight": "model-00001-of-00006.safetensors", "layers.1.ffn.experts.3.w_gate.weight": "model-00001-of-00006.safetensors", "layers.1.ffn.experts.3.w_up.weight": "model-00001-of-00006.safetensors", "layers.1.ffn.experts.3.w_down.weight": "model-00001-of-00006.safetensors", "layers.2.attn_norm.weight": "model-00001-of-00006.safetensors", "layers.2.attn.wq.weight": "model-00001-of-00006.safetensors", "layers.2.attn.wk.weight": "model-00001-of-00006.safetensors", "layers.2.attn.wv.weight": "model-00001-of-00006.safetensors", "layers.2.attn.wo.weight": "model-00001-of-00006.safetensors", "layers.2.ffn_norm.weight": "model-00001-of-00006.safetensors", "layers.2.ffn.expert_usage": "model-00001-of-00006.safetensors", "layers.2.ffn.expert_age": "model-00001-of-00006.safetensors", "layers.2.ffn.total_tokens_seen": "model-00001-of-00006.safetensors", "layers.2.ffn.router.gate.weight": "model-00001-of-00006.safetensors", "layers.2.ffn.ec_router.gate.weight": "model-00001-of-00006.safetensors", "layers.2.ffn.experts.0.w_gate.weight": "model-00001-of-00006.safetensors", "layers.2.ffn.experts.0.w_up.weight": "model-00001-of-00006.safetensors", "layers.2.ffn.experts.0.w_down.weight": "model-00001-of-00006.safetensors", "layers.2.ffn.experts.1.w_gate.weight": "model-00001-of-00006.safetensors", "layers.2.ffn.experts.1.w_up.weight": "model-00001-of-00006.safetensors", "layers.2.ffn.experts.1.w_down.weight": "model-00001-of-00006.safetensors", "layers.2.ffn.experts.2.w_gate.weight": "model-00001-of-00006.safetensors", "layers.2.ffn.experts.2.w_up.weight": "model-00001-of-00006.safetensors", "layers.2.ffn.experts.2.w_down.weight": "model-00001-of-00006.safetensors", "layers.2.ffn.experts.3.w_gate.weight": "model-00001-of-00006.safetensors", "layers.2.ffn.experts.3.w_up.weight": "model-00001-of-00006.safetensors", "layers.2.ffn.experts.3.w_down.weight": "model-00001-of-00006.safetensors", "layers.3.attn_norm.weight": "model-00001-of-00006.safetensors", "layers.3.attn.wq.weight": "model-00001-of-00006.safetensors", "layers.3.attn.wk.weight": "model-00001-of-00006.safetensors", "layers.3.attn.wv.weight": "model-00001-of-00006.safetensors", "layers.3.attn.wo.weight": "model-00001-of-00006.safetensors", "layers.3.ffn_norm.weight": "model-00001-of-00006.safetensors", "layers.3.ffn.expert_usage": "model-00001-of-00006.safetensors", "layers.3.ffn.expert_age": "model-00001-of-00006.safetensors", "layers.3.ffn.total_tokens_seen": "model-00001-of-00006.safetensors", "layers.3.ffn.router.gate.weight": "model-00001-of-00006.safetensors", "layers.3.ffn.ec_router.gate.weight": "model-00001-of-00006.safetensors", "layers.3.ffn.experts.0.w_gate.weight": "model-00001-of-00006.safetensors", "layers.3.ffn.experts.0.w_up.weight": "model-00001-of-00006.safetensors", "layers.3.ffn.experts.0.w_down.weight": "model-00001-of-00006.safetensors", "layers.3.ffn.experts.1.w_gate.weight": "model-00001-of-00006.safetensors", "layers.3.ffn.experts.1.w_up.weight": "model-00001-of-00006.safetensors", "layers.3.ffn.experts.1.w_down.weight": "model-00001-of-00006.safetensors", "layers.3.ffn.experts.2.w_gate.weight": "model-00001-of-00006.safetensors", "layers.3.ffn.experts.2.w_up.weight": "model-00001-of-00006.safetensors", "layers.3.ffn.experts.2.w_down.weight": "model-00001-of-00006.safetensors", "layers.3.ffn.experts.3.w_gate.weight": "model-00001-of-00006.safetensors", "layers.3.ffn.experts.3.w_up.weight": "model-00002-of-00006.safetensors", "layers.3.ffn.experts.3.w_down.weight": "model-00002-of-00006.safetensors", "layers.4.attn_norm.weight": "model-00002-of-00006.safetensors", "layers.4.attn.wq.weight": "model-00002-of-00006.safetensors", "layers.4.attn.wk.weight": "model-00002-of-00006.safetensors", "layers.4.attn.wv.weight": "model-00002-of-00006.safetensors", "layers.4.attn.wo.weight": "model-00002-of-00006.safetensors", "layers.4.ffn_norm.weight": "model-00002-of-00006.safetensors", "layers.4.ffn.expert_usage": "model-00002-of-00006.safetensors", "layers.4.ffn.expert_age": "model-00002-of-00006.safetensors", "layers.4.ffn.total_tokens_seen": "model-00002-of-00006.safetensors", "layers.4.ffn.router.gate.weight": "model-00002-of-00006.safetensors", "layers.4.ffn.ec_router.gate.weight": "model-00002-of-00006.safetensors", "layers.4.ffn.experts.0.w_gate.weight": "model-00002-of-00006.safetensors", "layers.4.ffn.experts.0.w_up.weight": "model-00002-of-00006.safetensors", "layers.4.ffn.experts.0.w_down.weight": "model-00002-of-00006.safetensors", "layers.4.ffn.experts.1.w_gate.weight": "model-00002-of-00006.safetensors", "layers.4.ffn.experts.1.w_up.weight": "model-00002-of-00006.safetensors", "layers.4.ffn.experts.1.w_down.weight": "model-00002-of-00006.safetensors", "layers.4.ffn.experts.2.w_gate.weight": "model-00002-of-00006.safetensors", "layers.4.ffn.experts.2.w_up.weight": "model-00002-of-00006.safetensors", "layers.4.ffn.experts.2.w_down.weight": "model-00002-of-00006.safetensors", "layers.4.ffn.experts.3.w_gate.weight": "model-00002-of-00006.safetensors", "layers.4.ffn.experts.3.w_up.weight": "model-00002-of-00006.safetensors", "layers.4.ffn.experts.3.w_down.weight": "model-00002-of-00006.safetensors", "layers.5.attn_norm.weight": "model-00002-of-00006.safetensors", "layers.5.attn.wq.weight": "model-00002-of-00006.safetensors", "layers.5.attn.wk.weight": "model-00002-of-00006.safetensors", "layers.5.attn.wv.weight": "model-00002-of-00006.safetensors", "layers.5.attn.wo.weight": "model-00002-of-00006.safetensors", "layers.5.ffn_norm.weight": "model-00002-of-00006.safetensors", "layers.5.ffn.expert_usage": "model-00002-of-00006.safetensors", "layers.5.ffn.expert_age": "model-00002-of-00006.safetensors", "layers.5.ffn.total_tokens_seen": "model-00002-of-00006.safetensors", "layers.5.ffn.router.gate.weight": "model-00002-of-00006.safetensors", "layers.5.ffn.ec_router.gate.weight": "model-00002-of-00006.safetensors", "layers.5.ffn.experts.0.w_gate.weight": "model-00002-of-00006.safetensors", "layers.5.ffn.experts.0.w_up.weight": "model-00002-of-00006.safetensors", "layers.5.ffn.experts.0.w_down.weight": "model-00002-of-00006.safetensors", "layers.5.ffn.experts.1.w_gate.weight": "model-00002-of-00006.safetensors", "layers.5.ffn.experts.1.w_up.weight": "model-00002-of-00006.safetensors", "layers.5.ffn.experts.1.w_down.weight": "model-00002-of-00006.safetensors", "layers.5.ffn.experts.2.w_gate.weight": "model-00002-of-00006.safetensors", "layers.5.ffn.experts.2.w_up.weight": "model-00002-of-00006.safetensors", "layers.5.ffn.experts.2.w_down.weight": "model-00002-of-00006.safetensors", "layers.5.ffn.experts.3.w_gate.weight": "model-00002-of-00006.safetensors", "layers.5.ffn.experts.3.w_up.weight": "model-00002-of-00006.safetensors", "layers.5.ffn.experts.3.w_down.weight": "model-00002-of-00006.safetensors", "layers.6.attn_norm.weight": "model-00002-of-00006.safetensors", "layers.6.attn.wq.weight": "model-00002-of-00006.safetensors", "layers.6.attn.wk.weight": "model-00002-of-00006.safetensors", "layers.6.attn.wv.weight": "model-00002-of-00006.safetensors", "layers.6.attn.wo.weight": "model-00002-of-00006.safetensors", "layers.6.ffn_norm.weight": "model-00002-of-00006.safetensors", "layers.6.ffn.expert_usage": "model-00002-of-00006.safetensors", "layers.6.ffn.expert_age": "model-00002-of-00006.safetensors", "layers.6.ffn.total_tokens_seen": "model-00002-of-00006.safetensors", "layers.6.ffn.router.gate.weight": "model-00002-of-00006.safetensors", "layers.6.ffn.ec_router.gate.weight": "model-00002-of-00006.safetensors", "layers.6.ffn.experts.0.w_gate.weight": "model-00002-of-00006.safetensors", "layers.6.ffn.experts.0.w_up.weight": "model-00002-of-00006.safetensors", "layers.6.ffn.experts.0.w_down.weight": "model-00002-of-00006.safetensors", "layers.6.ffn.experts.1.w_gate.weight": "model-00002-of-00006.safetensors", "layers.6.ffn.experts.1.w_up.weight": "model-00002-of-00006.safetensors", "layers.6.ffn.experts.1.w_down.weight": "model-00002-of-00006.safetensors", "layers.6.ffn.experts.2.w_gate.weight": "model-00002-of-00006.safetensors", "layers.6.ffn.experts.2.w_up.weight": "model-00002-of-00006.safetensors", "layers.6.ffn.experts.2.w_down.weight": "model-00002-of-00006.safetensors", "layers.6.ffn.experts.3.w_gate.weight": "model-00002-of-00006.safetensors", "layers.6.ffn.experts.3.w_up.weight": "model-00002-of-00006.safetensors", "layers.6.ffn.experts.3.w_down.weight": "model-00002-of-00006.safetensors", "layers.7.attn_norm.weight": "model-00002-of-00006.safetensors", "layers.7.attn.wq.weight": "model-00002-of-00006.safetensors", "layers.7.attn.wk.weight": "model-00002-of-00006.safetensors", "layers.7.attn.wv.weight": "model-00002-of-00006.safetensors", "layers.7.attn.wo.weight": "model-00002-of-00006.safetensors", "layers.7.ffn_norm.weight": "model-00002-of-00006.safetensors", "layers.7.ffn.expert_usage": "model-00002-of-00006.safetensors", "layers.7.ffn.expert_age": "model-00002-of-00006.safetensors", "layers.7.ffn.total_tokens_seen": "model-00002-of-00006.safetensors", "layers.7.ffn.router.gate.weight": "model-00002-of-00006.safetensors", "layers.7.ffn.ec_router.gate.weight": "model-00002-of-00006.safetensors", "layers.7.ffn.experts.0.w_gate.weight": "model-00002-of-00006.safetensors", "layers.7.ffn.experts.0.w_up.weight": "model-00002-of-00006.safetensors", "layers.7.ffn.experts.0.w_down.weight": "model-00002-of-00006.safetensors", "layers.7.ffn.experts.1.w_gate.weight": "model-00002-of-00006.safetensors", "layers.7.ffn.experts.1.w_up.weight": "model-00002-of-00006.safetensors", "layers.7.ffn.experts.1.w_down.weight": "model-00002-of-00006.safetensors", "layers.7.ffn.experts.2.w_gate.weight": "model-00002-of-00006.safetensors", "layers.7.ffn.experts.2.w_up.weight": "model-00002-of-00006.safetensors", "layers.7.ffn.experts.2.w_down.weight": "model-00002-of-00006.safetensors", "layers.7.ffn.experts.3.w_gate.weight": "model-00002-of-00006.safetensors", "layers.7.ffn.experts.3.w_up.weight": "model-00002-of-00006.safetensors", "layers.7.ffn.experts.3.w_down.weight": "model-00002-of-00006.safetensors", "layers.8.attn_norm.weight": "model-00002-of-00006.safetensors", "layers.8.attn.wq.weight": "model-00002-of-00006.safetensors", "layers.8.attn.wk.weight": "model-00002-of-00006.safetensors", "layers.8.attn.wv.weight": "model-00002-of-00006.safetensors", "layers.8.attn.wo.weight": "model-00002-of-00006.safetensors", "layers.8.ffn_norm.weight": "model-00002-of-00006.safetensors", "layers.8.ffn.expert_usage": "model-00002-of-00006.safetensors", "layers.8.ffn.expert_age": "model-00002-of-00006.safetensors", "layers.8.ffn.total_tokens_seen": "model-00002-of-00006.safetensors", "layers.8.ffn.router.gate.weight": "model-00002-of-00006.safetensors", "layers.8.ffn.ec_router.gate.weight": "model-00002-of-00006.safetensors", "layers.8.ffn.experts.0.w_gate.weight": "model-00002-of-00006.safetensors", "layers.8.ffn.experts.0.w_up.weight": "model-00002-of-00006.safetensors", "layers.8.ffn.experts.0.w_down.weight": "model-00002-of-00006.safetensors", "layers.8.ffn.experts.1.w_gate.weight": "model-00002-of-00006.safetensors", "layers.8.ffn.experts.1.w_up.weight": "model-00003-of-00006.safetensors", "layers.8.ffn.experts.1.w_down.weight": "model-00003-of-00006.safetensors", "layers.8.ffn.experts.2.w_gate.weight": "model-00003-of-00006.safetensors", "layers.8.ffn.experts.2.w_up.weight": "model-00003-of-00006.safetensors", "layers.8.ffn.experts.2.w_down.weight": "model-00003-of-00006.safetensors", "layers.8.ffn.experts.3.w_gate.weight": "model-00003-of-00006.safetensors", "layers.8.ffn.experts.3.w_up.weight": "model-00003-of-00006.safetensors", "layers.8.ffn.experts.3.w_down.weight": "model-00003-of-00006.safetensors", "layers.9.attn_norm.weight": "model-00003-of-00006.safetensors", "layers.9.attn.wq.weight": "model-00003-of-00006.safetensors", "layers.9.attn.wk.weight": "model-00003-of-00006.safetensors", "layers.9.attn.wv.weight": "model-00003-of-00006.safetensors", "layers.9.attn.wo.weight": "model-00003-of-00006.safetensors", "layers.9.ffn_norm.weight": "model-00003-of-00006.safetensors", "layers.9.ffn.expert_usage": "model-00003-of-00006.safetensors", "layers.9.ffn.expert_age": "model-00003-of-00006.safetensors", "layers.9.ffn.total_tokens_seen": "model-00003-of-00006.safetensors", "layers.9.ffn.router.gate.weight": "model-00003-of-00006.safetensors", "layers.9.ffn.ec_router.gate.weight": "model-00003-of-00006.safetensors", "layers.9.ffn.experts.0.w_gate.weight": "model-00003-of-00006.safetensors", "layers.9.ffn.experts.0.w_up.weight": "model-00003-of-00006.safetensors", "layers.9.ffn.experts.0.w_down.weight": "model-00003-of-00006.safetensors", "layers.9.ffn.experts.1.w_gate.weight": "model-00003-of-00006.safetensors", "layers.9.ffn.experts.1.w_up.weight": "model-00003-of-00006.safetensors", "layers.9.ffn.experts.1.w_down.weight": "model-00003-of-00006.safetensors", "layers.9.ffn.experts.2.w_gate.weight": "model-00003-of-00006.safetensors", "layers.9.ffn.experts.2.w_up.weight": "model-00003-of-00006.safetensors", "layers.9.ffn.experts.2.w_down.weight": "model-00003-of-00006.safetensors", "layers.9.ffn.experts.3.w_gate.weight": "model-00003-of-00006.safetensors", "layers.9.ffn.experts.3.w_up.weight": "model-00003-of-00006.safetensors", "layers.9.ffn.experts.3.w_down.weight": "model-00003-of-00006.safetensors", "layers.10.attn_norm.weight": "model-00003-of-00006.safetensors", "layers.10.attn.wq.weight": "model-00003-of-00006.safetensors", "layers.10.attn.wk.weight": "model-00003-of-00006.safetensors", "layers.10.attn.wv.weight": "model-00003-of-00006.safetensors", "layers.10.attn.wo.weight": "model-00003-of-00006.safetensors", "layers.10.ffn_norm.weight": "model-00003-of-00006.safetensors", "layers.10.ffn.expert_usage": "model-00003-of-00006.safetensors", "layers.10.ffn.expert_age": "model-00003-of-00006.safetensors", "layers.10.ffn.total_tokens_seen": "model-00003-of-00006.safetensors", "layers.10.ffn.router.gate.weight": "model-00003-of-00006.safetensors", "layers.10.ffn.ec_router.gate.weight": "model-00003-of-00006.safetensors", "layers.10.ffn.experts.0.w_gate.weight": "model-00003-of-00006.safetensors", "layers.10.ffn.experts.0.w_up.weight": "model-00003-of-00006.safetensors", "layers.10.ffn.experts.0.w_down.weight": "model-00003-of-00006.safetensors", "layers.10.ffn.experts.1.w_gate.weight": "model-00003-of-00006.safetensors", "layers.10.ffn.experts.1.w_up.weight": "model-00003-of-00006.safetensors", "layers.10.ffn.experts.1.w_down.weight": "model-00003-of-00006.safetensors", "layers.10.ffn.experts.2.w_gate.weight": "model-00003-of-00006.safetensors", "layers.10.ffn.experts.2.w_up.weight": "model-00003-of-00006.safetensors", "layers.10.ffn.experts.2.w_down.weight": "model-00003-of-00006.safetensors", "layers.10.ffn.experts.3.w_gate.weight": "model-00003-of-00006.safetensors", "layers.10.ffn.experts.3.w_up.weight": "model-00003-of-00006.safetensors", "layers.10.ffn.experts.3.w_down.weight": "model-00003-of-00006.safetensors", "layers.11.attn_norm.weight": "model-00003-of-00006.safetensors", "layers.11.attn.wq.weight": "model-00003-of-00006.safetensors", "layers.11.attn.wk.weight": "model-00003-of-00006.safetensors", "layers.11.attn.wv.weight": "model-00003-of-00006.safetensors", "layers.11.attn.wo.weight": "model-00003-of-00006.safetensors", "layers.11.ffn_norm.weight": "model-00003-of-00006.safetensors", "layers.11.ffn.expert_usage": "model-00003-of-00006.safetensors", "layers.11.ffn.expert_age": "model-00003-of-00006.safetensors", "layers.11.ffn.total_tokens_seen": "model-00003-of-00006.safetensors", "layers.11.ffn.router.gate.weight": "model-00003-of-00006.safetensors", "layers.11.ffn.ec_router.gate.weight": "model-00003-of-00006.safetensors", "layers.11.ffn.experts.0.w_gate.weight": "model-00003-of-00006.safetensors", "layers.11.ffn.experts.0.w_up.weight": "model-00003-of-00006.safetensors", "layers.11.ffn.experts.0.w_down.weight": "model-00003-of-00006.safetensors", "layers.11.ffn.experts.1.w_gate.weight": "model-00003-of-00006.safetensors", "layers.11.ffn.experts.1.w_up.weight": "model-00003-of-00006.safetensors", "layers.11.ffn.experts.1.w_down.weight": "model-00003-of-00006.safetensors", "layers.11.ffn.experts.2.w_gate.weight": "model-00003-of-00006.safetensors", "layers.11.ffn.experts.2.w_up.weight": "model-00003-of-00006.safetensors", "layers.11.ffn.experts.2.w_down.weight": "model-00003-of-00006.safetensors", "layers.11.ffn.experts.3.w_gate.weight": "model-00003-of-00006.safetensors", "layers.11.ffn.experts.3.w_up.weight": "model-00003-of-00006.safetensors", "layers.11.ffn.experts.3.w_down.weight": "model-00003-of-00006.safetensors", "layers.12.attn_norm.weight": "model-00003-of-00006.safetensors", "layers.12.attn.wq.weight": "model-00003-of-00006.safetensors", "layers.12.attn.wk.weight": "model-00003-of-00006.safetensors", "layers.12.attn.wv.weight": "model-00003-of-00006.safetensors", "layers.12.attn.wo.weight": "model-00003-of-00006.safetensors", "layers.12.ffn_norm.weight": "model-00003-of-00006.safetensors", "layers.12.ffn.expert_usage": "model-00003-of-00006.safetensors", "layers.12.ffn.expert_age": "model-00003-of-00006.safetensors", "layers.12.ffn.total_tokens_seen": "model-00003-of-00006.safetensors", "layers.12.ffn.router.gate.weight": "model-00003-of-00006.safetensors", "layers.12.ffn.ec_router.gate.weight": "model-00003-of-00006.safetensors", "layers.12.ffn.experts.0.w_gate.weight": "model-00003-of-00006.safetensors", "layers.12.ffn.experts.0.w_up.weight": "model-00003-of-00006.safetensors", "layers.12.ffn.experts.0.w_down.weight": "model-00003-of-00006.safetensors", "layers.12.ffn.experts.1.w_gate.weight": "model-00003-of-00006.safetensors", "layers.12.ffn.experts.1.w_up.weight": "model-00003-of-00006.safetensors", "layers.12.ffn.experts.1.w_down.weight": "model-00003-of-00006.safetensors", "layers.12.ffn.experts.2.w_gate.weight": "model-00003-of-00006.safetensors", "layers.12.ffn.experts.2.w_up.weight": "model-00003-of-00006.safetensors", "layers.12.ffn.experts.2.w_down.weight": "model-00003-of-00006.safetensors", "layers.12.ffn.experts.3.w_gate.weight": "model-00003-of-00006.safetensors", "layers.12.ffn.experts.3.w_up.weight": "model-00003-of-00006.safetensors", "layers.12.ffn.experts.3.w_down.weight": "model-00004-of-00006.safetensors", "layers.13.attn_norm.weight": "model-00004-of-00006.safetensors", "layers.13.attn.wq.weight": "model-00004-of-00006.safetensors", "layers.13.attn.wk.weight": "model-00004-of-00006.safetensors", "layers.13.attn.wv.weight": "model-00004-of-00006.safetensors", "layers.13.attn.wo.weight": "model-00004-of-00006.safetensors", "layers.13.ffn_norm.weight": "model-00004-of-00006.safetensors", "layers.13.ffn.expert_usage": "model-00004-of-00006.safetensors", "layers.13.ffn.expert_age": "model-00004-of-00006.safetensors", "layers.13.ffn.total_tokens_seen": "model-00004-of-00006.safetensors", "layers.13.ffn.router.gate.weight": "model-00004-of-00006.safetensors", "layers.13.ffn.ec_router.gate.weight": "model-00004-of-00006.safetensors", "layers.13.ffn.experts.0.w_gate.weight": "model-00004-of-00006.safetensors", "layers.13.ffn.experts.0.w_up.weight": "model-00004-of-00006.safetensors", "layers.13.ffn.experts.0.w_down.weight": "model-00004-of-00006.safetensors", "layers.13.ffn.experts.1.w_gate.weight": "model-00004-of-00006.safetensors", "layers.13.ffn.experts.1.w_up.weight": "model-00004-of-00006.safetensors", "layers.13.ffn.experts.1.w_down.weight": "model-00004-of-00006.safetensors", "layers.13.ffn.experts.2.w_gate.weight": "model-00004-of-00006.safetensors", "layers.13.ffn.experts.2.w_up.weight": "model-00004-of-00006.safetensors", "layers.13.ffn.experts.2.w_down.weight": "model-00004-of-00006.safetensors", "layers.13.ffn.experts.3.w_gate.weight": "model-00004-of-00006.safetensors", "layers.13.ffn.experts.3.w_up.weight": "model-00004-of-00006.safetensors", "layers.13.ffn.experts.3.w_down.weight": "model-00004-of-00006.safetensors", "layers.14.attn_norm.weight": "model-00004-of-00006.safetensors", "layers.14.attn.wq.weight": "model-00004-of-00006.safetensors", "layers.14.attn.wk.weight": "model-00004-of-00006.safetensors", "layers.14.attn.wv.weight": "model-00004-of-00006.safetensors", "layers.14.attn.wo.weight": "model-00004-of-00006.safetensors", "layers.14.ffn_norm.weight": "model-00004-of-00006.safetensors", "layers.14.ffn.expert_usage": "model-00004-of-00006.safetensors", "layers.14.ffn.expert_age": "model-00004-of-00006.safetensors", "layers.14.ffn.total_tokens_seen": "model-00004-of-00006.safetensors", "layers.14.ffn.router.gate.weight": "model-00004-of-00006.safetensors", "layers.14.ffn.ec_router.gate.weight": "model-00004-of-00006.safetensors", "layers.14.ffn.experts.0.w_gate.weight": "model-00004-of-00006.safetensors", "layers.14.ffn.experts.0.w_up.weight": "model-00004-of-00006.safetensors", "layers.14.ffn.experts.0.w_down.weight": "model-00004-of-00006.safetensors", "layers.14.ffn.experts.1.w_gate.weight": "model-00004-of-00006.safetensors", "layers.14.ffn.experts.1.w_up.weight": "model-00004-of-00006.safetensors", "layers.14.ffn.experts.1.w_down.weight": "model-00004-of-00006.safetensors", "layers.14.ffn.experts.2.w_gate.weight": "model-00004-of-00006.safetensors", "layers.14.ffn.experts.2.w_up.weight": "model-00004-of-00006.safetensors", "layers.14.ffn.experts.2.w_down.weight": "model-00004-of-00006.safetensors", "layers.14.ffn.experts.3.w_gate.weight": "model-00004-of-00006.safetensors", "layers.14.ffn.experts.3.w_up.weight": "model-00004-of-00006.safetensors", "layers.14.ffn.experts.3.w_down.weight": "model-00004-of-00006.safetensors", "layers.15.attn_norm.weight": "model-00004-of-00006.safetensors", "layers.15.attn.wq.weight": "model-00004-of-00006.safetensors", "layers.15.attn.wk.weight": "model-00004-of-00006.safetensors", "layers.15.attn.wv.weight": "model-00004-of-00006.safetensors", "layers.15.attn.wo.weight": "model-00004-of-00006.safetensors", "layers.15.ffn_norm.weight": "model-00004-of-00006.safetensors", "layers.15.ffn.expert_usage": "model-00004-of-00006.safetensors", "layers.15.ffn.expert_age": "model-00004-of-00006.safetensors", "layers.15.ffn.total_tokens_seen": "model-00004-of-00006.safetensors", "layers.15.ffn.router.gate.weight": "model-00004-of-00006.safetensors", "layers.15.ffn.ec_router.gate.weight": "model-00004-of-00006.safetensors", "layers.15.ffn.experts.0.w_gate.weight": "model-00004-of-00006.safetensors", "layers.15.ffn.experts.0.w_up.weight": "model-00004-of-00006.safetensors", "layers.15.ffn.experts.0.w_down.weight": "model-00004-of-00006.safetensors", "layers.15.ffn.experts.1.w_gate.weight": "model-00004-of-00006.safetensors", "layers.15.ffn.experts.1.w_up.weight": "model-00004-of-00006.safetensors", "layers.15.ffn.experts.1.w_down.weight": "model-00004-of-00006.safetensors", "layers.15.ffn.experts.2.w_gate.weight": "model-00004-of-00006.safetensors", "layers.15.ffn.experts.2.w_up.weight": "model-00004-of-00006.safetensors", "layers.15.ffn.experts.2.w_down.weight": "model-00004-of-00006.safetensors", "layers.15.ffn.experts.3.w_gate.weight": "model-00004-of-00006.safetensors", "layers.15.ffn.experts.3.w_up.weight": "model-00004-of-00006.safetensors", "layers.15.ffn.experts.3.w_down.weight": "model-00004-of-00006.safetensors", "layers.16.attn_norm.weight": "model-00004-of-00006.safetensors", "layers.16.attn.wq.weight": "model-00004-of-00006.safetensors", "layers.16.attn.wk.weight": "model-00004-of-00006.safetensors", "layers.16.attn.wv.weight": "model-00004-of-00006.safetensors", "layers.16.attn.wo.weight": "model-00004-of-00006.safetensors", "layers.16.ffn_norm.weight": "model-00004-of-00006.safetensors", "layers.16.ffn.expert_usage": "model-00004-of-00006.safetensors", "layers.16.ffn.expert_age": "model-00004-of-00006.safetensors", "layers.16.ffn.total_tokens_seen": "model-00004-of-00006.safetensors", "layers.16.ffn.router.gate.weight": "model-00004-of-00006.safetensors", "layers.16.ffn.ec_router.gate.weight": "model-00004-of-00006.safetensors", "layers.16.ffn.experts.0.w_gate.weight": "model-00004-of-00006.safetensors", "layers.16.ffn.experts.0.w_up.weight": "model-00004-of-00006.safetensors", "layers.16.ffn.experts.0.w_down.weight": "model-00004-of-00006.safetensors", "layers.16.ffn.experts.1.w_gate.weight": "model-00004-of-00006.safetensors", "layers.16.ffn.experts.1.w_up.weight": "model-00004-of-00006.safetensors", "layers.16.ffn.experts.1.w_down.weight": "model-00004-of-00006.safetensors", "layers.16.ffn.experts.2.w_gate.weight": "model-00004-of-00006.safetensors", "layers.16.ffn.experts.2.w_up.weight": "model-00004-of-00006.safetensors", "layers.16.ffn.experts.2.w_down.weight": "model-00004-of-00006.safetensors", "layers.16.ffn.experts.3.w_gate.weight": "model-00004-of-00006.safetensors", "layers.16.ffn.experts.3.w_up.weight": "model-00004-of-00006.safetensors", "layers.16.ffn.experts.3.w_down.weight": "model-00004-of-00006.safetensors", "layers.17.attn_norm.weight": "model-00004-of-00006.safetensors", "layers.17.attn.wq.weight": "model-00004-of-00006.safetensors", "layers.17.attn.wk.weight": "model-00004-of-00006.safetensors", "layers.17.attn.wv.weight": "model-00004-of-00006.safetensors", "layers.17.attn.wo.weight": "model-00004-of-00006.safetensors", "layers.17.ffn_norm.weight": "model-00004-of-00006.safetensors", "layers.17.ffn.expert_usage": "model-00004-of-00006.safetensors", "layers.17.ffn.expert_age": "model-00004-of-00006.safetensors", "layers.17.ffn.total_tokens_seen": "model-00004-of-00006.safetensors", "layers.17.ffn.router.gate.weight": "model-00004-of-00006.safetensors", "layers.17.ffn.ec_router.gate.weight": "model-00004-of-00006.safetensors", "layers.17.ffn.experts.0.w_gate.weight": "model-00004-of-00006.safetensors", "layers.17.ffn.experts.0.w_up.weight": "model-00004-of-00006.safetensors", "layers.17.ffn.experts.0.w_down.weight": "model-00004-of-00006.safetensors", "layers.17.ffn.experts.1.w_gate.weight": "model-00004-of-00006.safetensors", "layers.17.ffn.experts.1.w_up.weight": "model-00004-of-00006.safetensors", "layers.17.ffn.experts.1.w_down.weight": "model-00005-of-00006.safetensors", "layers.17.ffn.experts.2.w_gate.weight": "model-00005-of-00006.safetensors", "layers.17.ffn.experts.2.w_up.weight": "model-00005-of-00006.safetensors", "layers.17.ffn.experts.2.w_down.weight": "model-00005-of-00006.safetensors", "layers.17.ffn.experts.3.w_gate.weight": "model-00005-of-00006.safetensors", "layers.17.ffn.experts.3.w_up.weight": "model-00005-of-00006.safetensors", "layers.17.ffn.experts.3.w_down.weight": "model-00005-of-00006.safetensors", "layers.18.attn_norm.weight": "model-00005-of-00006.safetensors", "layers.18.attn.wq.weight": "model-00005-of-00006.safetensors", "layers.18.attn.wk.weight": "model-00005-of-00006.safetensors", "layers.18.attn.wv.weight": "model-00005-of-00006.safetensors", "layers.18.attn.wo.weight": "model-00005-of-00006.safetensors", "layers.18.ffn_norm.weight": "model-00005-of-00006.safetensors", "layers.18.ffn.expert_usage": "model-00005-of-00006.safetensors", "layers.18.ffn.expert_age": "model-00005-of-00006.safetensors", "layers.18.ffn.total_tokens_seen": "model-00005-of-00006.safetensors", "layers.18.ffn.router.gate.weight": "model-00005-of-00006.safetensors", "layers.18.ffn.ec_router.gate.weight": "model-00005-of-00006.safetensors", "layers.18.ffn.experts.0.w_gate.weight": "model-00005-of-00006.safetensors", "layers.18.ffn.experts.0.w_up.weight": "model-00005-of-00006.safetensors", "layers.18.ffn.experts.0.w_down.weight": "model-00005-of-00006.safetensors", "layers.18.ffn.experts.1.w_gate.weight": "model-00005-of-00006.safetensors", "layers.18.ffn.experts.1.w_up.weight": "model-00005-of-00006.safetensors", "layers.18.ffn.experts.1.w_down.weight": "model-00005-of-00006.safetensors", "layers.18.ffn.experts.2.w_gate.weight": "model-00005-of-00006.safetensors", "layers.18.ffn.experts.2.w_up.weight": "model-00005-of-00006.safetensors", "layers.18.ffn.experts.2.w_down.weight": "model-00005-of-00006.safetensors", "layers.18.ffn.experts.3.w_gate.weight": "model-00005-of-00006.safetensors", "layers.18.ffn.experts.3.w_up.weight": "model-00005-of-00006.safetensors", "layers.18.ffn.experts.3.w_down.weight": "model-00005-of-00006.safetensors", "layers.19.attn_norm.weight": "model-00005-of-00006.safetensors", "layers.19.attn.wq.weight": "model-00005-of-00006.safetensors", "layers.19.attn.wk.weight": "model-00005-of-00006.safetensors", "layers.19.attn.wv.weight": "model-00005-of-00006.safetensors", "layers.19.attn.wo.weight": "model-00005-of-00006.safetensors", "layers.19.ffn_norm.weight": "model-00005-of-00006.safetensors", "layers.19.ffn.expert_usage": "model-00005-of-00006.safetensors", "layers.19.ffn.expert_age": "model-00005-of-00006.safetensors", "layers.19.ffn.total_tokens_seen": "model-00005-of-00006.safetensors", "layers.19.ffn.router.gate.weight": "model-00005-of-00006.safetensors", "layers.19.ffn.ec_router.gate.weight": "model-00005-of-00006.safetensors", "layers.19.ffn.experts.0.w_gate.weight": "model-00005-of-00006.safetensors", "layers.19.ffn.experts.0.w_up.weight": "model-00005-of-00006.safetensors", "layers.19.ffn.experts.0.w_down.weight": "model-00005-of-00006.safetensors", "layers.19.ffn.experts.1.w_gate.weight": "model-00005-of-00006.safetensors", "layers.19.ffn.experts.1.w_up.weight": "model-00005-of-00006.safetensors", "layers.19.ffn.experts.1.w_down.weight": "model-00005-of-00006.safetensors", "layers.19.ffn.experts.2.w_gate.weight": "model-00005-of-00006.safetensors", "layers.19.ffn.experts.2.w_up.weight": "model-00005-of-00006.safetensors", "layers.19.ffn.experts.2.w_down.weight": "model-00005-of-00006.safetensors", "layers.19.ffn.experts.3.w_gate.weight": "model-00005-of-00006.safetensors", "layers.19.ffn.experts.3.w_up.weight": "model-00005-of-00006.safetensors", "layers.19.ffn.experts.3.w_down.weight": "model-00005-of-00006.safetensors", "layers.20.attn_norm.weight": "model-00005-of-00006.safetensors", "layers.20.attn.wq.weight": "model-00005-of-00006.safetensors", "layers.20.attn.wk.weight": "model-00005-of-00006.safetensors", "layers.20.attn.wv.weight": "model-00005-of-00006.safetensors", "layers.20.attn.wo.weight": "model-00005-of-00006.safetensors", "layers.20.ffn_norm.weight": "model-00005-of-00006.safetensors", "layers.20.ffn.expert_usage": "model-00005-of-00006.safetensors", "layers.20.ffn.expert_age": "model-00005-of-00006.safetensors", "layers.20.ffn.total_tokens_seen": "model-00005-of-00006.safetensors", "layers.20.ffn.router.gate.weight": "model-00005-of-00006.safetensors", "layers.20.ffn.ec_router.gate.weight": "model-00005-of-00006.safetensors", "layers.20.ffn.experts.0.w_gate.weight": "model-00005-of-00006.safetensors", "layers.20.ffn.experts.0.w_up.weight": "model-00005-of-00006.safetensors", "layers.20.ffn.experts.0.w_down.weight": "model-00005-of-00006.safetensors", "layers.20.ffn.experts.1.w_gate.weight": "model-00005-of-00006.safetensors", "layers.20.ffn.experts.1.w_up.weight": "model-00005-of-00006.safetensors", "layers.20.ffn.experts.1.w_down.weight": "model-00005-of-00006.safetensors", "layers.20.ffn.experts.2.w_gate.weight": "model-00005-of-00006.safetensors", "layers.20.ffn.experts.2.w_up.weight": "model-00005-of-00006.safetensors", "layers.20.ffn.experts.2.w_down.weight": "model-00005-of-00006.safetensors", "layers.20.ffn.experts.3.w_gate.weight": "model-00005-of-00006.safetensors", "layers.20.ffn.experts.3.w_up.weight": "model-00005-of-00006.safetensors", "layers.20.ffn.experts.3.w_down.weight": "model-00005-of-00006.safetensors", "layers.21.attn_norm.weight": "model-00005-of-00006.safetensors", "layers.21.attn.wq.weight": "model-00005-of-00006.safetensors", "layers.21.attn.wk.weight": "model-00005-of-00006.safetensors", "layers.21.attn.wv.weight": "model-00005-of-00006.safetensors", "layers.21.attn.wo.weight": "model-00005-of-00006.safetensors", "layers.21.ffn_norm.weight": "model-00005-of-00006.safetensors", "layers.21.ffn.expert_usage": "model-00005-of-00006.safetensors", "layers.21.ffn.expert_age": "model-00005-of-00006.safetensors", "layers.21.ffn.total_tokens_seen": "model-00005-of-00006.safetensors", "layers.21.ffn.router.gate.weight": "model-00005-of-00006.safetensors", "layers.21.ffn.ec_router.gate.weight": "model-00005-of-00006.safetensors", "layers.21.ffn.experts.0.w_gate.weight": "model-00005-of-00006.safetensors", "layers.21.ffn.experts.0.w_up.weight": "model-00005-of-00006.safetensors", "layers.21.ffn.experts.0.w_down.weight": "model-00005-of-00006.safetensors", "layers.21.ffn.experts.1.w_gate.weight": "model-00005-of-00006.safetensors", "layers.21.ffn.experts.1.w_up.weight": "model-00005-of-00006.safetensors", "layers.21.ffn.experts.1.w_down.weight": "model-00005-of-00006.safetensors", "layers.21.ffn.experts.2.w_gate.weight": "model-00005-of-00006.safetensors", "layers.21.ffn.experts.2.w_up.weight": "model-00005-of-00006.safetensors", "layers.21.ffn.experts.2.w_down.weight": "model-00005-of-00006.safetensors", "layers.21.ffn.experts.3.w_gate.weight": "model-00005-of-00006.safetensors", "layers.21.ffn.experts.3.w_up.weight": "model-00005-of-00006.safetensors", "layers.21.ffn.experts.3.w_down.weight": "model-00005-of-00006.safetensors", "layers.22.attn_norm.weight": "model-00005-of-00006.safetensors", "layers.22.attn.wq.weight": "model-00005-of-00006.safetensors", "layers.22.attn.wk.weight": "model-00005-of-00006.safetensors", "layers.22.attn.wv.weight": "model-00005-of-00006.safetensors", "layers.22.attn.wo.weight": "model-00006-of-00006.safetensors", "layers.22.ffn_norm.weight": "model-00006-of-00006.safetensors", "layers.22.ffn.expert_usage": "model-00006-of-00006.safetensors", "layers.22.ffn.expert_age": "model-00006-of-00006.safetensors", "layers.22.ffn.total_tokens_seen": "model-00006-of-00006.safetensors", "layers.22.ffn.router.gate.weight": "model-00006-of-00006.safetensors", "layers.22.ffn.ec_router.gate.weight": "model-00006-of-00006.safetensors", "layers.22.ffn.experts.0.w_gate.weight": "model-00006-of-00006.safetensors", "layers.22.ffn.experts.0.w_up.weight": "model-00006-of-00006.safetensors", "layers.22.ffn.experts.0.w_down.weight": "model-00006-of-00006.safetensors", "layers.22.ffn.experts.1.w_gate.weight": "model-00006-of-00006.safetensors", "layers.22.ffn.experts.1.w_up.weight": "model-00006-of-00006.safetensors", "layers.22.ffn.experts.1.w_down.weight": "model-00006-of-00006.safetensors", "layers.22.ffn.experts.2.w_gate.weight": "model-00006-of-00006.safetensors", "layers.22.ffn.experts.2.w_up.weight": "model-00006-of-00006.safetensors", "layers.22.ffn.experts.2.w_down.weight": "model-00006-of-00006.safetensors", "layers.22.ffn.experts.3.w_gate.weight": "model-00006-of-00006.safetensors", "layers.22.ffn.experts.3.w_up.weight": "model-00006-of-00006.safetensors", "layers.22.ffn.experts.3.w_down.weight": "model-00006-of-00006.safetensors", "layers.23.attn_norm.weight": "model-00006-of-00006.safetensors", "layers.23.attn.wq.weight": "model-00006-of-00006.safetensors", "layers.23.attn.wk.weight": "model-00006-of-00006.safetensors", "layers.23.attn.wv.weight": "model-00006-of-00006.safetensors", "layers.23.attn.wo.weight": "model-00006-of-00006.safetensors", "layers.23.ffn_norm.weight": "model-00006-of-00006.safetensors", "layers.23.ffn.expert_usage": "model-00006-of-00006.safetensors", "layers.23.ffn.expert_age": "model-00006-of-00006.safetensors", "layers.23.ffn.total_tokens_seen": "model-00006-of-00006.safetensors", "layers.23.ffn.router.gate.weight": "model-00006-of-00006.safetensors", "layers.23.ffn.ec_router.gate.weight": "model-00006-of-00006.safetensors", "layers.23.ffn.experts.0.w_gate.weight": "model-00006-of-00006.safetensors", "layers.23.ffn.experts.0.w_up.weight": "model-00006-of-00006.safetensors", "layers.23.ffn.experts.0.w_down.weight": "model-00006-of-00006.safetensors", "layers.23.ffn.experts.1.w_gate.weight": "model-00006-of-00006.safetensors", "layers.23.ffn.experts.1.w_up.weight": "model-00006-of-00006.safetensors", "layers.23.ffn.experts.1.w_down.weight": "model-00006-of-00006.safetensors", "layers.23.ffn.experts.2.w_gate.weight": "model-00006-of-00006.safetensors", "layers.23.ffn.experts.2.w_up.weight": "model-00006-of-00006.safetensors", "layers.23.ffn.experts.2.w_down.weight": "model-00006-of-00006.safetensors", "layers.23.ffn.experts.3.w_gate.weight": "model-00006-of-00006.safetensors", "layers.23.ffn.experts.3.w_up.weight": "model-00006-of-00006.safetensors", "layers.23.ffn.experts.3.w_down.weight": "model-00006-of-00006.safetensors", "norm.weight": "model-00006-of-00006.safetensors", "lm_head.weight": "model-00006-of-00006.safetensors" } }