Merged weights from jetmoe-8b-ultrainteract-sft-lora-v4

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "jetmoe/jetmoe-8b",
+  "activation_function": "silu",
+  "architectures": [
+    "JetMoEForCausalLM"
+  ],
+  "bias": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "ffn_hidden_size": 5632,
+  "glu": true,
+  "hidden_size": 2048,
+  "initializer_range": 0.01,
+  "kv_channels": 128,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 4096,
+  "model_type": "jetmoe",
+  "moe_num_experts": 8,
+  "moe_top_k": 2,
+  "n_positions": 4096,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "num_layers": 24,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "rotary_percent": 1.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "4.40.0.dev0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14e2033590c0488eff6318a05c5e6d313683a240f7291826e852bd3eccc0db66
+size 4879573992

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e08abe8cae757733889f680e3e44e0433c6be08680d8e74cf49bf1c297a2e46
+size 4933084288

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef7c25dc7fa42309e9105b57a6a2dce8a116f2e70215ce85a87223f4c0db20e6
+size 4933084344

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcba9add38653bc71b9b6bede80ce2475f44b5734562408488f7abdfde29d525
+size 2298765576

model.safetensors.index.json

@@ -0,0 +1,273 @@
+{
+  "metadata": {
+    "total_size": 17044475904
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.input_linear.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.output_linear.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.router.layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attention.experts.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attention.experts.input_linear.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attention.experts.output_linear.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attention.experts.router.layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attention.kv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.input_linear.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.output_linear.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.router.layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attention.experts.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attention.experts.input_linear.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attention.experts.output_linear.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attention.experts.router.layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attention.kv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.input_linear.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.output_linear.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.router.layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attention.experts.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attention.experts.input_linear.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attention.experts.output_linear.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attention.experts.router.layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attention.kv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.input_linear.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.output_linear.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.router.layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attention.experts.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attention.experts.input_linear.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attention.experts.output_linear.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attention.experts.router.layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attention.kv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.input_linear.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.output_linear.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.router.layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attention.experts.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attention.experts.input_linear.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attention.experts.output_linear.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attention.experts.router.layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attention.kv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.input_linear.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.output_linear.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.mlp.router.layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attention.experts.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attention.experts.input_linear.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attention.experts.output_linear.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attention.experts.router.layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attention.kv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.mlp.bias": "model-00003-of-00004.safetensors",
+    "model.layers.14.mlp.input_linear.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.mlp.output_linear.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.mlp.router.layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.self_attention.experts.bias": "model-00003-of-00004.safetensors",
+    "model.layers.14.self_attention.experts.input_linear.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.self_attention.experts.output_linear.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.self_attention.experts.router.layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.self_attention.kv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.mlp.bias": "model-00003-of-00004.safetensors",
+    "model.layers.15.mlp.input_linear.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.mlp.output_linear.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.mlp.router.layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.self_attention.experts.bias": "model-00003-of-00004.safetensors",
+    "model.layers.15.self_attention.experts.input_linear.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.self_attention.experts.output_linear.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.self_attention.experts.router.layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.self_attention.kv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.bias": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.input_linear.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.output_linear.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.router.layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attention.experts.bias": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attention.experts.input_linear.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attention.experts.output_linear.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attention.experts.router.layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attention.kv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.input_linear.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.output_linear.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.router.layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attention.experts.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attention.experts.input_linear.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attention.experts.output_linear.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attention.experts.router.layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attention.kv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.input_linear.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.output_linear.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.router.layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attention.experts.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attention.experts.input_linear.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attention.experts.output_linear.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attention.experts.router.layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attention.kv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.input_linear.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.output_linear.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.router.layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attention.experts.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attention.experts.input_linear.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attention.experts.output_linear.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attention.experts.router.layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attention.kv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.input_linear.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.output_linear.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.router.layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attention.experts.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attention.experts.input_linear.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attention.experts.output_linear.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attention.experts.router.layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attention.kv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.input_linear.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.output_linear.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.mlp.router.layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attention.experts.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attention.experts.input_linear.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attention.experts.output_linear.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attention.experts.router.layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attention.kv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.mlp.bias": "model-00004-of-00004.safetensors",
+    "model.layers.21.mlp.input_linear.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.mlp.output_linear.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.mlp.router.layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.self_attention.experts.bias": "model-00004-of-00004.safetensors",
+    "model.layers.21.self_attention.experts.input_linear.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.self_attention.experts.output_linear.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.self_attention.experts.router.layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.self_attention.kv_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.mlp.bias": "model-00004-of-00004.safetensors",
+    "model.layers.22.mlp.input_linear.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.mlp.output_linear.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.mlp.router.layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.self_attention.experts.bias": "model-00004-of-00004.safetensors",
+    "model.layers.22.self_attention.experts.input_linear.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.self_attention.experts.output_linear.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.self_attention.experts.router.layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.self_attention.kv_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.mlp.bias": "model-00004-of-00004.safetensors",
+    "model.layers.23.mlp.input_linear.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.mlp.output_linear.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.mlp.router.layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.self_attention.experts.bias": "model-00004-of-00004.safetensors",
+    "model.layers.23.self_attention.experts.input_linear.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.self_attention.experts.output_linear.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.self_attention.experts.router.layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.self_attention.kv_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.input_linear.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.output_linear.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.router.layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attention.experts.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attention.experts.input_linear.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attention.experts.output_linear.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attention.experts.router.layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attention.kv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.input_linear.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.output_linear.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.router.layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attention.experts.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attention.experts.input_linear.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attention.experts.output_linear.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attention.experts.router.layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attention.kv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.input_linear.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.output_linear.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.router.layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attention.experts.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attention.experts.input_linear.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attention.experts.output_linear.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attention.experts.router.layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attention.kv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.input_linear.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.output_linear.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.router.layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attention.experts.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attention.experts.input_linear.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attention.experts.output_linear.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attention.experts.router.layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attention.kv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.input_linear.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.output_linear.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.router.layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attention.experts.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attention.experts.input_linear.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attention.experts.output_linear.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attention.experts.router.layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attention.kv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.input_linear.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.output_linear.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.router.layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attention.experts.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attention.experts.input_linear.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attention.experts.output_linear.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attention.experts.router.layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attention.kv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.input_linear.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.output_linear.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.router.layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attention.experts.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attention.experts.input_linear.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attention.experts.output_linear.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attention.experts.router.layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attention.kv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}