Upload 6 files

added_tokens.json

@@ -0,0 +1,42 @@
+{
+  "\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,
+  "<|im_end|>": 50295,
+  "<|im_start|>": 50296
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "vince62s/phi-2-psy",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "PhiForCausalLM"
+  ],
+  "attn_pdrop": 0.0,
+  "auto_map": {
+    "AutoConfig": "vince62s/phi-2-psy--configuration_phi.PhiConfig",
+    "AutoModelForCausalLM": "vince62s/phi-2-psy--modeling_phi.PhiForCausalLM"
+  },
+  "embd_pdrop": 0.0,
+  "flash_attn": false,
+  "flash_rotary": false,
+  "fused_dense": false,
+  "img_processor": null,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "phi-msft",
+  "n_embd": 2560,
+  "n_head": 32,
+  "n_head_kv": null,
+  "n_inner": null,
+  "n_layer": 32,
+  "n_positions": 2048,
+  "resid_pdrop": 0.1,
+  "rotary_dim": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.2",
+  "use_cache": false,
+  "vocab_size": 51200
+}

configuration_phi.py

@@ -0,0 +1,62 @@
+# Copyright (c) Microsoft Corporation.
+# Licensed under the MIT license.
+
+import math
+from typing import Optional
+
+from transformers import PretrainedConfig
+
+
+class PhiConfig(PretrainedConfig):
+    """Phi configuration."""
+
+    model_type = "phi-msft"
+    attribute_map = {
+        "max_position_embeddings": "n_positions",
+        "hidden_size": "n_embd",
+        "num_attention_heads": "n_head",
+        "num_hidden_layers": "n_layer",
+    }
+
+    def __init__(
+        self,
+        vocab_size: int = 50304,
+        n_positions: int = 2048,
+        n_embd: int = 1024,
+        n_layer: int = 20,
+        n_inner: Optional[int] = None,
+        n_head: int = 16,
+        n_head_kv: Optional[int] = None,
+        rotary_dim: Optional[int] = 32,
+        activation_function: Optional[str] = "gelu_new",
+        flash_attn: bool = False,
+        flash_rotary: bool = False,
+        fused_dense: bool = False,
+        attn_pdrop: float = 0.0,
+        embd_pdrop: float = 0.0,
+        resid_pdrop: float = 0.0,
+        layer_norm_epsilon: float = 1e-5,
+        initializer_range: float = 0.02,
+        tie_word_embeddings: bool = False,
+        pad_vocab_size_multiple: int = 64,
+        **kwargs
+    ) -> None:
+        self.vocab_size = int(math.ceil(vocab_size / pad_vocab_size_multiple) * pad_vocab_size_multiple)
+        self.n_positions = n_positions
+        self.n_embd = n_embd
+        self.n_layer = n_layer
+        self.n_inner = n_inner
+        self.n_head = n_head
+        self.n_head_kv = n_head_kv
+        self.rotary_dim = min(rotary_dim, n_embd // n_head)
+        self.activation_function = activation_function
+        self.flash_attn = flash_attn
+        self.flash_rotary = flash_rotary
+        self.fused_dense = fused_dense
+        self.attn_pdrop = attn_pdrop
+        self.embd_pdrop = embd_pdrop
+        self.resid_pdrop = resid_pdrop
+        self.layer_norm_epsilon = layer_norm_epsilon
+        self.initializer_range = initializer_range
+
+        super().__init__(tie_word_embeddings=tie_word_embeddings, **kwargs)

mergekit_config.yml

@@ -0,0 +1,17 @@
+
+slices:
+  - sources:
+      - model: rhysjones/phi-2-orange
+        layer_range: [0, 32]
+      - model: cognitivecomputations/dolphin-2_6-phi-2
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: rhysjones/phi-2-orange
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.3.2"}, "weight_map": {"transformer.embd.wte.weight": "model-00001-of-00003.safetensors", "transformer.h.0.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.0.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.0.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.0.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.0.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.0.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.0.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.0.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.0.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.0.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.1.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.1.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.1.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.1.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.1.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.1.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.1.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.1.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.1.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.1.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.10.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.10.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.10.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.10.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.10.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.10.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.10.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.10.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.10.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.10.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.11.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.11.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.11.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.11.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.11.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.11.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.11.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.11.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.11.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.11.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.12.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.12.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.12.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.12.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.12.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.12.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.12.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.12.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.12.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.12.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.13.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.13.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.13.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.13.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.13.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.13.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.13.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.13.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.13.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.13.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.14.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.14.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.14.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.14.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.14.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.14.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.14.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.14.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.14.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.14.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.15.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.15.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.15.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.15.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.15.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.15.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.15.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.15.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.15.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.15.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.16.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.16.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.16.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.16.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.16.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.16.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.16.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.16.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.16.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.16.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.17.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.17.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.17.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.17.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.17.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.17.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.17.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.17.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.17.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.17.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.18.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.18.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.18.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.18.mixer.Wqkv.weight": "model-00001-of-00003.safetensors", "transformer.h.18.mixer.out_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.18.mixer.out_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.18.mlp.fc1.bias": "model-00001-of-00003.safetensors", "transformer.h.18.mlp.fc1.weight": "model-00001-of-00003.safetensors", "transformer.h.18.mlp.fc2.bias": "model-00001-of-00003.safetensors", "transformer.h.18.mlp.fc2.weight": "model-00001-of-00003.safetensors", "transformer.h.19.ln.bias": "model-00001-of-00003.safetensors", "transformer.h.19.ln.weight": "model-00001-of-00003.safetensors", "transformer.h.19.mixer.Wqkv.bias": "model-00001-of-00003.safetensors", "transformer.h.19.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.19.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.19.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.19.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.19.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.19.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.19.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.2.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.2.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.2.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.2.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.2.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.2.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.2.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.2.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.2.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.2.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.20.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.20.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.20.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.20.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.20.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.20.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.20.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.20.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.20.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.20.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.21.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.21.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.21.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.21.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.21.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.21.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.21.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.21.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.21.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.21.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.22.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.22.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.22.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.22.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.22.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.22.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.22.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.22.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.22.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.22.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.23.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.23.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.23.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.23.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.23.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.23.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.23.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.23.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.23.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.23.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.24.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.24.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.24.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.24.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.24.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.24.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.24.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.24.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.24.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.24.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.25.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.25.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.25.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.25.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.25.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.25.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.25.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.25.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.25.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.25.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.26.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.26.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.26.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.26.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.26.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.26.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.26.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.26.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.26.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.26.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.27.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.27.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.27.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.27.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.27.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.27.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.27.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.27.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.27.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.27.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.28.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.28.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.28.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.28.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.28.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.28.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.28.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.28.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.28.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.28.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.29.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.29.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.29.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.29.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.29.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.29.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.29.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.29.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.29.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.29.mlp.fc2.weight": "model-00002-of-00003.safetensors", "transformer.h.3.ln.bias": "model-00002-of-00003.safetensors", "transformer.h.3.ln.weight": "model-00002-of-00003.safetensors", "transformer.h.3.mixer.Wqkv.bias": "model-00002-of-00003.safetensors", "transformer.h.3.mixer.Wqkv.weight": "model-00002-of-00003.safetensors", "transformer.h.3.mixer.out_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.3.mixer.out_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.3.mlp.fc1.bias": "model-00002-of-00003.safetensors", "transformer.h.3.mlp.fc1.weight": "model-00002-of-00003.safetensors", "transformer.h.3.mlp.fc2.bias": "model-00002-of-00003.safetensors", "transformer.h.3.mlp.fc2.weight": "model-00003-of-00003.safetensors", "transformer.h.30.ln.bias": "model-00003-of-00003.safetensors", "transformer.h.30.ln.weight": "model-00003-of-00003.safetensors", "transformer.h.4.ln.bias": "model-00003-of-00003.safetensors", "transformer.h.4.ln.weight": "model-00003-of-00003.safetensors", "transformer.h.4.mixer.Wqkv.bias": "model-00003-of-00003.safetensors", "transformer.h.4.mixer.Wqkv.weight": "model-00003-of-00003.safetensors", "transformer.h.4.mixer.out_proj.bias": "model-00003-of-00003.safetensors", "transformer.h.4.mixer.out_proj.weight": "model-00003-of-00003.safetensors", "transformer.h.4.mlp.fc1.bias": "model-00003-of-00003.safetensors", "transformer.h.4.mlp.fc1.weight": "model-00003-of-00003.safetensors", "transformer.h.4.mlp.fc2.bias": "model-00003-of-00003.safetensors", "transformer.h.4.mlp.fc2.weight": "model-00003-of-00003.safetensors", "transformer.h.5.ln.bias": "model-00003-of-00003.safetensors", "transformer.h.5.ln.weight": "model-00003-of-00003.safetensors", "transformer.h.5.mixer.Wqkv.bias": "model-00003-of-00003.safetensors", "transformer.h.5.mixer.Wqkv.weight": "model-00003-of-00003.safetensors", "transformer.h.5.mixer.out_proj.bias": "model-00003-of-00003.safetensors", "transformer.h.5.mixer.out_proj.weight": "model-00003-of-00003.safetensors", "transformer.h.5.mlp.fc1.bias": "model-00003-of-00003.safetensors", "transformer.h.5.mlp.fc1.weight": "model-00003-of-00003.safetensors", "transformer.h.5.mlp.fc2.bias": "model-00003-of-00003.safetensors", "transformer.h.5.mlp.fc2.weight": "model-00003-of-00003.safetensors", "transformer.h.6.ln.bias": "model-00003-of-00003.safetensors", "transformer.h.6.ln.weight": "model-00003-of-00003.safetensors", "transformer.h.6.mixer.Wqkv.bias": "model-00003-of-00003.safetensors", "transformer.h.6.mixer.Wqkv.weight": "model-00003-of-00003.safetensors", "transformer.h.6.mixer.out_proj.bias": "model-00003-of-00003.safetensors", "transformer.h.6.mixer.out_proj.weight": "model-00003-of-00003.safetensors", "transformer.h.6.mlp.fc1.bias": "model-00003-of-00003.safetensors", "transformer.h.6.mlp.fc1.weight": "model-00003-of-00003.safetensors", "transformer.h.6.mlp.fc2.bias": "model-00003-of-00003.safetensors", "transformer.h.6.mlp.fc2.weight": "model-00003-of-00003.safetensors", "transformer.h.7.ln.bias": "model-00003-of-00003.safetensors", "transformer.h.7.ln.weight": "model-00003-of-00003.safetensors", "transformer.h.7.mixer.Wqkv.bias": "model-00003-of-00003.safetensors", "transformer.h.7.mixer.Wqkv.weight": "model-00003-of-00003.safetensors", "transformer.h.7.mixer.out_proj.bias": "model-00003-of-00003.safetensors", "transformer.h.7.mixer.out_proj.weight": "model-00003-of-00003.safetensors", "transformer.h.7.mlp.fc1.bias": "model-00003-of-00003.safetensors", "transformer.h.7.mlp.fc1.weight": "model-00003-of-00003.safetensors", "transformer.h.7.mlp.fc2.bias": "model-00003-of-00003.safetensors", "transformer.h.7.mlp.fc2.weight": "model-00003-of-00003.safetensors", "transformer.h.8.ln.bias": "model-00003-of-00003.safetensors", "transformer.h.8.ln.weight": "model-00003-of-00003.safetensors", "transformer.h.8.mixer.Wqkv.bias": "model-00003-of-00003.safetensors", "transformer.h.8.mixer.Wqkv.weight": "model-00003-of-00003.safetensors", "transformer.h.8.mixer.out_proj.bias": "model-00003-of-00003.safetensors", "transformer.h.8.mixer.out_proj.weight": "model-00003-of-00003.safetensors", "transformer.h.8.mlp.fc1.bias": "model-00003-of-00003.safetensors", "transformer.h.8.mlp.fc1.weight": "model-00003-of-00003.safetensors", "transformer.h.8.mlp.fc2.bias": "model-00003-of-00003.safetensors", "transformer.h.8.mlp.fc2.weight": "model-00003-of-00003.safetensors", "transformer.h.9.ln.bias": "model-00003-of-00003.safetensors", "transformer.h.9.ln.weight": "model-00003-of-00003.safetensors", "transformer.h.9.mixer.Wqkv.bias": "model-00003-of-00003.safetensors", "transformer.h.9.mixer.Wqkv.weight": "model-00003-of-00003.safetensors", "transformer.h.9.mixer.out_proj.bias": "model-00003-of-00003.safetensors", "transformer.h.9.mixer.out_proj.weight": "model-00003-of-00003.safetensors", "transformer.h.9.mlp.fc1.bias": "model-00003-of-00003.safetensors", "transformer.h.9.mlp.fc1.weight": "model-00003-of-00003.safetensors", "transformer.h.9.mlp.fc2.bias": "model-00003-of-00003.safetensors", "transformer.h.9.mlp.fc2.weight": "model-00003-of-00003.safetensors", "lm_head.linear.bias": "model-00003-of-00003.safetensors", "lm_head.linear.weight": "model-00003-of-00003.safetensors", "lm_head.ln.bias": "model-00003-of-00003.safetensors", "lm_head.ln.weight": "model-00003-of-00003.safetensors", "transformer.h.30.mixer.Wqkv.bias": "model-00003-of-00003.safetensors", "transformer.h.30.mixer.Wqkv.weight": "model-00003-of-00003.safetensors", "transformer.h.30.mixer.out_proj.bias": "model-00003-of-00003.safetensors", "transformer.h.30.mixer.out_proj.weight": "model-00003-of-00003.safetensors", "transformer.h.30.mlp.fc1.bias": "model-00003-of-00003.safetensors", "transformer.h.30.mlp.fc1.weight": "model-00003-of-00003.safetensors", "transformer.h.30.mlp.fc2.bias": "model-00003-of-00003.safetensors", "transformer.h.30.mlp.fc2.weight": "model-00003-of-00003.safetensors", "transformer.h.31.ln.bias": "model-00003-of-00003.safetensors", "transformer.h.31.ln.weight": "model-00003-of-00003.safetensors", "transformer.h.31.mixer.Wqkv.bias": "model-00003-of-00003.safetensors", "transformer.h.31.mixer.Wqkv.weight": "model-00003-of-00003.safetensors", "transformer.h.31.mixer.out_proj.bias": "model-00003-of-00003.safetensors", "transformer.h.31.mixer.out_proj.weight": "model-00003-of-00003.safetensors", "transformer.h.31.mlp.fc1.bias": "model-00003-of-00003.safetensors", "transformer.h.31.mlp.fc1.weight": "model-00003-of-00003.safetensors", "transformer.h.31.mlp.fc2.bias": "model-00003-of-00003.safetensors", "transformer.h.31.mlp.fc2.weight": "model-00003-of-00003.safetensors"}}