Upload config files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,88 @@
+{
+  "architectures": [
+    "GptOssForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "eos_token_id": 200002,
+  "experts_per_token": 4,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2880,
+  "initial_context_length": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 2880,
+  "layer_types": [
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 131072,
+  "model_type": "gpt_oss",
+  "num_attention_heads": 64,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "num_local_experts": 128,
+  "output_router_logits": false,
+  "pad_token_id": 199999,
+  "quantization_config": {
+    "modules_to_not_convert": [
+      "model.layers.*.self_attn",
+      "model.layers.*.mlp.router",
+      "model.embed_tokens",
+      "lm_head"
+    ],
+    "quant_method": "mxfp4"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "beta_fast": 32.0,
+    "beta_slow": 1.0,
+    "factor": 32.0,
+    "original_max_position_embeddings": 4096,
+    "rope_type": "yarn",
+    "truncate": false
+  },
+  "rope_theta": 150000,
+  "router_aux_loss_coef": 0.9,
+  "sliding_window": 128,
+  "swiglu_limit": 7.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.55.0.dev0",
+  "use_cache": true,
+  "vocab_size": 201088
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "bos_token_id": 199998,
+  "do_sample": true,
+  "eos_token_id": [
+    200002,
+    199999,
+    200012
+  ],
+  "pad_token_id": 199999,
+  "transformers_version": "4.55.0.dev0"
+}

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"total_size": 65248815744}, "weight_map": {"model.layers.25.mlp.experts.gate_up_proj_blocks": "model-00000-of-00014.safetensors", "model.layers.25.mlp.experts.gate_up_proj_scales": "model-00000-of-00014.safetensors", "model.layers.25.mlp.experts.down_proj_bias": "model-00000-of-00014.safetensors", "model.layers.25.mlp.experts.down_proj_blocks": "model-00000-of-00014.safetensors", "model.layers.25.mlp.experts.down_proj_scales": "model-00000-of-00014.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00000-of-00014.safetensors", "model.layers.26.input_layernorm.weight": "model-00000-of-00014.safetensors", "model.layers.26.self_attn.o_proj.bias": "model-00000-of-00014.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00000-of-00014.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00000-of-00014.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00000-of-00014.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00000-of-00014.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00000-of-00014.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00000-of-00014.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00000-of-00014.safetensors", "model.layers.26.self_attn.sinks": "model-00000-of-00014.safetensors", "model.layers.26.mlp.router.bias": "model-00000-of-00014.safetensors", "model.layers.26.mlp.router.weight": "model-00000-of-00014.safetensors", "model.layers.26.mlp.experts.gate_up_proj_bias": "model-00000-of-00014.safetensors", "model.layers.26.mlp.experts.gate_up_proj_blocks": "model-00000-of-00014.safetensors", "model.layers.26.mlp.experts.gate_up_proj_scales": "model-00000-of-00014.safetensors", "model.layers.26.mlp.experts.down_proj_bias": "model-00000-of-00014.safetensors", "model.layers.26.mlp.experts.down_proj_blocks": "model-00000-of-00014.safetensors", "model.layers.26.mlp.experts.down_proj_scales": "model-00000-of-00014.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00000-of-00014.safetensors", "model.layers.27.input_layernorm.weight": "model-00000-of-00014.safetensors", "model.layers.27.self_attn.o_proj.bias": "model-00000-of-00014.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00000-of-00014.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00000-of-00014.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00000-of-00014.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00000-of-00014.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00000-of-00014.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00000-of-00014.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00000-of-00014.safetensors", "model.layers.27.self_attn.sinks": "model-00000-of-00014.safetensors", "model.layers.27.mlp.router.bias": "model-00000-of-00014.safetensors", "model.layers.27.mlp.router.weight": "model-00000-of-00014.safetensors", "model.layers.27.mlp.experts.gate_up_proj_bias": "model-00000-of-00014.safetensors", "model.layers.27.mlp.experts.gate_up_proj_blocks": "model-00000-of-00014.safetensors", "model.layers.27.mlp.experts.gate_up_proj_scales": "model-00000-of-00014.safetensors", "model.layers.27.mlp.experts.down_proj_bias": "model-00000-of-00014.safetensors", "model.layers.27.mlp.experts.down_proj_blocks": "model-00001-of-00014.safetensors", "model.layers.27.mlp.experts.down_proj_scales": "model-00001-of-00014.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.28.self_attn.o_proj.bias": "model-00001-of-00014.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00014.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00014.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00014.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.28.self_attn.sinks": "model-00001-of-00014.safetensors", "model.layers.28.mlp.router.bias": "model-00001-of-00014.safetensors", "model.layers.28.mlp.router.weight": "model-00001-of-00014.safetensors", "model.layers.28.mlp.experts.gate_up_proj_bias": "model-00001-of-00014.safetensors", "model.layers.28.mlp.experts.gate_up_proj_blocks": "model-00001-of-00014.safetensors", "model.layers.28.mlp.experts.gate_up_proj_scales": "model-00001-of-00014.safetensors", "model.layers.28.mlp.experts.down_proj_bias": "model-00001-of-00014.safetensors", "model.layers.28.mlp.experts.down_proj_blocks": "model-00001-of-00014.safetensors", "model.layers.28.mlp.experts.down_proj_scales": "model-00001-of-00014.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.29.self_attn.o_proj.bias": "model-00001-of-00014.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00001-of-00014.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00001-of-00014.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00001-of-00014.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.29.self_attn.sinks": "model-00001-of-00014.safetensors", "model.layers.29.mlp.router.bias": "model-00001-of-00014.safetensors", "model.layers.29.mlp.router.weight": "model-00001-of-00014.safetensors", "model.layers.29.mlp.experts.gate_up_proj_bias": "model-00001-of-00014.safetensors", "model.layers.29.mlp.experts.gate_up_proj_blocks": "model-00001-of-00014.safetensors", "model.layers.29.mlp.experts.gate_up_proj_scales": "model-00001-of-00014.safetensors", "model.layers.29.mlp.experts.down_proj_bias": "model-00001-of-00014.safetensors", "model.layers.29.mlp.experts.down_proj_blocks": "model-00001-of-00014.safetensors", "model.layers.29.mlp.experts.down_proj_scales": "model-00001-of-00014.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.3.self_attn.o_proj.bias": "model-00001-of-00014.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00014.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00014.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00014.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.3.self_attn.sinks": "model-00001-of-00014.safetensors", "model.layers.3.mlp.router.bias": "model-00001-of-00014.safetensors", "model.layers.3.mlp.router.weight": "model-00001-of-00014.safetensors", "model.layers.3.mlp.experts.gate_up_proj_bias": "model-00001-of-00014.safetensors", "model.layers.3.mlp.experts.gate_up_proj_blocks": "model-00002-of-00014.safetensors", "model.layers.3.mlp.experts.gate_up_proj_scales": "model-00002-of-00014.safetensors", "model.layers.3.mlp.experts.down_proj_bias": "model-00002-of-00014.safetensors", "model.layers.3.mlp.experts.down_proj_blocks": "model-00002-of-00014.safetensors", "model.layers.3.mlp.experts.down_proj_scales": "model-00002-of-00014.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.30.self_attn.o_proj.bias": "model-00002-of-00014.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00014.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00014.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00014.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.30.self_attn.sinks": "model-00002-of-00014.safetensors", "model.layers.30.mlp.router.bias": "model-00002-of-00014.safetensors", "model.layers.30.mlp.router.weight": "model-00002-of-00014.safetensors", "model.layers.30.mlp.experts.gate_up_proj_bias": "model-00002-of-00014.safetensors", "model.layers.2.mlp.experts.gate_up_proj_blocks": "model-00002-of-00014.safetensors", "model.layers.2.mlp.experts.gate_up_proj_scales": "model-00002-of-00014.safetensors", "model.layers.2.mlp.experts.down_proj_bias": "model-00002-of-00014.safetensors", "model.layers.2.mlp.experts.down_proj_blocks": "model-00002-of-00014.safetensors", "model.layers.2.mlp.experts.down_proj_scales": "model-00002-of-00014.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.20.self_attn.o_proj.bias": "model-00002-of-00014.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00014.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00014.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00014.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.20.self_attn.sinks": "model-00002-of-00014.safetensors", "model.layers.20.mlp.router.bias": "model-00002-of-00014.safetensors", "model.layers.20.mlp.router.weight": "model-00002-of-00014.safetensors", "model.layers.20.mlp.experts.gate_up_proj_bias": "model-00002-of-00014.safetensors", "model.layers.20.mlp.experts.gate_up_proj_blocks": "model-00002-of-00014.safetensors", "model.layers.20.mlp.experts.gate_up_proj_scales": "model-00002-of-00014.safetensors", "model.layers.20.mlp.experts.down_proj_bias": "model-00002-of-00014.safetensors", "model.layers.20.mlp.experts.down_proj_blocks": "model-00003-of-00014.safetensors", "model.layers.20.mlp.experts.down_proj_scales": "model-00003-of-00014.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.21.self_attn.o_proj.bias": "model-00003-of-00014.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00014.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00014.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00014.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.21.self_attn.sinks": "model-00003-of-00014.safetensors", "model.layers.21.mlp.router.bias": "model-00003-of-00014.safetensors", "model.layers.21.mlp.router.weight": "model-00003-of-00014.safetensors", "model.layers.21.mlp.experts.gate_up_proj_bias": "model-00003-of-00014.safetensors", "model.layers.21.mlp.experts.gate_up_proj_blocks": "model-00003-of-00014.safetensors", "model.layers.21.mlp.experts.gate_up_proj_scales": "model-00003-of-00014.safetensors", "model.layers.21.mlp.experts.down_proj_bias": "model-00003-of-00014.safetensors", "model.layers.21.mlp.experts.down_proj_blocks": "model-00003-of-00014.safetensors", "model.layers.21.mlp.experts.down_proj_scales": "model-00003-of-00014.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.22.self_attn.o_proj.bias": "model-00003-of-00014.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00014.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00014.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00014.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.22.self_attn.sinks": "model-00003-of-00014.safetensors", "model.layers.22.mlp.router.bias": "model-00003-of-00014.safetensors", "model.layers.22.mlp.router.weight": "model-00003-of-00014.safetensors", "model.layers.22.mlp.experts.gate_up_proj_bias": "model-00003-of-00014.safetensors", "model.layers.22.mlp.experts.gate_up_proj_blocks": "model-00003-of-00014.safetensors", "model.layers.22.mlp.experts.gate_up_proj_scales": "model-00003-of-00014.safetensors", "model.layers.22.mlp.experts.down_proj_bias": "model-00003-of-00014.safetensors", "model.layers.22.mlp.experts.down_proj_blocks": "model-00003-of-00014.safetensors", "model.layers.22.mlp.experts.down_proj_scales": "model-00003-of-00014.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.23.self_attn.o_proj.bias": "model-00003-of-00014.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00014.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00014.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00014.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.23.self_attn.sinks": "model-00003-of-00014.safetensors", "model.layers.23.mlp.router.bias": "model-00003-of-00014.safetensors", "model.layers.23.mlp.router.weight": "model-00003-of-00014.safetensors", "model.layers.23.mlp.experts.gate_up_proj_bias": "model-00003-of-00014.safetensors", "model.layers.23.mlp.experts.gate_up_proj_blocks": "model-00004-of-00014.safetensors", "model.layers.23.mlp.experts.gate_up_proj_scales": "model-00004-of-00014.safetensors", "model.layers.23.mlp.experts.down_proj_bias": "model-00004-of-00014.safetensors", "model.layers.23.mlp.experts.down_proj_blocks": "model-00004-of-00014.safetensors", "model.layers.23.mlp.experts.down_proj_scales": "model-00004-of-00014.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.24.self_attn.o_proj.bias": "model-00004-of-00014.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00004-of-00014.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00004-of-00014.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00004-of-00014.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.24.self_attn.sinks": "model-00004-of-00014.safetensors", "model.layers.24.mlp.router.bias": "model-00004-of-00014.safetensors", "model.layers.24.mlp.router.weight": "model-00004-of-00014.safetensors", "model.layers.24.mlp.experts.gate_up_proj_bias": "model-00004-of-00014.safetensors", "model.layers.24.mlp.experts.gate_up_proj_blocks": "model-00004-of-00014.safetensors", "model.layers.24.mlp.experts.gate_up_proj_scales": "model-00004-of-00014.safetensors", "model.layers.24.mlp.experts.down_proj_bias": "model-00004-of-00014.safetensors", "model.layers.24.mlp.experts.down_proj_blocks": "model-00004-of-00014.safetensors", "model.layers.24.mlp.experts.down_proj_scales": "model-00004-of-00014.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.25.self_attn.o_proj.bias": "model-00004-of-00014.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00014.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00014.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00014.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.25.self_attn.sinks": "model-00004-of-00014.safetensors", "model.layers.25.mlp.router.bias": "model-00004-of-00014.safetensors", "model.layers.25.mlp.router.weight": "model-00004-of-00014.safetensors", "model.layers.25.mlp.experts.gate_up_proj_bias": "model-00004-of-00014.safetensors", "model.layers.4.mlp.experts.gate_up_proj_blocks": "model-00004-of-00014.safetensors", "model.layers.4.mlp.experts.gate_up_proj_scales": "model-00004-of-00014.safetensors", "model.layers.4.mlp.experts.down_proj_bias": "model-00004-of-00014.safetensors", "model.layers.4.mlp.experts.down_proj_blocks": "model-00005-of-00014.safetensors", "model.layers.4.mlp.experts.down_proj_scales": "model-00005-of-00014.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.5.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.5.self_attn.o_proj.bias": "model-00005-of-00014.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00005-of-00014.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00005-of-00014.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00005-of-00014.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.5.self_attn.sinks": "model-00005-of-00014.safetensors", "model.layers.5.mlp.router.bias": "model-00005-of-00014.safetensors", "model.layers.5.mlp.router.weight": "model-00005-of-00014.safetensors", "model.layers.5.mlp.experts.gate_up_proj_bias": "model-00005-of-00014.safetensors", "model.layers.5.mlp.experts.gate_up_proj_blocks": "model-00005-of-00014.safetensors", "model.layers.5.mlp.experts.gate_up_proj_scales": "model-00005-of-00014.safetensors", "model.layers.5.mlp.experts.down_proj_bias": "model-00005-of-00014.safetensors", "model.layers.5.mlp.experts.down_proj_blocks": "model-00005-of-00014.safetensors", "model.layers.5.mlp.experts.down_proj_scales": "model-00005-of-00014.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.6.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.6.self_attn.o_proj.bias": "model-00005-of-00014.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00005-of-00014.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00005-of-00014.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00005-of-00014.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.6.self_attn.sinks": "model-00005-of-00014.safetensors", "model.layers.6.mlp.router.bias": "model-00005-of-00014.safetensors", "model.layers.6.mlp.router.weight": "model-00005-of-00014.safetensors", "model.layers.6.mlp.experts.gate_up_proj_bias": "model-00005-of-00014.safetensors", "model.layers.6.mlp.experts.gate_up_proj_blocks": "model-00005-of-00014.safetensors", "model.layers.6.mlp.experts.gate_up_proj_scales": "model-00005-of-00014.safetensors", "model.layers.6.mlp.experts.down_proj_bias": "model-00005-of-00014.safetensors", "model.layers.6.mlp.experts.down_proj_blocks": "model-00005-of-00014.safetensors", "model.layers.6.mlp.experts.down_proj_scales": "model-00005-of-00014.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.7.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.7.self_attn.o_proj.bias": "model-00005-of-00014.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00005-of-00014.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00005-of-00014.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00005-of-00014.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.7.self_attn.sinks": "model-00005-of-00014.safetensors", "model.layers.7.mlp.router.bias": "model-00005-of-00014.safetensors", "model.layers.7.mlp.router.weight": "model-00005-of-00014.safetensors", "model.layers.7.mlp.experts.gate_up_proj_bias": "model-00005-of-00014.safetensors", "model.layers.7.mlp.experts.gate_up_proj_blocks": "model-00006-of-00014.safetensors", "model.layers.7.mlp.experts.gate_up_proj_scales": "model-00006-of-00014.safetensors", "model.layers.7.mlp.experts.down_proj_bias": "model-00006-of-00014.safetensors", "model.layers.7.mlp.experts.down_proj_blocks": "model-00006-of-00014.safetensors", "model.layers.7.mlp.experts.down_proj_scales": "model-00006-of-00014.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.8.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.8.self_attn.o_proj.bias": "model-00006-of-00014.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00006-of-00014.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00006-of-00014.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00006-of-00014.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.8.self_attn.sinks": "model-00006-of-00014.safetensors", "model.layers.8.mlp.router.bias": "model-00006-of-00014.safetensors", "model.layers.8.mlp.router.weight": "model-00006-of-00014.safetensors", "model.layers.8.mlp.experts.gate_up_proj_bias": "model-00006-of-00014.safetensors", "model.layers.8.mlp.experts.gate_up_proj_blocks": "model-00006-of-00014.safetensors", "model.layers.8.mlp.experts.gate_up_proj_scales": "model-00006-of-00014.safetensors", "model.layers.8.mlp.experts.down_proj_bias": "model-00006-of-00014.safetensors", "model.layers.8.mlp.experts.down_proj_blocks": "model-00006-of-00014.safetensors", "model.layers.8.mlp.experts.down_proj_scales": "model-00006-of-00014.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.9.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.9.self_attn.o_proj.bias": "model-00006-of-00014.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00006-of-00014.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00006-of-00014.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00006-of-00014.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.9.self_attn.sinks": "model-00006-of-00014.safetensors", "model.layers.9.mlp.router.bias": "model-00006-of-00014.safetensors", "model.layers.9.mlp.router.weight": "model-00006-of-00014.safetensors", "model.layers.9.mlp.experts.gate_up_proj_bias": "model-00006-of-00014.safetensors", "model.layers.9.mlp.experts.gate_up_proj_blocks": "model-00006-of-00014.safetensors", "model.layers.9.mlp.experts.gate_up_proj_scales": "model-00006-of-00014.safetensors", "model.layers.9.mlp.experts.down_proj_bias": "model-00006-of-00014.safetensors", "model.layers.9.mlp.experts.down_proj_blocks": "model-00007-of-00014.safetensors", "model.layers.9.mlp.experts.down_proj_scales": "model-00007-of-00014.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.14.mlp.experts.gate_up_proj_blocks": "model-00007-of-00014.safetensors", "model.layers.14.mlp.experts.gate_up_proj_scales": "model-00007-of-00014.safetensors", "model.layers.14.mlp.experts.down_proj_bias": "model-00007-of-00014.safetensors", "model.layers.14.mlp.experts.down_proj_blocks": "model-00007-of-00014.safetensors", "model.layers.14.mlp.experts.down_proj_scales": "model-00007-of-00014.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.15.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.o_proj.bias": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.sinks": "model-00007-of-00014.safetensors", "model.layers.15.mlp.router.bias": "model-00007-of-00014.safetensors", "model.layers.15.mlp.router.weight": "model-00007-of-00014.safetensors", "model.layers.15.mlp.experts.gate_up_proj_bias": "model-00007-of-00014.safetensors", "model.layers.15.mlp.experts.gate_up_proj_blocks": "model-00007-of-00014.safetensors", "model.layers.15.mlp.experts.gate_up_proj_scales": "model-00007-of-00014.safetensors", "model.layers.15.mlp.experts.down_proj_bias": "model-00007-of-00014.safetensors", "model.layers.15.mlp.experts.down_proj_blocks": "model-00007-of-00014.safetensors", "model.layers.15.mlp.experts.down_proj_scales": "model-00007-of-00014.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.16.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.o_proj.bias": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.sinks": "model-00007-of-00014.safetensors", "model.layers.16.mlp.router.bias": "model-00007-of-00014.safetensors", "model.layers.16.mlp.router.weight": "model-00007-of-00014.safetensors", "model.layers.16.mlp.experts.gate_up_proj_bias": "model-00007-of-00014.safetensors", "model.layers.16.mlp.experts.gate_up_proj_blocks": "model-00008-of-00014.safetensors", "model.layers.16.mlp.experts.gate_up_proj_scales": "model-00008-of-00014.safetensors", "model.layers.16.mlp.experts.down_proj_bias": "model-00008-of-00014.safetensors", "model.layers.16.mlp.experts.down_proj_blocks": "model-00008-of-00014.safetensors", "model.layers.16.mlp.experts.down_proj_scales": "model-00008-of-00014.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.17.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.o_proj.bias": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.sinks": "model-00008-of-00014.safetensors", "model.layers.17.mlp.router.bias": "model-00008-of-00014.safetensors", "model.layers.17.mlp.router.weight": "model-00008-of-00014.safetensors", "model.layers.17.mlp.experts.gate_up_proj_bias": "model-00008-of-00014.safetensors", "model.layers.17.mlp.experts.gate_up_proj_blocks": "model-00008-of-00014.safetensors", "model.layers.17.mlp.experts.gate_up_proj_scales": "model-00008-of-00014.safetensors", "model.layers.17.mlp.experts.down_proj_bias": "model-00008-of-00014.safetensors", "model.layers.17.mlp.experts.down_proj_blocks": "model-00008-of-00014.safetensors", "model.layers.17.mlp.experts.down_proj_scales": "model-00008-of-00014.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.18.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.o_proj.bias": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.sinks": "model-00008-of-00014.safetensors", "model.layers.18.mlp.router.bias": "model-00008-of-00014.safetensors", "model.layers.18.mlp.router.weight": "model-00008-of-00014.safetensors", "model.layers.18.mlp.experts.gate_up_proj_bias": "model-00008-of-00014.safetensors", "model.layers.18.mlp.experts.gate_up_proj_blocks": "model-00008-of-00014.safetensors", "model.layers.18.mlp.experts.gate_up_proj_scales": "model-00008-of-00014.safetensors", "model.layers.18.mlp.experts.down_proj_bias": "model-00008-of-00014.safetensors", "model.layers.18.mlp.experts.down_proj_blocks": "model-00009-of-00014.safetensors", "model.layers.18.mlp.experts.down_proj_scales": "model-00009-of-00014.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.19.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.o_proj.bias": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.sinks": "model-00009-of-00014.safetensors", "model.layers.19.mlp.router.bias": "model-00009-of-00014.safetensors", "model.layers.19.mlp.router.weight": "model-00009-of-00014.safetensors", "model.layers.19.mlp.experts.gate_up_proj_bias": "model-00009-of-00014.safetensors", "model.layers.19.mlp.experts.gate_up_proj_blocks": "model-00009-of-00014.safetensors", "model.layers.19.mlp.experts.gate_up_proj_scales": "model-00009-of-00014.safetensors", "model.layers.19.mlp.experts.down_proj_bias": "model-00009-of-00014.safetensors", "model.layers.19.mlp.experts.down_proj_blocks": "model-00009-of-00014.safetensors", "model.layers.19.mlp.experts.down_proj_scales": "model-00009-of-00014.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.2.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.2.self_attn.o_proj.bias": "model-00009-of-00014.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00009-of-00014.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00009-of-00014.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00009-of-00014.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.2.self_attn.sinks": "model-00009-of-00014.safetensors", "model.layers.2.mlp.router.bias": "model-00009-of-00014.safetensors", "model.layers.2.mlp.router.weight": "model-00009-of-00014.safetensors", "model.layers.2.mlp.experts.gate_up_proj_bias": "model-00009-of-00014.safetensors", "model.layers.0.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.0.self_attn.o_proj.bias": "model-00009-of-00014.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00009-of-00014.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00009-of-00014.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00009-of-00014.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.0.self_attn.sinks": "model-00009-of-00014.safetensors", "model.layers.0.mlp.router.bias": "model-00009-of-00014.safetensors", "model.layers.0.mlp.router.weight": "model-00009-of-00014.safetensors", "model.layers.0.mlp.experts.gate_up_proj_bias": "model-00009-of-00014.safetensors", "model.layers.0.mlp.experts.gate_up_proj_blocks": "model-00009-of-00014.safetensors", "model.layers.0.mlp.experts.gate_up_proj_scales": "model-00009-of-00014.safetensors", "model.layers.0.mlp.experts.down_proj_bias": "model-00009-of-00014.safetensors", "model.layers.0.mlp.experts.down_proj_blocks": "model-00009-of-00014.safetensors", "model.layers.0.mlp.experts.down_proj_scales": "model-00009-of-00014.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.1.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.1.self_attn.o_proj.bias": "model-00009-of-00014.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00009-of-00014.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00009-of-00014.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00009-of-00014.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.1.self_attn.sinks": "model-00009-of-00014.safetensors", "model.layers.1.mlp.router.bias": "model-00009-of-00014.safetensors", "model.layers.1.mlp.router.weight": "model-00009-of-00014.safetensors", "model.layers.1.mlp.experts.gate_up_proj_bias": "model-00009-of-00014.safetensors", "model.layers.1.mlp.experts.gate_up_proj_blocks": "model-00010-of-00014.safetensors", "model.layers.1.mlp.experts.gate_up_proj_scales": "model-00010-of-00014.safetensors", "model.layers.1.mlp.experts.down_proj_bias": "model-00010-of-00014.safetensors", "model.layers.1.mlp.experts.down_proj_blocks": "model-00010-of-00014.safetensors", "model.layers.1.mlp.experts.down_proj_scales": "model-00010-of-00014.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.10.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.10.self_attn.o_proj.bias": "model-00010-of-00014.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00010-of-00014.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00010-of-00014.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00010-of-00014.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.10.self_attn.sinks": "model-00010-of-00014.safetensors", "model.layers.10.mlp.router.bias": "model-00010-of-00014.safetensors", "model.layers.10.mlp.router.weight": "model-00010-of-00014.safetensors", "model.layers.10.mlp.experts.gate_up_proj_bias": "model-00010-of-00014.safetensors", "model.layers.10.mlp.experts.gate_up_proj_blocks": "model-00010-of-00014.safetensors", "model.layers.10.mlp.experts.gate_up_proj_scales": "model-00010-of-00014.safetensors", "model.layers.10.mlp.experts.down_proj_bias": "model-00010-of-00014.safetensors", "model.layers.10.mlp.experts.down_proj_blocks": "model-00010-of-00014.safetensors", "model.layers.10.mlp.experts.down_proj_scales": "model-00010-of-00014.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.11.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.11.self_attn.o_proj.bias": "model-00010-of-00014.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00010-of-00014.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00010-of-00014.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00010-of-00014.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.11.self_attn.sinks": "model-00010-of-00014.safetensors", "model.layers.11.mlp.router.bias": "model-00010-of-00014.safetensors", "model.layers.11.mlp.router.weight": "model-00010-of-00014.safetensors", "model.layers.11.mlp.experts.gate_up_proj_bias": "model-00010-of-00014.safetensors", "model.layers.11.mlp.experts.gate_up_proj_blocks": "model-00010-of-00014.safetensors", "model.layers.11.mlp.experts.gate_up_proj_scales": "model-00010-of-00014.safetensors", "model.layers.11.mlp.experts.down_proj_bias": "model-00010-of-00014.safetensors", "model.layers.11.mlp.experts.down_proj_blocks": "model-00011-of-00014.safetensors", "model.layers.11.mlp.experts.down_proj_scales": "model-00011-of-00014.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.12.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.12.self_attn.o_proj.bias": "model-00011-of-00014.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00011-of-00014.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00011-of-00014.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00011-of-00014.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.12.self_attn.sinks": "model-00011-of-00014.safetensors", "model.layers.12.mlp.router.bias": "model-00011-of-00014.safetensors", "model.layers.12.mlp.router.weight": "model-00011-of-00014.safetensors", "model.layers.12.mlp.experts.gate_up_proj_bias": "model-00011-of-00014.safetensors", "model.layers.12.mlp.experts.gate_up_proj_blocks": "model-00011-of-00014.safetensors", "model.layers.12.mlp.experts.gate_up_proj_scales": "model-00011-of-00014.safetensors", "model.layers.12.mlp.experts.down_proj_bias": "model-00011-of-00014.safetensors", "model.layers.12.mlp.experts.down_proj_blocks": "model-00011-of-00014.safetensors", "model.layers.12.mlp.experts.down_proj_scales": "model-00011-of-00014.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.13.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.13.self_attn.o_proj.bias": "model-00011-of-00014.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00011-of-00014.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00011-of-00014.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00011-of-00014.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.13.self_attn.sinks": "model-00011-of-00014.safetensors", "model.layers.13.mlp.router.bias": "model-00011-of-00014.safetensors", "model.layers.13.mlp.router.weight": "model-00011-of-00014.safetensors", "model.layers.13.mlp.experts.gate_up_proj_bias": "model-00011-of-00014.safetensors", "model.layers.13.mlp.experts.gate_up_proj_blocks": "model-00011-of-00014.safetensors", "model.layers.13.mlp.experts.gate_up_proj_scales": "model-00011-of-00014.safetensors", "model.layers.13.mlp.experts.down_proj_bias": "model-00011-of-00014.safetensors", "model.layers.13.mlp.experts.down_proj_blocks": "model-00011-of-00014.safetensors", "model.layers.13.mlp.experts.down_proj_scales": "model-00011-of-00014.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.14.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.14.self_attn.o_proj.bias": "model-00011-of-00014.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00011-of-00014.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00011-of-00014.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00011-of-00014.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.14.self_attn.sinks": "model-00011-of-00014.safetensors", "model.layers.14.mlp.router.bias": "model-00011-of-00014.safetensors", "model.layers.14.mlp.router.weight": "model-00011-of-00014.safetensors", "model.layers.14.mlp.experts.gate_up_proj_bias": "model-00011-of-00014.safetensors", "model.embed_tokens.weight": "model-00012-of-00014.safetensors", "model.norm.weight": "model-00012-of-00014.safetensors", "lm_head.weight": "model-00012-of-00014.safetensors", "model.layers.30.mlp.experts.gate_up_proj_blocks": "model-00012-of-00014.safetensors", "model.layers.30.mlp.experts.gate_up_proj_scales": "model-00012-of-00014.safetensors", "model.layers.30.mlp.experts.down_proj_bias": "model-00012-of-00014.safetensors", "model.layers.30.mlp.experts.down_proj_blocks": "model-00012-of-00014.safetensors", "model.layers.30.mlp.experts.down_proj_scales": "model-00012-of-00014.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.31.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.o_proj.bias": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.sinks": "model-00012-of-00014.safetensors", "model.layers.31.mlp.router.bias": "model-00012-of-00014.safetensors", "model.layers.31.mlp.router.weight": "model-00012-of-00014.safetensors", "model.layers.31.mlp.experts.gate_up_proj_bias": "model-00012-of-00014.safetensors", "model.layers.31.mlp.experts.gate_up_proj_blocks": "model-00013-of-00014.safetensors", "model.layers.31.mlp.experts.gate_up_proj_scales": "model-00013-of-00014.safetensors", "model.layers.31.mlp.experts.down_proj_bias": "model-00013-of-00014.safetensors", "model.layers.31.mlp.experts.down_proj_blocks": "model-00013-of-00014.safetensors", "model.layers.31.mlp.experts.down_proj_scales": "model-00013-of-00014.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.32.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.o_proj.bias": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.sinks": "model-00013-of-00014.safetensors", "model.layers.32.mlp.router.bias": "model-00013-of-00014.safetensors", "model.layers.32.mlp.router.weight": "model-00013-of-00014.safetensors", "model.layers.32.mlp.experts.gate_up_proj_bias": "model-00013-of-00014.safetensors", "model.layers.32.mlp.experts.gate_up_proj_blocks": "model-00013-of-00014.safetensors", "model.layers.32.mlp.experts.gate_up_proj_scales": "model-00013-of-00014.safetensors", "model.layers.32.mlp.experts.down_proj_bias": "model-00013-of-00014.safetensors", "model.layers.32.mlp.experts.down_proj_blocks": "model-00013-of-00014.safetensors", "model.layers.32.mlp.experts.down_proj_scales": "model-00013-of-00014.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.33.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.o_proj.bias": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.sinks": "model-00013-of-00014.safetensors", "model.layers.33.mlp.router.bias": "model-00013-of-00014.safetensors", "model.layers.33.mlp.router.weight": "model-00013-of-00014.safetensors", "model.layers.33.mlp.experts.gate_up_proj_bias": "model-00013-of-00014.safetensors", "model.layers.33.mlp.experts.gate_up_proj_blocks": "model-00013-of-00014.safetensors", "model.layers.33.mlp.experts.gate_up_proj_scales": "model-00013-of-00014.safetensors", "model.layers.33.mlp.experts.down_proj_bias": "model-00013-of-00014.safetensors", "model.layers.33.mlp.experts.down_proj_blocks": "model-00014-of-00014.safetensors", "model.layers.33.mlp.experts.down_proj_scales": "model-00014-of-00014.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.34.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.34.self_attn.o_proj.bias": "model-00014-of-00014.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00014-of-00014.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00014-of-00014.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00014-of-00014.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.34.self_attn.sinks": "model-00014-of-00014.safetensors", "model.layers.34.mlp.router.bias": "model-00014-of-00014.safetensors", "model.layers.34.mlp.router.weight": "model-00014-of-00014.safetensors", "model.layers.34.mlp.experts.gate_up_proj_bias": "model-00014-of-00014.safetensors", "model.layers.34.mlp.experts.gate_up_proj_blocks": "model-00014-of-00014.safetensors", "model.layers.34.mlp.experts.gate_up_proj_scales": "model-00014-of-00014.safetensors", "model.layers.34.mlp.experts.down_proj_bias": "model-00014-of-00014.safetensors", "model.layers.34.mlp.experts.down_proj_blocks": "model-00014-of-00014.safetensors", "model.layers.34.mlp.experts.down_proj_scales": "model-00014-of-00014.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.35.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.35.self_attn.o_proj.bias": "model-00014-of-00014.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00014-of-00014.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00014-of-00014.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00014-of-00014.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.35.self_attn.sinks": "model-00014-of-00014.safetensors", "model.layers.35.mlp.router.bias": "model-00014-of-00014.safetensors", "model.layers.35.mlp.router.weight": "model-00014-of-00014.safetensors", "model.layers.35.mlp.experts.gate_up_proj_bias": "model-00014-of-00014.safetensors", "model.layers.35.mlp.experts.gate_up_proj_blocks": "model-00014-of-00014.safetensors", "model.layers.35.mlp.experts.gate_up_proj_scales": "model-00014-of-00014.safetensors", "model.layers.35.mlp.experts.down_proj_bias": "model-00014-of-00014.safetensors", "model.layers.35.mlp.experts.down_proj_blocks": "model-00014-of-00014.safetensors", "model.layers.35.mlp.experts.down_proj_scales": "model-00014-of-00014.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.4.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.4.self_attn.o_proj.bias": "model-00014-of-00014.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00014-of-00014.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00014-of-00014.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00014-of-00014.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.4.self_attn.sinks": "model-00014-of-00014.safetensors", "model.layers.4.mlp.router.bias": "model-00014-of-00014.safetensors", "model.layers.4.mlp.router.weight": "model-00014-of-00014.safetensors", "model.layers.4.mlp.experts.gate_up_proj_bias": "model-00014-of-00014.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|startoftext|>",
+  "eos_token": "<|return|>",
+  "pad_token": "<|endoftext|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
+size 27868174

tokenizer_config.json

@@ -0,0 +1,183 @@
+{
+  "added_tokens_decoder": {
+    "199998": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "199999": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200000": {
+      "content": "<|reserved_200000|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200001": {
+      "content": "<|reserved_200001|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200002": {
+      "content": "<|return|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200003": {
+      "content": "<|constrain|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200004": {
+      "content": "<|reserved_200004|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200005": {
+      "content": "<|channel|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200006": {
+      "content": "<|start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200008": {
+      "content": "<|message|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200009": {
+      "content": "<|reserved_200009|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200010": {
+      "content": "<|reserved_200010|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200011": {
+      "content": "<|reserved_200011|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200012": {
+      "content": "<|call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200013": {
+      "content": "<|reserved_200013|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200014": {
+      "content": "<|reserved_200014|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200015": {
+      "content": "<|reserved_200015|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200016": {
+      "content": "<|reserved_200016|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200017": {
+      "content": "<|reserved_200017|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200018": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|return|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}