Initial model upload

.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

added_tokens.json

@@ -0,0 +1,12 @@
+{
+  "<|/tool_call|>": 200026,
+  "<|/tool|>": 200024,
+  "<|assistant|>": 200019,
+  "<|end|>": 200020,
+  "<|system|>": 200022,
+  "<|tag|>": 200028,
+  "<|tool_call|>": 200025,
+  "<|tool_response|>": 200027,
+  "<|tool|>": 200023,
+  "<|user|>": 200021
+}

config.json

@@ -0,0 +1,11 @@
+{
+  "architectures": [
+    "Phi4CodeLlamaModelMerger"
+  ],
+  "codellama_model_name": "/teamspace/studios/this_studio/model/codellama",
+  "hidden_size": 4096,
+  "model_type": "model_merger",
+  "phi_model_name": "/teamspace/studios/this_studio/model/phi-4",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.0"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5624ed4fc631805b0cb1b6bb5a2bfaaa831697c251da62675e7c9b2151fa94c0
+size 4903638824

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:997d6ec70d4c6eb975bad2e1e761327c91e732221748c554a08f3b0cd95df082
+size 4964349784

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a6436a39737355128731f7901b5f492712ac8252602b9dbd7d39e5dd366d59d
+size 4980963792

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:168e2e2ddd60e1e05048e60b0de5f969f3136909e024caff95d34c01ef74c192
+size 4957878664

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5b5684a254de43264ffbac4cb6d3f5646b29d9d4bb312ea1aa683c5a78075e1
+size 1929766320

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:799a84b4c51d2e70c3bf03ab0ac20b38ef237f9ff547a614d47cb8e56c143d9a
+size 3278681984

model.safetensors.index.json

@@ -0,0 +1,518 @@
+{
+  "metadata": {
+    "total_size": 25015213576
+  },
+  "weight_map": {
+    "codellama_adapter.bias": "model-00005-of-00006.safetensors",
+    "codellama_adapter.weight": "model-00005-of-00006.safetensors",
+    "codellama_model.lm_head.weight": "model-00005-of-00006.safetensors",
+    "codellama_model.model.embed_tokens.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.0.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.0.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.0.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.0.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.0.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.0.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.0.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.0.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.0.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.1.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.1.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.1.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.1.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.1.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.1.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.1.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.1.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.1.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.10.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.10.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.10.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.10.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.10.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.10.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.2.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.2.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.2.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.2.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.2.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.2.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.2.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.2.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.2.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "codellama_model.model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "codellama_model.model.layers.29.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "codellama_model.model.layers.29.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "codellama_model.model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "codellama_model.model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "codellama_model.model.layers.3.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.3.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.3.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.3.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.3.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.3.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.3.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.3.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "codellama_model.model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "codellama_model.model.layers.30.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "codellama_model.model.layers.30.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "codellama_model.model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "codellama_model.model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "codellama_model.model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "codellama_model.model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "codellama_model.model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "codellama_model.model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "codellama_model.model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "codellama_model.model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "codellama_model.model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "codellama_model.model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "codellama_model.model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "codellama_model.model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "codellama_model.model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "codellama_model.model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "codellama_model.model.layers.4.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.4.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.4.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.4.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.4.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "codellama_model.model.layers.5.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.5.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.5.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.5.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.5.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.5.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.5.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.5.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.5.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.6.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.6.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.6.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.6.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.6.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.6.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.6.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.6.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.6.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.7.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.7.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.7.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.7.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.7.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.7.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.7.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.7.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.7.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.8.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.8.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.8.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.8.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.8.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.8.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.8.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.8.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.8.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.9.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.9.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.9.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.9.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.9.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.9.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.9.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.9.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.layers.9.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "codellama_model.model.norm.weight": "model-00005-of-00006.safetensors",
+    "codellama_to_phi_attn.key.bias": "model-00005-of-00006.safetensors",
+    "codellama_to_phi_attn.key.weight": "model-00005-of-00006.safetensors",
+    "codellama_to_phi_attn.out_proj.bias": "model-00005-of-00006.safetensors",
+    "codellama_to_phi_attn.out_proj.weight": "model-00005-of-00006.safetensors",
+    "codellama_to_phi_attn.query.bias": "model-00005-of-00006.safetensors",
+    "codellama_to_phi_attn.query.weight": "model-00005-of-00006.safetensors",
+    "codellama_to_phi_attn.value.bias": "model-00005-of-00006.safetensors",
+    "codellama_to_phi_attn.value.weight": "model-00005-of-00006.safetensors",
+    "layer_norm.bias": "model-00006-of-00006.safetensors",
+    "layer_norm.weight": "model-00006-of-00006.safetensors",
+    "output_projection.bias": "model-00006-of-00006.safetensors",
+    "output_projection.weight": "model-00006-of-00006.safetensors",
+    "phi_adapter.bias": "model-00005-of-00006.safetensors",
+    "phi_adapter.weight": "model-00005-of-00006.safetensors",
+    "phi_model.model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.10.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.10.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.11.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.11.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.12.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.12.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.12.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.12.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.13.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.13.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.13.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.13.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.14.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.14.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.14.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.14.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.15.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.15.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.15.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.15.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.16.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.16.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.16.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.16.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.16.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.16.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.17.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.17.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.17.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.17.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.17.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.17.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.18.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.18.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.18.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.18.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.19.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.19.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.19.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.20.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.20.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.20.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.21.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.22.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.22.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.23.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.23.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.23.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.24.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.24.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.24.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.24.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.25.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.25.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.25.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.26.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.26.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.26.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.26.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.26.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.27.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.27.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.27.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.27.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.28.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.28.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.28.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.28.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.28.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.28.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.29.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.29.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.29.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.29.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.29.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.29.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.30.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.30.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.30.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.30.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.30.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.30.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.31.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.31.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.31.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.31.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.31.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.31.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
+    "phi_model.model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.6.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.7.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.8.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.9.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
+    "phi_model.model.norm.weight": "model-00002-of-00006.safetensors",
+    "phi_to_codellama_attn.key.bias": "model-00005-of-00006.safetensors",
+    "phi_to_codellama_attn.key.weight": "model-00005-of-00006.safetensors",
+    "phi_to_codellama_attn.out_proj.bias": "model-00005-of-00006.safetensors",
+    "phi_to_codellama_attn.out_proj.weight": "model-00005-of-00006.safetensors",
+    "phi_to_codellama_attn.query.bias": "model-00005-of-00006.safetensors",
+    "phi_to_codellama_attn.query.weight": "model-00005-of-00006.safetensors",
+    "phi_to_codellama_attn.value.bias": "model-00005-of-00006.safetensors",
+    "phi_to_codellama_attn.value.weight": "model-00005-of-00006.safetensors",
+    "router.router.bias": "model-00005-of-00006.safetensors",
+    "router.router.weight": "model-00005-of-00006.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:382cc235b56c725945e149cc25f191da667c836655efd0857b004320e90e91ea
+size 15524095

tokenizer_config.json

@@ -0,0 +1,112 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "199999": {
+      "content": "<|endoftext|>",
+      "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
+    },
+    "200019": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200020": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200021": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200022": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200023": {
+      "content": "<|tool|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200024": {
+      "content": "<|/tool|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200025": {
+      "content": "<|tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200026": {
+      "content": "<|/tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200027": {
+      "content": "<|tool_response|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200028": {
+      "content": "<|tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}