First model version

README.md

@@ -9,9 +9,7 @@ language:
 - code
 ---
 
-Converted from [bullerwins/Codestral-22B-v0.1-hf](https://huggingface.co/bullerwins/Codestral-22B-v0.1-hf)
-
-Using [exllamav2 0.1.1](https://github.com/turboderp/exllamav2)
+Converted using [this](https://huggingface.co/bullerwins/Codestral-22B-v0.1-hf/blob/main/convert_mistral_weights_to_hf-22B.py) script
 
 # Model Card for Codestral-22B-v0.1
 

config.json

@@ -0,0 +1,36 @@
+{
+    "architectures": [
+        "MistralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 6144,
+    "initializer_range": 0.02,
+    "intermediate_size": 16384,
+    "max_position_embeddings": 32768,
+    "model_type": "mistral",
+    "num_attention_heads": 48,
+    "num_hidden_layers": 56,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.40.2",
+    "use_cache": true,
+    "vocab_size": 32768,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.0.21",
+        "bits": 5.0,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 100,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

convert_mistral_weights_to_hf-22B.py

@@ -0,0 +1,290 @@
+# Copyright 2023 Mistral AI and The HuggingFace Inc. team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+import argparse
+import gc
+import json
+import os
+import shutil
+import warnings
+
+import torch
+from safetensors.torch import load_file as safe_load_file
+
+from transformers import (
+    LlamaTokenizer,
+    MistralConfig,
+    MistralForCausalLM,
+)
+
+
+try:
+    from transformers import LlamaTokenizerFast
+
+    tokenizer_class = LlamaTokenizerFast
+except ImportError as e:
+    warnings.warn(e)
+    warnings.warn(
+        "The converted tokenizer will be the `slow` tokenizer. To use the fast, update your `tokenizers` library and re-run the tokenizer conversion"
+    )
+    tokenizer_class = LlamaTokenizer
+
+"""
+Sample usage:
+
+```
+python src/transformers/models/mistral/convert_mistral_weights_to_hf.py \
+    --input_dir /path/to/downloaded/mistral/weights --model_size 22B --output_dir /output/path
+```
+
+Thereafter, models can be loaded via:
+
+```py
+from transformers import MistralForCausalLM, LlamaTokenizer
+
+model = MistralForCausalLM.from_pretrained("/output/path")
+tokenizer = LlamaTokenizer.from_pretrained("/output/path")
+```
+
+Important note: you need to be able to host the whole model in RAM to execute this script (even if the biggest versions
+come in several checkpoints they each contain a part of each weight of the model, so we need to load them all in RAM).
+"""
+
+NUM_SHARDS = {"22B": 1}
+
+
+def compute_intermediate_size(n, ffn_dim_multiplier=1, multiple_of=256):
+    return multiple_of * ((int(ffn_dim_multiplier * int(8 * n / 3)) + multiple_of - 1) // multiple_of)
+
+
+def read_json(path):
+    with open(path, "r") as f:
+        return json.load(f)
+
+
+def write_json(text, path):
+    with open(path, "w") as f:
+        json.dump(text, f)
+
+
+def write_model(model_path, input_base_path, model_size, tokenizer_path=None, safe_serialization=True, is_v3=False):
+    # for backward compatibility, before you needed the repo to be called `my_repo/model_size`
+    if not os.path.isfile(os.path.join(input_base_path, "params.json")):
+        input_base_path = os.path.join(input_base_path, model_size)
+
+    os.makedirs(model_path, exist_ok=True)
+    tmp_model_path = os.path.join(model_path, "tmp")
+    os.makedirs(tmp_model_path, exist_ok=True)
+
+    params = read_json(os.path.join(input_base_path, "params.json"))
+    num_shards = NUM_SHARDS[model_size]
+
+    sliding_window = params.get("sliding_window", None)
+
+    # For some reason this is a string in the params.json
+    if sliding_window is not None:
+        sliding_window = int(sliding_window)
+
+    n_layers = params["n_layers"]
+    n_heads = params["n_heads"]
+    n_heads_per_shard = n_heads // num_shards
+    dim = params["dim"]
+    dims_per_head = dim // n_heads
+    base = params.get("rope_theta", 10000.0)
+    inv_freq = 1.0 / (base ** (torch.arange(0, dims_per_head, 2).float() / dims_per_head))
+    max_position_embeddings = 4096 * 8
+
+    if tokenizer_path is not None:
+        tokenizer = tokenizer_class(tokenizer_path + ".v3" if is_v3 else "")
+        tokenizer.save_pretrained(model_path)
+    vocab_size = tokenizer.vocab_size if tokenizer_path is not None else 32000
+
+    if "n_kv_heads" in params:
+        num_key_value_heads = params["n_kv_heads"]  # for GQA / MQA
+        num_local_key_value_heads = num_key_value_heads // num_shards
+        key_value_dim = dims_per_head * num_local_key_value_heads
+    else:  # compatibility with other checkpoints
+        num_key_value_heads = n_heads
+        num_local_key_value_heads = n_heads_per_shard
+        key_value_dim = dim
+
+    # permute for sliced rotary
+    def permute(w, n_heads=n_heads, dim1=dim, dim2=dim):
+        return w.view(n_heads, dim1 // n_heads // 2, 2, dim2).transpose(1, 2).reshape(dim1, dim2)
+
+    print(f"Fetching all parameters from the checkpoint at {input_base_path}.")
+
+    # Load weights - for v3 models the consolidated weights are in a single file format in safetensors
+    if is_v3:
+        loaded = [safe_load_file(os.path.join(input_base_path, "consolidated.safetensors"))]
+    else:
+        loaded = [
+            torch.load(os.path.join(input_base_path, f"consolidated.{i:02d}.pth"), map_location="cpu")
+            for i in range(num_shards)
+        ]
+    param_count = 0
+    index_dict = {"weight_map": {}}
+    for layer_i in range(n_layers):
+        filename = f"pytorch_model-{layer_i + 1}-of-{n_layers + 1}.bin"
+
+        # Sharded
+        # Note that attention.w{q,k,v,o}, feed_fordward.w[1,2,3], attention_norm.weight and ffn_norm.weight share
+        # the same storage object, saving attention_norm and ffn_norm will save other weights too, which is
+        # redundant as other weights will be stitched from multiple shards. To avoid that, they are cloned.
+
+        state_dict = {
+            f"model.layers.{layer_i}.input_layernorm.weight": loaded[0][
+                f"layers.{layer_i}.attention_norm.weight"
+            ].clone(),
+            f"model.layers.{layer_i}.post_attention_layernorm.weight": loaded[0][
+                f"layers.{layer_i}.ffn_norm.weight"
+            ].clone(),
+        }
+        state_dict[f"model.layers.{layer_i}.self_attn.q_proj.weight"] = permute(
+            torch.cat(
+                [
+                    loaded[i][f"layers.{layer_i}.attention.wq.weight"].view(n_heads_per_shard, dims_per_head, dim)
+                    for i in range(num_shards)
+                ],
+                dim=0,
+            ).reshape(dim, dim)
+        )
+        state_dict[f"model.layers.{layer_i}.self_attn.k_proj.weight"] = permute(
+            torch.cat(
+                [
+                    loaded[i][f"layers.{layer_i}.attention.wk.weight"].view(
+                        num_local_key_value_heads, dims_per_head, dim
+                    )
+                    for i in range(num_shards)
+                ],
+                dim=0,
+            ).reshape(key_value_dim, dim),
+            num_key_value_heads,
+            key_value_dim,
+            dim,
+        )
+        state_dict[f"model.layers.{layer_i}.self_attn.v_proj.weight"] = torch.cat(
+            [
+                loaded[i][f"layers.{layer_i}.attention.wv.weight"].view(num_local_key_value_heads, dims_per_head, dim)
+                for i in range(num_shards)
+            ],
+            dim=0,
+        ).reshape(key_value_dim, dim)
+
+        state_dict[f"model.layers.{layer_i}.self_attn.o_proj.weight"] = torch.cat(
+            [loaded[i][f"layers.{layer_i}.attention.wo.weight"] for i in range(num_shards)], dim=1
+        )
+        state_dict[f"model.layers.{layer_i}.mlp.gate_proj.weight"] = torch.cat(
+            [loaded[i][f"layers.{layer_i}.feed_forward.w1.weight"] for i in range(num_shards)], dim=0
+        )
+        state_dict[f"model.layers.{layer_i}.mlp.down_proj.weight"] = torch.cat(
+            [loaded[i][f"layers.{layer_i}.feed_forward.w2.weight"] for i in range(num_shards)], dim=1
+        )
+        state_dict[f"model.layers.{layer_i}.mlp.up_proj.weight"] = torch.cat(
+            [loaded[i][f"layers.{layer_i}.feed_forward.w3.weight"] for i in range(num_shards)], dim=0
+        )
+
+        state_dict[f"model.layers.{layer_i}.self_attn.rotary_emb.inv_freq"] = inv_freq
+        for k, v in state_dict.items():
+            index_dict["weight_map"][k] = filename
+            param_count += v.numel()
+        torch.save(state_dict, os.path.join(tmp_model_path, filename))
+
+    filename = f"pytorch_model-{n_layers + 1}-of-{n_layers + 1}.bin"
+    state_dict = {
+        "model.norm.weight": loaded[0]["norm.weight"],
+        "model.embed_tokens.weight": torch.cat([loaded[i]["tok_embeddings.weight"] for i in range(num_shards)], dim=1),
+        "lm_head.weight": torch.cat([loaded[i]["output.weight"] for i in range(num_shards)], dim=0),
+    }
+
+    for k, v in state_dict.items():
+        index_dict["weight_map"][k] = filename
+        param_count += v.numel()
+    torch.save(state_dict, os.path.join(tmp_model_path, filename))
+
+    # Write configs
+    index_dict["metadata"] = {"total_size": param_count * 2}
+    write_json(index_dict, os.path.join(tmp_model_path, "pytorch_model.bin.index.json"))
+    config = MistralConfig(
+        hidden_size=dim,
+        intermediate_size=params["hidden_dim"],
+        num_attention_heads=params["n_heads"],
+        num_hidden_layers=params["n_layers"],
+        rms_norm_eps=params["norm_eps"],
+        num_key_value_heads=num_key_value_heads,
+        vocab_size=vocab_size,
+        rope_theta=base,
+        max_position_embeddings=max_position_embeddings,
+        sliding_window=sliding_window,
+    )
+    config.save_pretrained(tmp_model_path)
+
+    # Make space so we can load the model properly now.
+    del state_dict
+    del loaded
+    gc.collect()
+
+    print("Loading the checkpoint in a Mistral model.")
+    model = MistralForCausalLM.from_pretrained(tmp_model_path, torch_dtype=torch.bfloat16, low_cpu_mem_usage=True)
+    # Avoid saving this as part of the config.
+    del model.config._name_or_path
+    model.config.torch_dtype = torch.float16
+    print("Saving in the Transformers format.")
+
+    model.save_pretrained(model_path, safe_serialization=safe_serialization)
+    shutil.rmtree(tmp_model_path)
+
+
+def write_tokenizer(tokenizer_path, input_tokenizer_path):
+    # Initialize the tokenizer based on the `spm` model
+    print(f"Saving a {tokenizer_class.__name__} to {tokenizer_path}.")
+    tokenizer = tokenizer_class(input_tokenizer_path)
+    tokenizer.save_pretrained(tokenizer_path)
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--input_dir",
+        help="Location of Mistral weights, which contains tokenizer.model and model folders",
+    )
+    parser.add_argument(
+        "--model_size",
+        choices=["22B", "tokenizer_only"],
+        help="'f' models correspond to the finetuned versions, and are specific to the Mistral2 official release. For more details on Mistral2, checkout the original repo: https://huggingface.co/meta-mistral",
+    )
+    parser.add_argument(
+        "--output_dir",
+        help="Location to write HF model and tokenizer",
+    )
+    parser.add_argument("--safe_serialization", type=bool, help="Whether or not to save using `safetensors`.")
+    parser.add_argument(
+        "--is_v3", action="store_true", help="Whether the checkpoints correspond to the 3rd version or not."
+    )
+    args = parser.parse_args()
+    spm_path = os.path.join(args.input_dir, "tokenizer.model")
+    if args.model_size != "tokenizer_only":
+        write_model(
+            model_path=args.output_dir,
+            input_base_path=args.input_dir,
+            model_size=args.model_size,
+            safe_serialization=args.safe_serialization,
+            tokenizer_path=spm_path,
+            is_v3=args.is_v3,
+        )
+    else:
+        write_tokenizer(args.output_dir, spm_path)
+
+
+if __name__ == "__main__":
+    main()

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.40.2"
+}

model.safetensors.index.json

@@ -0,0 +1,514 @@
+{
+    "metadata": {
+        "total_size": 44494565376
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00009-of-00009.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00009.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00002-of-00009.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00002-of-00009.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00003-of-00009.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00003-of-00009.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00003-of-00009.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00003-of-00009.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00003-of-00009.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00003-of-00009.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00004-of-00009.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00004-of-00009.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00009.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00004-of-00009.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00004-of-00009.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00004-of-00009.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00004-of-00009.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00005-of-00009.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00005-of-00009.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00005-of-00009.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00005-of-00009.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00005-of-00009.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00005-of-00009.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00009.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00005-of-00009.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00006-of-00009.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+        "model.layers.32.input_layernorm.weight": "model-00006-of-00009.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.32.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.33.input_layernorm.weight": "model-00006-of-00009.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.33.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.34.input_layernorm.weight": "model-00006-of-00009.safetensors",
+        "model.layers.34.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.34.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.35.input_layernorm.weight": "model-00006-of-00009.safetensors",
+        "model.layers.35.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.35.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.36.input_layernorm.weight": "model-00006-of-00009.safetensors",
+        "model.layers.36.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.36.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+        "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.37.input_layernorm.weight": "model-00007-of-00009.safetensors",
+        "model.layers.37.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.37.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+        "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+        "model.layers.38.input_layernorm.weight": "model-00007-of-00009.safetensors",
+        "model.layers.38.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.38.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+        "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.39.input_layernorm.weight": "model-00007-of-00009.safetensors",
+        "model.layers.39.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.39.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+        "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001-of-00009.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.40.input_layernorm.weight": "model-00007-of-00009.safetensors",
+        "model.layers.40.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.40.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.40.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.40.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+        "model.layers.40.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.40.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.40.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.40.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.41.input_layernorm.weight": "model-00007-of-00009.safetensors",
+        "model.layers.41.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.41.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.41.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.41.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+        "model.layers.41.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.41.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.41.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.41.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.42.input_layernorm.weight": "model-00007-of-00009.safetensors",
+        "model.layers.42.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.42.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.42.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.42.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+        "model.layers.42.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.42.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.43.input_layernorm.weight": "model-00008-of-00009.safetensors",
+        "model.layers.43.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.43.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.43.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.43.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+        "model.layers.43.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.43.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.43.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+        "model.layers.44.input_layernorm.weight": "model-00008-of-00009.safetensors",
+        "model.layers.44.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.44.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.44.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.44.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+        "model.layers.44.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.44.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.44.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.44.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.45.input_layernorm.weight": "model-00008-of-00009.safetensors",
+        "model.layers.45.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.45.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.45.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.45.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+        "model.layers.45.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.45.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.45.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.45.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.46.input_layernorm.weight": "model-00008-of-00009.safetensors",
+        "model.layers.46.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.46.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.46.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.46.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+        "model.layers.46.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.46.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.46.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.46.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.47.input_layernorm.weight": "model-00008-of-00009.safetensors",
+        "model.layers.47.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.47.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.47.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.47.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+        "model.layers.47.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.47.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.47.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.47.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.48.input_layernorm.weight": "model-00008-of-00009.safetensors",
+        "model.layers.48.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.48.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.48.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.48.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+        "model.layers.48.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.48.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.48.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.48.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.49.input_layernorm.weight": "model-00008-of-00009.safetensors",
+        "model.layers.49.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.49.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.49.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.49.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+        "model.layers.49.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.49.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.49.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.49.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00002-of-00009.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+        "model.layers.50.input_layernorm.weight": "model-00009-of-00009.safetensors",
+        "model.layers.50.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.50.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.50.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.50.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+        "model.layers.50.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.50.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.50.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.50.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+        "model.layers.51.input_layernorm.weight": "model-00009-of-00009.safetensors",
+        "model.layers.51.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.51.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.51.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.51.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+        "model.layers.51.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.51.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.51.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.51.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.52.input_layernorm.weight": "model-00009-of-00009.safetensors",
+        "model.layers.52.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.52.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.52.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.52.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+        "model.layers.52.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.52.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.52.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.52.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.53.input_layernorm.weight": "model-00009-of-00009.safetensors",
+        "model.layers.53.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.53.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.53.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.53.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+        "model.layers.53.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.53.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.53.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.53.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.54.input_layernorm.weight": "model-00009-of-00009.safetensors",
+        "model.layers.54.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.54.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.54.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.54.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+        "model.layers.54.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.54.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.54.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.54.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.55.input_layernorm.weight": "model-00009-of-00009.safetensors",
+        "model.layers.55.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.55.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.55.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.55.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+        "model.layers.55.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.55.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.55.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.55.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00002-of-00009.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00002-of-00009.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00002-of-00009.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00002-of-00009.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+        "model.norm.weight": "model-00009-of-00009.safetensors"
+    }
+}

output-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:506cf7775b692a8c9a131490aca1431338fc116f9d5a0361a80c2c1f520ade5d
+size 8589844128

output-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd599123777a3ec8c66d3e52146eedca025b7ff3a2ef29bbfda0014737a77509
+size 5616015176

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}