Upload 14 files

added_tokens.json

@@ -0,0 +1,41 @@
+{
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257,
+  "<|eot_id|>": 50295
+}

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "/data2/caoty/convert/phi2_0.45_0-31_gsm8k_second",
+  "architectures": [
+    "PhiPrunedForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_pruned_phi.PhiPrunedConfig",
+    "AutoModel": "modeling_pruned_phi.PhiPrunedForCausalLM",
+    "AutoModelForCausalLM": "modeling_pruned_phi.PhiPrunedForCausalLM"
+  },
+  "begin_pruned_layer": 0,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "end_pruned_layer": 32,
+  "eos_token_id": 50256,
+  "hidden_act": "gelu_new",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "phi",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "partial_rotary_factor": 0.4,
+  "qk_layernorm": false,
+  "resid_pdrop": 0.1,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.45.2",
+  "use_cache": true,
+  "vocab_size": 51200
+}

configuration_pruned_phi.py

@@ -0,0 +1,84 @@
+
+from transformers import PretrainedConfig
+
+
+class PhiPrunedConfig(PretrainedConfig):
+    model_type = "phi"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+            self,
+            vocab_size=51200,
+            hidden_size=2048,
+            intermediate_size=8192,
+            num_hidden_layers=24,
+            num_attention_heads=32,
+            num_key_value_heads=None,
+            resid_pdrop=0.0,
+            embd_pdrop=0.0,
+            attention_dropout=0.0,
+            hidden_act="gelu_new",
+            max_position_embeddings=2048,
+            initializer_range=0.02,
+            layer_norm_eps=1e-5,
+            use_cache=True,
+            tie_word_embeddings=False,
+            rope_theta=10000.0,
+            rope_scaling=None,
+            partial_rotary_factor=0.5,
+            qk_layernorm=False,
+            bos_token_id=1,
+            eos_token_id=2,
+            begin_pruned_layer=None,
+            end_pruned_layer=None,
+            **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+
+        if num_key_value_heads is None:
+            num_key_value_heads = num_attention_heads
+
+        self.num_key_value_heads = num_key_value_heads
+        self.resid_pdrop = resid_pdrop
+        self.embd_pdrop = embd_pdrop
+        self.attention_dropout = attention_dropout
+        self.hidden_act = hidden_act
+        self.max_position_embeddings = max_position_embeddings
+        self.initializer_range = initializer_range
+        self.layer_norm_eps = layer_norm_eps
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.rope_scaling = rope_scaling
+        self.partial_rotary_factor = partial_rotary_factor
+        self.qk_layernorm = qk_layernorm
+        self._rope_scaling_validation()
+
+        self.begin_pruned_layer = begin_pruned_layer
+        self.end_pruned_layer = end_pruned_layer
+        super().__init__(
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )
+
+    def _rope_scaling_validation(self):
+        if self.rope_scaling is None:
+            return
+
+        if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 2:
+            raise ValueError(
+                "`rope_scaling` must be a dictionary with two fields, `type` and `factor`, " f"got {self.rope_scaling}"
+            )
+        rope_scaling_type = self.rope_scaling.get("type", None)
+        rope_scaling_factor = self.rope_scaling.get("factor", None)
+        if rope_scaling_type is None or rope_scaling_type not in ["linear", "dynamic"]:
+            raise ValueError(
+                f"`rope_scaling`'s type field must be one of ['linear', 'dynamic'], got {rope_scaling_type}"
+            )
+        if rope_scaling_factor is None or not isinstance(rope_scaling_factor, float) or rope_scaling_factor <= 1.0:
+            raise ValueError(f"`rope_scaling`'s factor field must be a float > 1, got {rope_scaling_factor}")

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "do_sample": true,
+  "eos_token_id": 50256,
+  "transformers_version": "4.45.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9818d66ab771784d637ebf355b3f9fb863a74799e87750a6ac8e35d6b757443d
+size 1979866336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8975c6e1c84fdd8af23e5c83f305d6441731e21589607a61b2c9db979b54e2e8
+size 1953739648

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb41f56b2e111165c243088b0b494f4c4dd145ca7ff95be9cff94d510d84764d
+size 367151112

model.safetensors.index.json

@@ -0,0 +1,460 @@
+{
+  "metadata": {
+    "total_size": 4300707840
+  },
+  "weight_map": {
+    "lm_head.bias": "model-00003-of-00003.safetensors",
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.final_layernorm.bias": "model-00003-of-00003.safetensors",
+    "model.final_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.0.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.3.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.4.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors"
+  }
+}

modeling_pruned_phi.py

@@ -0,0 +1,28 @@
+
+import torch
+from transformers import PhiForCausalLM
+from .configuration_pruned_phi import PhiPrunedConfig
+import torch.nn as nn
+
+
+class PhiPrunedForCausalLM(PhiForCausalLM):
+    config_class = PhiPrunedConfig
+
+    def __init__(self, config: PhiPrunedConfig):
+        super().__init__(config)
+        for i in range(32):
+            self.model.layers[i].self_attn.dense = nn.Linear(640, 2560, bias=True)
+            self.model.layers[i].self_attn.hidden_size = 640
+            self.model.layers[i].self_attn.q_proj = nn.Linear(2560, 640, bias=True)
+            self.model.layers[i].self_attn.k_proj = nn.Linear(2560, 640, bias=True)
+            self.model.layers[i].self_attn.v_proj = nn.Linear(2560, 640, bias=True)
+
+            self.model.layers[i].mlp.fc1 = nn.Linear(2560, 10240, bias=True)
+            self.model.layers[i].mlp.fc2 = nn.Linear(10240, 2560, bias=True)
+
+        
+
+        for layer in self.model.layers:
+            layer.self_attn.num_heads = layer.self_attn.q_proj.weight.data.shape[0] // layer.self_attn.head_dim
+            layer.self_attn.num_key_value_heads = layer.self_attn.k_proj.weight.data.shape[
+                                                      0] // layer.self_attn.head_dim

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,328 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "                               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "                         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50281": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50282": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50283": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50284": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50285": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "return_token_type_ids": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}