cb5e93f5f266d0b2e9ac1cadbc49a1da87adaffb087aa582466b6ca5db8c15c2

README.md

@@ -0,0 +1,232 @@
+---
+license: other
+license_name: mrl
+license_link: https://mistral.ai/licenses/MRL-0.1.md
+language:
+  - en
+  - fr
+  - de
+  - es
+  - it
+  - pt
+  - zh
+  - ja
+  - ru 
+  - ko
+
+extra_gated_description: If you want to learn more about how we process your personal data, please read our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
+---
+
+# Model Card for Mistral-Large-Instruct-2407
+
+Mistral-Large-Instruct-2407 is an advanced dense Large Language Model (LLM) of 123B parameters with state-of-the-art reasoning, knowledge and coding capabilities.
+
+For more details about this model please refer to our release [blog post](https://mistral.ai/news/mistral-large-2407/).
+
+## Key features
+- **Multi-lingual by design:** Dozens of languages supported, including English, French, German, Spanish, Italian, Chinese, Japanese, Korean, Portuguese, Dutch and Polish.
+- **Proficient in coding:** Trained on 80+ coding languages such as Python, Java, C, C++, Javacsript, and Bash. Also trained on more specific languages such as Swift and Fortran.
+- **Agentic-centric:** Best-in-class agentic capabilities with native function calling and JSON outputting.
+- **Advanced Reasoning:** State-of-the-art mathematical and reasoning capabilities.
+- **Mistral Research License:** Allows usage and modification for research and non-commercial usages.
+- **Large Context:** A large 128k context window.
+
+## Metrics
+
+### Base Pretrained Benchmarks
+
+| Benchmark | Score |
+| --- | --- |
+| MMLU | 84.0% |
+
+
+### Base Pretrained Multilingual Benchmarks (MMLU)
+| Benchmark | Score |
+| --- | --- |
+| French | 82.8% |
+| German | 81.6% |
+| Spanish | 82.7% |
+| Italian | 82.7% |
+| Dutch | 80.7% |
+| Portuguese | 81.6% |
+| Russian | 79.0% |
+| Korean | 60.1% |
+| Japanese | 78.8% |
+| Chinese | 74.8% |
+
+
+### Instruction Benchmarks
+
+| Benchmark | Score |
+| --- | --- |
+| MT Bench | 8.63 |
+| Wild Bench | 56.3 |
+| Arena Hard| 73.2 |
+
+### Code & Reasoning Benchmarks
+| Benchmark | Score |
+| --- | --- |
+| Human Eval | 92% |
+| Human Eval Plus| 87% |
+| MBPP Base| 80% |
+| MBPP Plus| 69% |
+
+### Math Benchmarks
+
+| Benchmark | Score |
+| --- | --- |
+| GSM8K | 93% |
+| Math Instruct (0-shot, no CoT) | 70% |
+| Math Instruct (0-shot, CoT)| 71.5% |
+
+## Usage
+
+The model can be used with two different frameworks
+
+- [`mistral_inference`](https://github.com/mistralai/mistral-inference): See [here](https://huggingface.co/mistralai/Mistral-Large-2407#mistral-inference)
+- [`transformers`](https://github.com/huggingface/transformers): See [here](#transformers)
+
+### Mistral Inference
+
+#### Install
+
+It is recommended to use `mistralai/Mistral-Large-2407` with [mistral-inference](https://github.com/mistralai/mistral-inference). For HF transformers code snippets, please keep scrolling.
+
+```
+pip install mistral_inference
+```
+
+#### Download
+
+```py
+from huggingface_hub import snapshot_download
+from pathlib import Path
+
+mistral_models_path = Path.home().joinpath('mistral_models', 'Large')
+mistral_models_path.mkdir(parents=True, exist_ok=True)
+
+snapshot_download(repo_id="mistralai/Mistral-Large-2407", allow_patterns=["params.json", "consolidated-*.safetensors", "tokenizer.model.v3"], local_dir=mistral_models_path)
+```
+
+#### Chat
+
+After installing `mistral_inference`, a `mistral-chat` CLI command should be available in your environment.
+Given the size of this model, you will need a node with several GPUs (more than 300GB cumulated vRAM).
+If you have 8 GPUs on your machine, you can chat with the model using
+
+```
+torchrun --nproc-per-node 8 --no-python mistral-chat $HOME/mistral_models/Large --instruct --max_tokens 256 --temperature 0.7
+```
+
+*E.g.* Try out something like:
+```
+How expensive would it be to ask a window cleaner to clean all windows in Paris. Make a reasonable guess in US Dollar.
+```
+
+#### Instruct following
+
+```py
+from mistral_inference.transformer import Transformer
+from mistral_inference.generate import generate
+
+from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
+from mistral_common.protocol.instruct.messages import UserMessage
+from mistral_common.protocol.instruct.request import ChatCompletionRequest
+
+tokenizer = MistralTokenizer.from_file(f"{mistral_models_path}/tokenizer.model.v3")
+model = Transformer.from_folder(mistral_models_path)
+
+prompt = "How expensive would it be to ask a window cleaner to clean all windows in Paris. Make a reasonable guess in US Dollar."
+
+completion_request = ChatCompletionRequest(messages=[UserMessage(content=prompt)])
+
+tokens = tokenizer.encode_chat_completion(completion_request).tokens
+
+out_tokens, _ = generate([tokens], model, max_tokens=64, temperature=0.7, eos_id=tokenizer.instruct_tokenizer.tokenizer.eos_id)
+result = tokenizer.decode(out_tokens[0])
+
+print(result)
+```
+
+#### Function calling
+
+```py
+from mistral_common.protocol.instruct.tool_calls import Function, Tool
+from mistral_inference.transformer import Transformer
+from mistral_inference.generate import generate
+
+from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
+from mistral_common.protocol.instruct.messages import UserMessage
+from mistral_common.protocol.instruct.request import ChatCompletionRequest
+
+
+tokenizer = MistralTokenizer.from_file(f"{mistral_models_path}/tokenizer.model.v3")
+model = Transformer.from_folder(mistral_models_path)
+
+completion_request = ChatCompletionRequest(
+    tools=[
+        Tool(
+            function=Function(
+                name="get_current_weather",
+                description="Get the current weather",
+                parameters={
+                    "type": "object",
+                    "properties": {
+                        "location": {
+                            "type": "string",
+                            "description": "The city and state, e.g. San Francisco, CA",
+                        },
+                        "format": {
+                            "type": "string",
+                            "enum": ["celsius", "fahrenheit"],
+                            "description": "The temperature unit to use. Infer this from the users location.",
+                        },
+                    },
+                    "required": ["location", "format"],
+                },
+            )
+        )
+    ],
+    messages=[
+        UserMessage(content="What's the weather like today in Paris?"),
+        ],
+)
+
+tokens = tokenizer.encode_chat_completion(completion_request).tokens
+
+out_tokens, _ = generate([tokens], model, max_tokens=256, temperature=0.7, eos_id=tokenizer.instruct_tokenizer.tokenizer.eos_id)
+result = tokenizer.decode(out_tokens[0])
+
+print(result)
+```
+
+### Transformers
+
+> [!IMPORTANT]
+> NOTE: Until a new release has been made, you need to install transformers from source:
+> ```sh
+> pip install git+https://github.com/huggingface/transformers.git
+> ```
+
+If you want to use Hugging Face `transformers` to generate text, you can do something like this.
+
+```py
+from transformers import pipeline
+
+messages = [
+    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
+    {"role": "user", "content": "Who are you?"},
+]
+chatbot = pipeline("text-generation", model="mistralai/Mistral-Large-2407")
+chatbot(messages)
+```
+
+## Limitations
+
+The Mistral Large model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance. 
+It does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to
+make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.
+
+## The Mistral AI Team
+
+Albert Jiang, Alexandre Sablayrolles, Alexis Tacnet, Alok Kothari, Antoine Roux, Arthur Mensch, Audrey Herblin-Stoop, Augustin Garreau, Austin Birky, Bam4d, Baptiste Bout, Baudouin de Monicault, Blanche Savary, Carole Rambaud, Caroline Feldman, Devendra Singh Chaplot, Diego de las Casas, Diogo Costa, Eleonore Arcelin, Emma Bou Hanna, Etienne Metzger, Gaspard Blanchet, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Harizo Rajaona, Henri Roussez, Hichem Sattouf, Ian Mack, Jean-Malo Delignon, Jessica Chudnovsky, Justus Murke, Kartik Khandelwal, Lawrence Stewart, Louis Martin, Louis Ternon, Lucile Saulnier, Lélio Renard Lavaud, Margaret Jennings, Marie Pellat, Marie Torelli, Marie-Anne Lachaux, Marjorie Janiewicz, Mickaël Seznec, Nicolas Schuhl, Niklas Muhs, Olivier de Garrigues, Patrick von Platen, Paul Jacob, Pauline Buche, Pavan Kumar Reddy, Perry Savas, Pierre Stock, Romain Sauvestre, Sagar Vaze, Sandeep Subramanian, Saurabh Garg, Sophia Yang, Szymon Antoniak, Teven Le Scao, Thibault Schueller, Thibaut Lavril, Thomas Wang, Théophile Gervet, Timothée Lacroix, Valera Nemychnikova, Wendy Shang, William El Sayed, William Marshall

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": 12288,
+    "initializer_range": 0.02,
+    "intermediate_size": 28672,
+    "max_position_embeddings": 32768,
+    "model_type": "mistral",
+    "num_attention_heads": 96,
+    "num_hidden_layers": 88,
+    "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": "4.42.3",
+    "use_cache": true,
+    "vocab_size": 32768,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.1.8",
+        "bits": 5.5,
+        "head_bits": 8,
+        "calibration": {
+            "rows": 115,
+            "length": 8192,
+            "dataset": "(default)"
+        }
+    }
+}

consolidated.safetensors.index.json

@@ -0,0 +1,802 @@
+{
+  "metadata": {
+    "total_size": 245220139008
+  },
+  "weight_map": {
+    "layers.0.attention.wk.weight": "consolidated-00001-of-00051.safetensors",
+    "layers.0.attention.wo.weight": "consolidated-00001-of-00051.safetensors",
+    "layers.0.attention.wq.weight": "consolidated-00001-of-00051.safetensors",
+    "layers.0.attention.wv.weight": "consolidated-00001-of-00051.safetensors",
+    "layers.0.attention_norm.weight": "consolidated-00001-of-00051.safetensors",
+    "layers.0.feed_forward.w1.weight": "consolidated-00001-of-00051.safetensors",
+    "layers.0.feed_forward.w2.weight": "consolidated-00001-of-00051.safetensors",
+    "layers.0.feed_forward.w3.weight": "consolidated-00001-of-00051.safetensors",
+    "layers.0.ffn_norm.weight": "consolidated-00001-of-00051.safetensors",
+    "layers.1.attention.wk.weight": "consolidated-00001-of-00051.safetensors",
+    "layers.1.attention.wo.weight": "consolidated-00001-of-00051.safetensors",
+    "layers.1.attention.wq.weight": "consolidated-00001-of-00051.safetensors",
+    "layers.1.attention.wv.weight": "consolidated-00001-of-00051.safetensors",
+    "layers.1.attention_norm.weight": "consolidated-00001-of-00051.safetensors",
+    "layers.1.feed_forward.w1.weight": "consolidated-00001-of-00051.safetensors",
+    "layers.1.feed_forward.w2.weight": "consolidated-00001-of-00051.safetensors",
+    "layers.1.feed_forward.w3.weight": "consolidated-00002-of-00051.safetensors",
+    "layers.1.ffn_norm.weight": "consolidated-00002-of-00051.safetensors",
+    "layers.10.attention.wk.weight": "consolidated-00002-of-00051.safetensors",
+    "layers.10.attention.wo.weight": "consolidated-00002-of-00051.safetensors",
+    "layers.10.attention.wq.weight": "consolidated-00002-of-00051.safetensors",
+    "layers.10.attention.wv.weight": "consolidated-00002-of-00051.safetensors",
+    "layers.10.attention_norm.weight": "consolidated-00002-of-00051.safetensors",
+    "layers.10.feed_forward.w1.weight": "consolidated-00002-of-00051.safetensors",
+    "layers.10.feed_forward.w2.weight": "consolidated-00002-of-00051.safetensors",
+    "layers.10.feed_forward.w3.weight": "consolidated-00002-of-00051.safetensors",
+    "layers.10.ffn_norm.weight": "consolidated-00002-of-00051.safetensors",
+    "layers.11.attention.wk.weight": "consolidated-00002-of-00051.safetensors",
+    "layers.11.attention.wo.weight": "consolidated-00002-of-00051.safetensors",
+    "layers.11.attention.wq.weight": "consolidated-00002-of-00051.safetensors",
+    "layers.11.attention.wv.weight": "consolidated-00002-of-00051.safetensors",
+    "layers.11.attention_norm.weight": "consolidated-00002-of-00051.safetensors",
+    "layers.11.feed_forward.w1.weight": "consolidated-00002-of-00051.safetensors",
+    "layers.11.feed_forward.w2.weight": "consolidated-00003-of-00051.safetensors",
+    "layers.11.feed_forward.w3.weight": "consolidated-00003-of-00051.safetensors",
+    "layers.11.ffn_norm.weight": "consolidated-00003-of-00051.safetensors",
+    "layers.12.attention.wk.weight": "consolidated-00003-of-00051.safetensors",
+    "layers.12.attention.wo.weight": "consolidated-00003-of-00051.safetensors",
+    "layers.12.attention.wq.weight": "consolidated-00003-of-00051.safetensors",
+    "layers.12.attention.wv.weight": "consolidated-00003-of-00051.safetensors",
+    "layers.12.attention_norm.weight": "consolidated-00003-of-00051.safetensors",
+    "layers.12.feed_forward.w1.weight": "consolidated-00003-of-00051.safetensors",
+    "layers.12.feed_forward.w2.weight": "consolidated-00003-of-00051.safetensors",
+    "layers.12.feed_forward.w3.weight": "consolidated-00003-of-00051.safetensors",
+    "layers.12.ffn_norm.weight": "consolidated-00003-of-00051.safetensors",
+    "layers.13.attention.wk.weight": "consolidated-00003-of-00051.safetensors",
+    "layers.13.attention.wo.weight": "consolidated-00003-of-00051.safetensors",
+    "layers.13.attention.wq.weight": "consolidated-00003-of-00051.safetensors",
+    "layers.13.attention.wv.weight": "consolidated-00003-of-00051.safetensors",
+    "layers.13.attention_norm.weight": "consolidated-00003-of-00051.safetensors",
+    "layers.13.feed_forward.w1.weight": "consolidated-00004-of-00051.safetensors",
+    "layers.13.feed_forward.w2.weight": "consolidated-00004-of-00051.safetensors",
+    "layers.13.feed_forward.w3.weight": "consolidated-00004-of-00051.safetensors",
+    "layers.13.ffn_norm.weight": "consolidated-00004-of-00051.safetensors",
+    "layers.14.attention.wk.weight": "consolidated-00004-of-00051.safetensors",
+    "layers.14.attention.wo.weight": "consolidated-00004-of-00051.safetensors",
+    "layers.14.attention.wq.weight": "consolidated-00004-of-00051.safetensors",
+    "layers.14.attention.wv.weight": "consolidated-00004-of-00051.safetensors",
+    "layers.14.attention_norm.weight": "consolidated-00004-of-00051.safetensors",
+    "layers.14.feed_forward.w1.weight": "consolidated-00004-of-00051.safetensors",
+    "layers.14.feed_forward.w2.weight": "consolidated-00004-of-00051.safetensors",
+    "layers.14.feed_forward.w3.weight": "consolidated-00004-of-00051.safetensors",
+    "layers.14.ffn_norm.weight": "consolidated-00004-of-00051.safetensors",
+    "layers.15.attention.wk.weight": "consolidated-00004-of-00051.safetensors",
+    "layers.15.attention.wo.weight": "consolidated-00005-of-00051.safetensors",
+    "layers.15.attention.wq.weight": "consolidated-00005-of-00051.safetensors",
+    "layers.15.attention.wv.weight": "consolidated-00005-of-00051.safetensors",
+    "layers.15.attention_norm.weight": "consolidated-00005-of-00051.safetensors",
+    "layers.15.feed_forward.w1.weight": "consolidated-00005-of-00051.safetensors",
+    "layers.15.feed_forward.w2.weight": "consolidated-00005-of-00051.safetensors",
+    "layers.15.feed_forward.w3.weight": "consolidated-00005-of-00051.safetensors",
+    "layers.15.ffn_norm.weight": "consolidated-00005-of-00051.safetensors",
+    "layers.16.attention.wk.weight": "consolidated-00005-of-00051.safetensors",
+    "layers.16.attention.wo.weight": "consolidated-00005-of-00051.safetensors",
+    "layers.16.attention.wq.weight": "consolidated-00005-of-00051.safetensors",
+    "layers.16.attention.wv.weight": "consolidated-00005-of-00051.safetensors",
+    "layers.16.attention_norm.weight": "consolidated-00005-of-00051.safetensors",
+    "layers.16.feed_forward.w1.weight": "consolidated-00005-of-00051.safetensors",
+    "layers.16.feed_forward.w2.weight": "consolidated-00005-of-00051.safetensors",
+    "layers.16.feed_forward.w3.weight": "consolidated-00006-of-00051.safetensors",
+    "layers.16.ffn_norm.weight": "consolidated-00006-of-00051.safetensors",
+    "layers.17.attention.wk.weight": "consolidated-00006-of-00051.safetensors",
+    "layers.17.attention.wo.weight": "consolidated-00006-of-00051.safetensors",
+    "layers.17.attention.wq.weight": "consolidated-00006-of-00051.safetensors",
+    "layers.17.attention.wv.weight": "consolidated-00006-of-00051.safetensors",
+    "layers.17.attention_norm.weight": "consolidated-00006-of-00051.safetensors",
+    "layers.17.feed_forward.w1.weight": "consolidated-00006-of-00051.safetensors",
+    "layers.17.feed_forward.w2.weight": "consolidated-00006-of-00051.safetensors",
+    "layers.17.feed_forward.w3.weight": "consolidated-00006-of-00051.safetensors",
+    "layers.17.ffn_norm.weight": "consolidated-00006-of-00051.safetensors",
+    "layers.18.attention.wk.weight": "consolidated-00006-of-00051.safetensors",
+    "layers.18.attention.wo.weight": "consolidated-00006-of-00051.safetensors",
+    "layers.18.attention.wq.weight": "consolidated-00006-of-00051.safetensors",
+    "layers.18.attention.wv.weight": "consolidated-00006-of-00051.safetensors",
+    "layers.18.attention_norm.weight": "consolidated-00006-of-00051.safetensors",
+    "layers.18.feed_forward.w1.weight": "consolidated-00006-of-00051.safetensors",
+    "layers.18.feed_forward.w2.weight": "consolidated-00007-of-00051.safetensors",
+    "layers.18.feed_forward.w3.weight": "consolidated-00007-of-00051.safetensors",
+    "layers.18.ffn_norm.weight": "consolidated-00007-of-00051.safetensors",
+    "layers.19.attention.wk.weight": "consolidated-00007-of-00051.safetensors",
+    "layers.19.attention.wo.weight": "consolidated-00007-of-00051.safetensors",
+    "layers.19.attention.wq.weight": "consolidated-00007-of-00051.safetensors",
+    "layers.19.attention.wv.weight": "consolidated-00007-of-00051.safetensors",
+    "layers.19.attention_norm.weight": "consolidated-00007-of-00051.safetensors",
+    "layers.19.feed_forward.w1.weight": "consolidated-00007-of-00051.safetensors",
+    "layers.19.feed_forward.w2.weight": "consolidated-00007-of-00051.safetensors",
+    "layers.19.feed_forward.w3.weight": "consolidated-00007-of-00051.safetensors",
+    "layers.19.ffn_norm.weight": "consolidated-00007-of-00051.safetensors",
+    "layers.2.attention.wk.weight": "consolidated-00007-of-00051.safetensors",
+    "layers.2.attention.wo.weight": "consolidated-00007-of-00051.safetensors",
+    "layers.2.attention.wq.weight": "consolidated-00007-of-00051.safetensors",
+    "layers.2.attention.wv.weight": "consolidated-00007-of-00051.safetensors",
+    "layers.2.attention_norm.weight": "consolidated-00007-of-00051.safetensors",
+    "layers.2.feed_forward.w1.weight": "consolidated-00008-of-00051.safetensors",
+    "layers.2.feed_forward.w2.weight": "consolidated-00008-of-00051.safetensors",
+    "layers.2.feed_forward.w3.weight": "consolidated-00008-of-00051.safetensors",
+    "layers.2.ffn_norm.weight": "consolidated-00008-of-00051.safetensors",
+    "layers.20.attention.wk.weight": "consolidated-00008-of-00051.safetensors",
+    "layers.20.attention.wo.weight": "consolidated-00008-of-00051.safetensors",
+    "layers.20.attention.wq.weight": "consolidated-00008-of-00051.safetensors",
+    "layers.20.attention.wv.weight": "consolidated-00008-of-00051.safetensors",
+    "layers.20.attention_norm.weight": "consolidated-00008-of-00051.safetensors",
+    "layers.20.feed_forward.w1.weight": "consolidated-00008-of-00051.safetensors",
+    "layers.20.feed_forward.w2.weight": "consolidated-00008-of-00051.safetensors",
+    "layers.20.feed_forward.w3.weight": "consolidated-00008-of-00051.safetensors",
+    "layers.20.ffn_norm.weight": "consolidated-00008-of-00051.safetensors",
+    "layers.21.attention.wk.weight": "consolidated-00008-of-00051.safetensors",
+    "layers.21.attention.wo.weight": "consolidated-00009-of-00051.safetensors",
+    "layers.21.attention.wq.weight": "consolidated-00009-of-00051.safetensors",
+    "layers.21.attention.wv.weight": "consolidated-00009-of-00051.safetensors",
+    "layers.21.attention_norm.weight": "consolidated-00009-of-00051.safetensors",
+    "layers.21.feed_forward.w1.weight": "consolidated-00009-of-00051.safetensors",
+    "layers.21.feed_forward.w2.weight": "consolidated-00009-of-00051.safetensors",
+    "layers.21.feed_forward.w3.weight": "consolidated-00009-of-00051.safetensors",
+    "layers.21.ffn_norm.weight": "consolidated-00009-of-00051.safetensors",
+    "layers.22.attention.wk.weight": "consolidated-00009-of-00051.safetensors",
+    "layers.22.attention.wo.weight": "consolidated-00009-of-00051.safetensors",
+    "layers.22.attention.wq.weight": "consolidated-00009-of-00051.safetensors",
+    "layers.22.attention.wv.weight": "consolidated-00009-of-00051.safetensors",
+    "layers.22.attention_norm.weight": "consolidated-00009-of-00051.safetensors",
+    "layers.22.feed_forward.w1.weight": "consolidated-00009-of-00051.safetensors",
+    "layers.22.feed_forward.w2.weight": "consolidated-00009-of-00051.safetensors",
+    "layers.22.feed_forward.w3.weight": "consolidated-00010-of-00051.safetensors",
+    "layers.22.ffn_norm.weight": "consolidated-00010-of-00051.safetensors",
+    "layers.23.attention.wk.weight": "consolidated-00010-of-00051.safetensors",
+    "layers.23.attention.wo.weight": "consolidated-00010-of-00051.safetensors",
+    "layers.23.attention.wq.weight": "consolidated-00010-of-00051.safetensors",
+    "layers.23.attention.wv.weight": "consolidated-00010-of-00051.safetensors",
+    "layers.23.attention_norm.weight": "consolidated-00010-of-00051.safetensors",
+    "layers.23.feed_forward.w1.weight": "consolidated-00010-of-00051.safetensors",
+    "layers.23.feed_forward.w2.weight": "consolidated-00010-of-00051.safetensors",
+    "layers.23.feed_forward.w3.weight": "consolidated-00010-of-00051.safetensors",
+    "layers.23.ffn_norm.weight": "consolidated-00010-of-00051.safetensors",
+    "layers.24.attention.wk.weight": "consolidated-00010-of-00051.safetensors",
+    "layers.24.attention.wo.weight": "consolidated-00010-of-00051.safetensors",
+    "layers.24.attention.wq.weight": "consolidated-00010-of-00051.safetensors",
+    "layers.24.attention.wv.weight": "consolidated-00010-of-00051.safetensors",
+    "layers.24.attention_norm.weight": "consolidated-00010-of-00051.safetensors",
+    "layers.24.feed_forward.w1.weight": "consolidated-00010-of-00051.safetensors",
+    "layers.24.feed_forward.w2.weight": "consolidated-00011-of-00051.safetensors",
+    "layers.24.feed_forward.w3.weight": "consolidated-00011-of-00051.safetensors",
+    "layers.24.ffn_norm.weight": "consolidated-00011-of-00051.safetensors",
+    "layers.25.attention.wk.weight": "consolidated-00011-of-00051.safetensors",
+    "layers.25.attention.wo.weight": "consolidated-00011-of-00051.safetensors",
+    "layers.25.attention.wq.weight": "consolidated-00011-of-00051.safetensors",
+    "layers.25.attention.wv.weight": "consolidated-00011-of-00051.safetensors",
+    "layers.25.attention_norm.weight": "consolidated-00011-of-00051.safetensors",
+    "layers.25.feed_forward.w1.weight": "consolidated-00011-of-00051.safetensors",
+    "layers.25.feed_forward.w2.weight": "consolidated-00011-of-00051.safetensors",
+    "layers.25.feed_forward.w3.weight": "consolidated-00011-of-00051.safetensors",
+    "layers.25.ffn_norm.weight": "consolidated-00011-of-00051.safetensors",
+    "layers.26.attention.wk.weight": "consolidated-00011-of-00051.safetensors",
+    "layers.26.attention.wo.weight": "consolidated-00011-of-00051.safetensors",
+    "layers.26.attention.wq.weight": "consolidated-00011-of-00051.safetensors",
+    "layers.26.attention.wv.weight": "consolidated-00011-of-00051.safetensors",
+    "layers.26.attention_norm.weight": "consolidated-00011-of-00051.safetensors",
+    "layers.26.feed_forward.w1.weight": "consolidated-00012-of-00051.safetensors",
+    "layers.26.feed_forward.w2.weight": "consolidated-00012-of-00051.safetensors",
+    "layers.26.feed_forward.w3.weight": "consolidated-00012-of-00051.safetensors",
+    "layers.26.ffn_norm.weight": "consolidated-00012-of-00051.safetensors",
+    "layers.27.attention.wk.weight": "consolidated-00012-of-00051.safetensors",
+    "layers.27.attention.wo.weight": "consolidated-00012-of-00051.safetensors",
+    "layers.27.attention.wq.weight": "consolidated-00012-of-00051.safetensors",
+    "layers.27.attention.wv.weight": "consolidated-00012-of-00051.safetensors",
+    "layers.27.attention_norm.weight": "consolidated-00012-of-00051.safetensors",
+    "layers.27.feed_forward.w1.weight": "consolidated-00012-of-00051.safetensors",
+    "layers.27.feed_forward.w2.weight": "consolidated-00012-of-00051.safetensors",
+    "layers.27.feed_forward.w3.weight": "consolidated-00012-of-00051.safetensors",
+    "layers.27.ffn_norm.weight": "consolidated-00012-of-00051.safetensors",
+    "layers.28.attention.wk.weight": "consolidated-00012-of-00051.safetensors",
+    "layers.28.attention.wo.weight": "consolidated-00013-of-00051.safetensors",
+    "layers.28.attention.wq.weight": "consolidated-00013-of-00051.safetensors",
+    "layers.28.attention.wv.weight": "consolidated-00013-of-00051.safetensors",
+    "layers.28.attention_norm.weight": "consolidated-00013-of-00051.safetensors",
+    "layers.28.feed_forward.w1.weight": "consolidated-00013-of-00051.safetensors",
+    "layers.28.feed_forward.w2.weight": "consolidated-00013-of-00051.safetensors",
+    "layers.28.feed_forward.w3.weight": "consolidated-00013-of-00051.safetensors",
+    "layers.28.ffn_norm.weight": "consolidated-00013-of-00051.safetensors",
+    "layers.29.attention.wk.weight": "consolidated-00013-of-00051.safetensors",
+    "layers.29.attention.wo.weight": "consolidated-00013-of-00051.safetensors",
+    "layers.29.attention.wq.weight": "consolidated-00013-of-00051.safetensors",
+    "layers.29.attention.wv.weight": "consolidated-00013-of-00051.safetensors",
+    "layers.29.attention_norm.weight": "consolidated-00013-of-00051.safetensors",
+    "layers.29.feed_forward.w1.weight": "consolidated-00013-of-00051.safetensors",
+    "layers.29.feed_forward.w2.weight": "consolidated-00013-of-00051.safetensors",
+    "layers.29.feed_forward.w3.weight": "consolidated-00014-of-00051.safetensors",
+    "layers.29.ffn_norm.weight": "consolidated-00014-of-00051.safetensors",
+    "layers.3.attention.wk.weight": "consolidated-00014-of-00051.safetensors",
+    "layers.3.attention.wo.weight": "consolidated-00014-of-00051.safetensors",
+    "layers.3.attention.wq.weight": "consolidated-00014-of-00051.safetensors",
+    "layers.3.attention.wv.weight": "consolidated-00014-of-00051.safetensors",
+    "layers.3.attention_norm.weight": "consolidated-00014-of-00051.safetensors",
+    "layers.3.feed_forward.w1.weight": "consolidated-00014-of-00051.safetensors",
+    "layers.3.feed_forward.w2.weight": "consolidated-00014-of-00051.safetensors",
+    "layers.3.feed_forward.w3.weight": "consolidated-00014-of-00051.safetensors",
+    "layers.3.ffn_norm.weight": "consolidated-00014-of-00051.safetensors",
+    "layers.30.attention.wk.weight": "consolidated-00014-of-00051.safetensors",
+    "layers.30.attention.wo.weight": "consolidated-00014-of-00051.safetensors",
+    "layers.30.attention.wq.weight": "consolidated-00014-of-00051.safetensors",
+    "layers.30.attention.wv.weight": "consolidated-00014-of-00051.safetensors",
+    "layers.30.attention_norm.weight": "consolidated-00014-of-00051.safetensors",
+    "layers.30.feed_forward.w1.weight": "consolidated-00014-of-00051.safetensors",
+    "layers.30.feed_forward.w2.weight": "consolidated-00015-of-00051.safetensors",
+    "layers.30.feed_forward.w3.weight": "consolidated-00015-of-00051.safetensors",
+    "layers.30.ffn_norm.weight": "consolidated-00015-of-00051.safetensors",
+    "layers.31.attention.wk.weight": "consolidated-00015-of-00051.safetensors",
+    "layers.31.attention.wo.weight": "consolidated-00015-of-00051.safetensors",
+    "layers.31.attention.wq.weight": "consolidated-00015-of-00051.safetensors",
+    "layers.31.attention.wv.weight": "consolidated-00015-of-00051.safetensors",
+    "layers.31.attention_norm.weight": "consolidated-00015-of-00051.safetensors",
+    "layers.31.feed_forward.w1.weight": "consolidated-00015-of-00051.safetensors",
+    "layers.31.feed_forward.w2.weight": "consolidated-00015-of-00051.safetensors",
+    "layers.31.feed_forward.w3.weight": "consolidated-00015-of-00051.safetensors",
+    "layers.31.ffn_norm.weight": "consolidated-00015-of-00051.safetensors",
+    "layers.32.attention.wk.weight": "consolidated-00015-of-00051.safetensors",
+    "layers.32.attention.wo.weight": "consolidated-00015-of-00051.safetensors",
+    "layers.32.attention.wq.weight": "consolidated-00015-of-00051.safetensors",
+    "layers.32.attention.wv.weight": "consolidated-00015-of-00051.safetensors",
+    "layers.32.attention_norm.weight": "consolidated-00015-of-00051.safetensors",
+    "layers.32.feed_forward.w1.weight": "consolidated-00016-of-00051.safetensors",
+    "layers.32.feed_forward.w2.weight": "consolidated-00016-of-00051.safetensors",
+    "layers.32.feed_forward.w3.weight": "consolidated-00016-of-00051.safetensors",
+    "layers.32.ffn_norm.weight": "consolidated-00016-of-00051.safetensors",
+    "layers.33.attention.wk.weight": "consolidated-00016-of-00051.safetensors",
+    "layers.33.attention.wo.weight": "consolidated-00016-of-00051.safetensors",
+    "layers.33.attention.wq.weight": "consolidated-00016-of-00051.safetensors",
+    "layers.33.attention.wv.weight": "consolidated-00016-of-00051.safetensors",
+    "layers.33.attention_norm.weight": "consolidated-00016-of-00051.safetensors",
+    "layers.33.feed_forward.w1.weight": "consolidated-00016-of-00051.safetensors",
+    "layers.33.feed_forward.w2.weight": "consolidated-00016-of-00051.safetensors",
+    "layers.33.feed_forward.w3.weight": "consolidated-00016-of-00051.safetensors",
+    "layers.33.ffn_norm.weight": "consolidated-00016-of-00051.safetensors",
+    "layers.34.attention.wk.weight": "consolidated-00016-of-00051.safetensors",
+    "layers.34.attention.wo.weight": "consolidated-00017-of-00051.safetensors",
+    "layers.34.attention.wq.weight": "consolidated-00017-of-00051.safetensors",
+    "layers.34.attention.wv.weight": "consolidated-00017-of-00051.safetensors",
+    "layers.34.attention_norm.weight": "consolidated-00017-of-00051.safetensors",
+    "layers.34.feed_forward.w1.weight": "consolidated-00017-of-00051.safetensors",
+    "layers.34.feed_forward.w2.weight": "consolidated-00017-of-00051.safetensors",
+    "layers.34.feed_forward.w3.weight": "consolidated-00017-of-00051.safetensors",
+    "layers.34.ffn_norm.weight": "consolidated-00017-of-00051.safetensors",
+    "layers.35.attention.wk.weight": "consolidated-00017-of-00051.safetensors",
+    "layers.35.attention.wo.weight": "consolidated-00017-of-00051.safetensors",
+    "layers.35.attention.wq.weight": "consolidated-00017-of-00051.safetensors",
+    "layers.35.attention.wv.weight": "consolidated-00017-of-00051.safetensors",
+    "layers.35.attention_norm.weight": "consolidated-00017-of-00051.safetensors",
+    "layers.35.feed_forward.w1.weight": "consolidated-00017-of-00051.safetensors",
+    "layers.35.feed_forward.w2.weight": "consolidated-00017-of-00051.safetensors",
+    "layers.35.feed_forward.w3.weight": "consolidated-00018-of-00051.safetensors",
+    "layers.35.ffn_norm.weight": "consolidated-00018-of-00051.safetensors",
+    "layers.36.attention.wk.weight": "consolidated-00018-of-00051.safetensors",
+    "layers.36.attention.wo.weight": "consolidated-00018-of-00051.safetensors",
+    "layers.36.attention.wq.weight": "consolidated-00018-of-00051.safetensors",
+    "layers.36.attention.wv.weight": "consolidated-00018-of-00051.safetensors",
+    "layers.36.attention_norm.weight": "consolidated-00018-of-00051.safetensors",
+    "layers.36.feed_forward.w1.weight": "consolidated-00018-of-00051.safetensors",
+    "layers.36.feed_forward.w2.weight": "consolidated-00018-of-00051.safetensors",
+    "layers.36.feed_forward.w3.weight": "consolidated-00018-of-00051.safetensors",
+    "layers.36.ffn_norm.weight": "consolidated-00018-of-00051.safetensors",
+    "layers.37.attention.wk.weight": "consolidated-00018-of-00051.safetensors",
+    "layers.37.attention.wo.weight": "consolidated-00018-of-00051.safetensors",
+    "layers.37.attention.wq.weight": "consolidated-00018-of-00051.safetensors",
+    "layers.37.attention.wv.weight": "consolidated-00018-of-00051.safetensors",
+    "layers.37.attention_norm.weight": "consolidated-00018-of-00051.safetensors",
+    "layers.37.feed_forward.w1.weight": "consolidated-00018-of-00051.safetensors",
+    "layers.37.feed_forward.w2.weight": "consolidated-00019-of-00051.safetensors",
+    "layers.37.feed_forward.w3.weight": "consolidated-00019-of-00051.safetensors",
+    "layers.37.ffn_norm.weight": "consolidated-00019-of-00051.safetensors",
+    "layers.38.attention.wk.weight": "consolidated-00019-of-00051.safetensors",
+    "layers.38.attention.wo.weight": "consolidated-00019-of-00051.safetensors",
+    "layers.38.attention.wq.weight": "consolidated-00019-of-00051.safetensors",
+    "layers.38.attention.wv.weight": "consolidated-00019-of-00051.safetensors",
+    "layers.38.attention_norm.weight": "consolidated-00019-of-00051.safetensors",
+    "layers.38.feed_forward.w1.weight": "consolidated-00019-of-00051.safetensors",
+    "layers.38.feed_forward.w2.weight": "consolidated-00019-of-00051.safetensors",
+    "layers.38.feed_forward.w3.weight": "consolidated-00019-of-00051.safetensors",
+    "layers.38.ffn_norm.weight": "consolidated-00019-of-00051.safetensors",
+    "layers.39.attention.wk.weight": "consolidated-00019-of-00051.safetensors",
+    "layers.39.attention.wo.weight": "consolidated-00019-of-00051.safetensors",
+    "layers.39.attention.wq.weight": "consolidated-00019-of-00051.safetensors",
+    "layers.39.attention.wv.weight": "consolidated-00019-of-00051.safetensors",
+    "layers.39.attention_norm.weight": "consolidated-00019-of-00051.safetensors",
+    "layers.39.feed_forward.w1.weight": "consolidated-00020-of-00051.safetensors",
+    "layers.39.feed_forward.w2.weight": "consolidated-00020-of-00051.safetensors",
+    "layers.39.feed_forward.w3.weight": "consolidated-00020-of-00051.safetensors",
+    "layers.39.ffn_norm.weight": "consolidated-00020-of-00051.safetensors",
+    "layers.4.attention.wk.weight": "consolidated-00020-of-00051.safetensors",
+    "layers.4.attention.wo.weight": "consolidated-00020-of-00051.safetensors",
+    "layers.4.attention.wq.weight": "consolidated-00020-of-00051.safetensors",
+    "layers.4.attention.wv.weight": "consolidated-00020-of-00051.safetensors",
+    "layers.4.attention_norm.weight": "consolidated-00020-of-00051.safetensors",
+    "layers.4.feed_forward.w1.weight": "consolidated-00020-of-00051.safetensors",
+    "layers.4.feed_forward.w2.weight": "consolidated-00020-of-00051.safetensors",
+    "layers.4.feed_forward.w3.weight": "consolidated-00020-of-00051.safetensors",
+    "layers.4.ffn_norm.weight": "consolidated-00020-of-00051.safetensors",
+    "layers.40.attention.wk.weight": "consolidated-00020-of-00051.safetensors",
+    "layers.40.attention.wo.weight": "consolidated-00021-of-00051.safetensors",
+    "layers.40.attention.wq.weight": "consolidated-00021-of-00051.safetensors",
+    "layers.40.attention.wv.weight": "consolidated-00021-of-00051.safetensors",
+    "layers.40.attention_norm.weight": "consolidated-00021-of-00051.safetensors",
+    "layers.40.feed_forward.w1.weight": "consolidated-00021-of-00051.safetensors",
+    "layers.40.feed_forward.w2.weight": "consolidated-00021-of-00051.safetensors",
+    "layers.40.feed_forward.w3.weight": "consolidated-00021-of-00051.safetensors",
+    "layers.40.ffn_norm.weight": "consolidated-00021-of-00051.safetensors",
+    "layers.41.attention.wk.weight": "consolidated-00021-of-00051.safetensors",
+    "layers.41.attention.wo.weight": "consolidated-00021-of-00051.safetensors",
+    "layers.41.attention.wq.weight": "consolidated-00021-of-00051.safetensors",
+    "layers.41.attention.wv.weight": "consolidated-00021-of-00051.safetensors",
+    "layers.41.attention_norm.weight": "consolidated-00021-of-00051.safetensors",
+    "layers.41.feed_forward.w1.weight": "consolidated-00021-of-00051.safetensors",
+    "layers.41.feed_forward.w2.weight": "consolidated-00021-of-00051.safetensors",
+    "layers.41.feed_forward.w3.weight": "consolidated-00022-of-00051.safetensors",
+    "layers.41.ffn_norm.weight": "consolidated-00022-of-00051.safetensors",
+    "layers.42.attention.wk.weight": "consolidated-00022-of-00051.safetensors",
+    "layers.42.attention.wo.weight": "consolidated-00022-of-00051.safetensors",
+    "layers.42.attention.wq.weight": "consolidated-00022-of-00051.safetensors",
+    "layers.42.attention.wv.weight": "consolidated-00022-of-00051.safetensors",
+    "layers.42.attention_norm.weight": "consolidated-00022-of-00051.safetensors",
+    "layers.42.feed_forward.w1.weight": "consolidated-00022-of-00051.safetensors",
+    "layers.42.feed_forward.w2.weight": "consolidated-00022-of-00051.safetensors",
+    "layers.42.feed_forward.w3.weight": "consolidated-00022-of-00051.safetensors",
+    "layers.42.ffn_norm.weight": "consolidated-00022-of-00051.safetensors",
+    "layers.43.attention.wk.weight": "consolidated-00022-of-00051.safetensors",
+    "layers.43.attention.wo.weight": "consolidated-00022-of-00051.safetensors",
+    "layers.43.attention.wq.weight": "consolidated-00022-of-00051.safetensors",
+    "layers.43.attention.wv.weight": "consolidated-00022-of-00051.safetensors",
+    "layers.43.attention_norm.weight": "consolidated-00022-of-00051.safetensors",
+    "layers.43.feed_forward.w1.weight": "consolidated-00022-of-00051.safetensors",
+    "layers.43.feed_forward.w2.weight": "consolidated-00023-of-00051.safetensors",
+    "layers.43.feed_forward.w3.weight": "consolidated-00023-of-00051.safetensors",
+    "layers.43.ffn_norm.weight": "consolidated-00023-of-00051.safetensors",
+    "layers.44.attention.wk.weight": "consolidated-00023-of-00051.safetensors",
+    "layers.44.attention.wo.weight": "consolidated-00023-of-00051.safetensors",
+    "layers.44.attention.wq.weight": "consolidated-00023-of-00051.safetensors",
+    "layers.44.attention.wv.weight": "consolidated-00023-of-00051.safetensors",
+    "layers.44.attention_norm.weight": "consolidated-00023-of-00051.safetensors",
+    "layers.44.feed_forward.w1.weight": "consolidated-00023-of-00051.safetensors",
+    "layers.44.feed_forward.w2.weight": "consolidated-00023-of-00051.safetensors",
+    "layers.44.feed_forward.w3.weight": "consolidated-00023-of-00051.safetensors",
+    "layers.44.ffn_norm.weight": "consolidated-00023-of-00051.safetensors",
+    "layers.45.attention.wk.weight": "consolidated-00023-of-00051.safetensors",
+    "layers.45.attention.wo.weight": "consolidated-00023-of-00051.safetensors",
+    "layers.45.attention.wq.weight": "consolidated-00023-of-00051.safetensors",
+    "layers.45.attention.wv.weight": "consolidated-00023-of-00051.safetensors",
+    "layers.45.attention_norm.weight": "consolidated-00023-of-00051.safetensors",
+    "layers.45.feed_forward.w1.weight": "consolidated-00024-of-00051.safetensors",
+    "layers.45.feed_forward.w2.weight": "consolidated-00024-of-00051.safetensors",
+    "layers.45.feed_forward.w3.weight": "consolidated-00024-of-00051.safetensors",
+    "layers.45.ffn_norm.weight": "consolidated-00024-of-00051.safetensors",
+    "layers.46.attention.wk.weight": "consolidated-00024-of-00051.safetensors",
+    "layers.46.attention.wo.weight": "consolidated-00024-of-00051.safetensors",
+    "layers.46.attention.wq.weight": "consolidated-00024-of-00051.safetensors",
+    "layers.46.attention.wv.weight": "consolidated-00024-of-00051.safetensors",
+    "layers.46.attention_norm.weight": "consolidated-00024-of-00051.safetensors",
+    "layers.46.feed_forward.w1.weight": "consolidated-00024-of-00051.safetensors",
+    "layers.46.feed_forward.w2.weight": "consolidated-00024-of-00051.safetensors",
+    "layers.46.feed_forward.w3.weight": "consolidated-00024-of-00051.safetensors",
+    "layers.46.ffn_norm.weight": "consolidated-00024-of-00051.safetensors",
+    "layers.47.attention.wk.weight": "consolidated-00024-of-00051.safetensors",
+    "layers.47.attention.wo.weight": "consolidated-00025-of-00051.safetensors",
+    "layers.47.attention.wq.weight": "consolidated-00025-of-00051.safetensors",
+    "layers.47.attention.wv.weight": "consolidated-00025-of-00051.safetensors",
+    "layers.47.attention_norm.weight": "consolidated-00025-of-00051.safetensors",
+    "layers.47.feed_forward.w1.weight": "consolidated-00025-of-00051.safetensors",
+    "layers.47.feed_forward.w2.weight": "consolidated-00025-of-00051.safetensors",
+    "layers.47.feed_forward.w3.weight": "consolidated-00025-of-00051.safetensors",
+    "layers.47.ffn_norm.weight": "consolidated-00025-of-00051.safetensors",
+    "layers.48.attention.wk.weight": "consolidated-00025-of-00051.safetensors",
+    "layers.48.attention.wo.weight": "consolidated-00025-of-00051.safetensors",
+    "layers.48.attention.wq.weight": "consolidated-00025-of-00051.safetensors",
+    "layers.48.attention.wv.weight": "consolidated-00025-of-00051.safetensors",
+    "layers.48.attention_norm.weight": "consolidated-00025-of-00051.safetensors",
+    "layers.48.feed_forward.w1.weight": "consolidated-00025-of-00051.safetensors",
+    "layers.48.feed_forward.w2.weight": "consolidated-00025-of-00051.safetensors",
+    "layers.48.feed_forward.w3.weight": "consolidated-00026-of-00051.safetensors",
+    "layers.48.ffn_norm.weight": "consolidated-00026-of-00051.safetensors",
+    "layers.49.attention.wk.weight": "consolidated-00026-of-00051.safetensors",
+    "layers.49.attention.wo.weight": "consolidated-00026-of-00051.safetensors",
+    "layers.49.attention.wq.weight": "consolidated-00026-of-00051.safetensors",
+    "layers.49.attention.wv.weight": "consolidated-00026-of-00051.safetensors",
+    "layers.49.attention_norm.weight": "consolidated-00026-of-00051.safetensors",
+    "layers.49.feed_forward.w1.weight": "consolidated-00026-of-00051.safetensors",
+    "layers.49.feed_forward.w2.weight": "consolidated-00026-of-00051.safetensors",
+    "layers.49.feed_forward.w3.weight": "consolidated-00026-of-00051.safetensors",
+    "layers.49.ffn_norm.weight": "consolidated-00026-of-00051.safetensors",
+    "layers.5.attention.wk.weight": "consolidated-00026-of-00051.safetensors",
+    "layers.5.attention.wo.weight": "consolidated-00026-of-00051.safetensors",
+    "layers.5.attention.wq.weight": "consolidated-00026-of-00051.safetensors",
+    "layers.5.attention.wv.weight": "consolidated-00026-of-00051.safetensors",
+    "layers.5.attention_norm.weight": "consolidated-00026-of-00051.safetensors",
+    "layers.5.feed_forward.w1.weight": "consolidated-00026-of-00051.safetensors",
+    "layers.5.feed_forward.w2.weight": "consolidated-00027-of-00051.safetensors",
+    "layers.5.feed_forward.w3.weight": "consolidated-00027-of-00051.safetensors",
+    "layers.5.ffn_norm.weight": "consolidated-00027-of-00051.safetensors",
+    "layers.50.attention.wk.weight": "consolidated-00027-of-00051.safetensors",
+    "layers.50.attention.wo.weight": "consolidated-00027-of-00051.safetensors",
+    "layers.50.attention.wq.weight": "consolidated-00027-of-00051.safetensors",
+    "layers.50.attention.wv.weight": "consolidated-00027-of-00051.safetensors",
+    "layers.50.attention_norm.weight": "consolidated-00027-of-00051.safetensors",
+    "layers.50.feed_forward.w1.weight": "consolidated-00027-of-00051.safetensors",
+    "layers.50.feed_forward.w2.weight": "consolidated-00027-of-00051.safetensors",
+    "layers.50.feed_forward.w3.weight": "consolidated-00027-of-00051.safetensors",
+    "layers.50.ffn_norm.weight": "consolidated-00027-of-00051.safetensors",
+    "layers.51.attention.wk.weight": "consolidated-00027-of-00051.safetensors",
+    "layers.51.attention.wo.weight": "consolidated-00027-of-00051.safetensors",
+    "layers.51.attention.wq.weight": "consolidated-00027-of-00051.safetensors",
+    "layers.51.attention.wv.weight": "consolidated-00027-of-00051.safetensors",
+    "layers.51.attention_norm.weight": "consolidated-00027-of-00051.safetensors",
+    "layers.51.feed_forward.w1.weight": "consolidated-00028-of-00051.safetensors",
+    "layers.51.feed_forward.w2.weight": "consolidated-00028-of-00051.safetensors",
+    "layers.51.feed_forward.w3.weight": "consolidated-00028-of-00051.safetensors",
+    "layers.51.ffn_norm.weight": "consolidated-00028-of-00051.safetensors",
+    "layers.52.attention.wk.weight": "consolidated-00028-of-00051.safetensors",
+    "layers.52.attention.wo.weight": "consolidated-00028-of-00051.safetensors",
+    "layers.52.attention.wq.weight": "consolidated-00028-of-00051.safetensors",
+    "layers.52.attention.wv.weight": "consolidated-00028-of-00051.safetensors",
+    "layers.52.attention_norm.weight": "consolidated-00028-of-00051.safetensors",
+    "layers.52.feed_forward.w1.weight": "consolidated-00028-of-00051.safetensors",
+    "layers.52.feed_forward.w2.weight": "consolidated-00028-of-00051.safetensors",
+    "layers.52.feed_forward.w3.weight": "consolidated-00028-of-00051.safetensors",
+    "layers.52.ffn_norm.weight": "consolidated-00028-of-00051.safetensors",
+    "layers.53.attention.wk.weight": "consolidated-00028-of-00051.safetensors",
+    "layers.53.attention.wo.weight": "consolidated-00029-of-00051.safetensors",
+    "layers.53.attention.wq.weight": "consolidated-00029-of-00051.safetensors",
+    "layers.53.attention.wv.weight": "consolidated-00029-of-00051.safetensors",
+    "layers.53.attention_norm.weight": "consolidated-00029-of-00051.safetensors",
+    "layers.53.feed_forward.w1.weight": "consolidated-00029-of-00051.safetensors",
+    "layers.53.feed_forward.w2.weight": "consolidated-00029-of-00051.safetensors",
+    "layers.53.feed_forward.w3.weight": "consolidated-00029-of-00051.safetensors",
+    "layers.53.ffn_norm.weight": "consolidated-00029-of-00051.safetensors",
+    "layers.54.attention.wk.weight": "consolidated-00029-of-00051.safetensors",
+    "layers.54.attention.wo.weight": "consolidated-00029-of-00051.safetensors",
+    "layers.54.attention.wq.weight": "consolidated-00029-of-00051.safetensors",
+    "layers.54.attention.wv.weight": "consolidated-00029-of-00051.safetensors",
+    "layers.54.attention_norm.weight": "consolidated-00029-of-00051.safetensors",
+    "layers.54.feed_forward.w1.weight": "consolidated-00029-of-00051.safetensors",
+    "layers.54.feed_forward.w2.weight": "consolidated-00029-of-00051.safetensors",
+    "layers.54.feed_forward.w3.weight": "consolidated-00030-of-00051.safetensors",
+    "layers.54.ffn_norm.weight": "consolidated-00030-of-00051.safetensors",
+    "layers.55.attention.wk.weight": "consolidated-00030-of-00051.safetensors",
+    "layers.55.attention.wo.weight": "consolidated-00030-of-00051.safetensors",
+    "layers.55.attention.wq.weight": "consolidated-00030-of-00051.safetensors",
+    "layers.55.attention.wv.weight": "consolidated-00030-of-00051.safetensors",
+    "layers.55.attention_norm.weight": "consolidated-00030-of-00051.safetensors",
+    "layers.55.feed_forward.w1.weight": "consolidated-00030-of-00051.safetensors",
+    "layers.55.feed_forward.w2.weight": "consolidated-00030-of-00051.safetensors",
+    "layers.55.feed_forward.w3.weight": "consolidated-00030-of-00051.safetensors",
+    "layers.55.ffn_norm.weight": "consolidated-00030-of-00051.safetensors",
+    "layers.56.attention.wk.weight": "consolidated-00030-of-00051.safetensors",
+    "layers.56.attention.wo.weight": "consolidated-00030-of-00051.safetensors",
+    "layers.56.attention.wq.weight": "consolidated-00030-of-00051.safetensors",
+    "layers.56.attention.wv.weight": "consolidated-00030-of-00051.safetensors",
+    "layers.56.attention_norm.weight": "consolidated-00030-of-00051.safetensors",
+    "layers.56.feed_forward.w1.weight": "consolidated-00030-of-00051.safetensors",
+    "layers.56.feed_forward.w2.weight": "consolidated-00031-of-00051.safetensors",
+    "layers.56.feed_forward.w3.weight": "consolidated-00031-of-00051.safetensors",
+    "layers.56.ffn_norm.weight": "consolidated-00031-of-00051.safetensors",
+    "layers.57.attention.wk.weight": "consolidated-00031-of-00051.safetensors",
+    "layers.57.attention.wo.weight": "consolidated-00031-of-00051.safetensors",
+    "layers.57.attention.wq.weight": "consolidated-00031-of-00051.safetensors",
+    "layers.57.attention.wv.weight": "consolidated-00031-of-00051.safetensors",
+    "layers.57.attention_norm.weight": "consolidated-00031-of-00051.safetensors",
+    "layers.57.feed_forward.w1.weight": "consolidated-00031-of-00051.safetensors",
+    "layers.57.feed_forward.w2.weight": "consolidated-00031-of-00051.safetensors",
+    "layers.57.feed_forward.w3.weight": "consolidated-00031-of-00051.safetensors",
+    "layers.57.ffn_norm.weight": "consolidated-00031-of-00051.safetensors",
+    "layers.58.attention.wk.weight": "consolidated-00031-of-00051.safetensors",
+    "layers.58.attention.wo.weight": "consolidated-00031-of-00051.safetensors",
+    "layers.58.attention.wq.weight": "consolidated-00031-of-00051.safetensors",
+    "layers.58.attention.wv.weight": "consolidated-00031-of-00051.safetensors",
+    "layers.58.attention_norm.weight": "consolidated-00031-of-00051.safetensors",
+    "layers.58.feed_forward.w1.weight": "consolidated-00032-of-00051.safetensors",
+    "layers.58.feed_forward.w2.weight": "consolidated-00032-of-00051.safetensors",
+    "layers.58.feed_forward.w3.weight": "consolidated-00032-of-00051.safetensors",
+    "layers.58.ffn_norm.weight": "consolidated-00032-of-00051.safetensors",
+    "layers.59.attention.wk.weight": "consolidated-00032-of-00051.safetensors",
+    "layers.59.attention.wo.weight": "consolidated-00032-of-00051.safetensors",
+    "layers.59.attention.wq.weight": "consolidated-00032-of-00051.safetensors",
+    "layers.59.attention.wv.weight": "consolidated-00032-of-00051.safetensors",
+    "layers.59.attention_norm.weight": "consolidated-00032-of-00051.safetensors",
+    "layers.59.feed_forward.w1.weight": "consolidated-00032-of-00051.safetensors",
+    "layers.59.feed_forward.w2.weight": "consolidated-00032-of-00051.safetensors",
+    "layers.59.feed_forward.w3.weight": "consolidated-00032-of-00051.safetensors",
+    "layers.59.ffn_norm.weight": "consolidated-00032-of-00051.safetensors",
+    "layers.6.attention.wk.weight": "consolidated-00032-of-00051.safetensors",
+    "layers.6.attention.wo.weight": "consolidated-00033-of-00051.safetensors",
+    "layers.6.attention.wq.weight": "consolidated-00033-of-00051.safetensors",
+    "layers.6.attention.wv.weight": "consolidated-00033-of-00051.safetensors",
+    "layers.6.attention_norm.weight": "consolidated-00033-of-00051.safetensors",
+    "layers.6.feed_forward.w1.weight": "consolidated-00033-of-00051.safetensors",
+    "layers.6.feed_forward.w2.weight": "consolidated-00033-of-00051.safetensors",
+    "layers.6.feed_forward.w3.weight": "consolidated-00033-of-00051.safetensors",
+    "layers.6.ffn_norm.weight": "consolidated-00033-of-00051.safetensors",
+    "layers.60.attention.wk.weight": "consolidated-00033-of-00051.safetensors",
+    "layers.60.attention.wo.weight": "consolidated-00033-of-00051.safetensors",
+    "layers.60.attention.wq.weight": "consolidated-00033-of-00051.safetensors",
+    "layers.60.attention.wv.weight": "consolidated-00033-of-00051.safetensors",
+    "layers.60.attention_norm.weight": "consolidated-00033-of-00051.safetensors",
+    "layers.60.feed_forward.w1.weight": "consolidated-00033-of-00051.safetensors",
+    "layers.60.feed_forward.w2.weight": "consolidated-00033-of-00051.safetensors",
+    "layers.60.feed_forward.w3.weight": "consolidated-00034-of-00051.safetensors",
+    "layers.60.ffn_norm.weight": "consolidated-00034-of-00051.safetensors",
+    "layers.61.attention.wk.weight": "consolidated-00034-of-00051.safetensors",
+    "layers.61.attention.wo.weight": "consolidated-00034-of-00051.safetensors",
+    "layers.61.attention.wq.weight": "consolidated-00034-of-00051.safetensors",
+    "layers.61.attention.wv.weight": "consolidated-00034-of-00051.safetensors",
+    "layers.61.attention_norm.weight": "consolidated-00034-of-00051.safetensors",
+    "layers.61.feed_forward.w1.weight": "consolidated-00034-of-00051.safetensors",
+    "layers.61.feed_forward.w2.weight": "consolidated-00034-of-00051.safetensors",
+    "layers.61.feed_forward.w3.weight": "consolidated-00034-of-00051.safetensors",
+    "layers.61.ffn_norm.weight": "consolidated-00034-of-00051.safetensors",
+    "layers.62.attention.wk.weight": "consolidated-00034-of-00051.safetensors",
+    "layers.62.attention.wo.weight": "consolidated-00034-of-00051.safetensors",
+    "layers.62.attention.wq.weight": "consolidated-00034-of-00051.safetensors",
+    "layers.62.attention.wv.weight": "consolidated-00034-of-00051.safetensors",
+    "layers.62.attention_norm.weight": "consolidated-00034-of-00051.safetensors",
+    "layers.62.feed_forward.w1.weight": "consolidated-00034-of-00051.safetensors",
+    "layers.62.feed_forward.w2.weight": "consolidated-00035-of-00051.safetensors",
+    "layers.62.feed_forward.w3.weight": "consolidated-00035-of-00051.safetensors",
+    "layers.62.ffn_norm.weight": "consolidated-00035-of-00051.safetensors",
+    "layers.63.attention.wk.weight": "consolidated-00035-of-00051.safetensors",
+    "layers.63.attention.wo.weight": "consolidated-00035-of-00051.safetensors",
+    "layers.63.attention.wq.weight": "consolidated-00035-of-00051.safetensors",
+    "layers.63.attention.wv.weight": "consolidated-00035-of-00051.safetensors",
+    "layers.63.attention_norm.weight": "consolidated-00035-of-00051.safetensors",
+    "layers.63.feed_forward.w1.weight": "consolidated-00035-of-00051.safetensors",
+    "layers.63.feed_forward.w2.weight": "consolidated-00035-of-00051.safetensors",
+    "layers.63.feed_forward.w3.weight": "consolidated-00035-of-00051.safetensors",
+    "layers.63.ffn_norm.weight": "consolidated-00035-of-00051.safetensors",
+    "layers.64.attention.wk.weight": "consolidated-00035-of-00051.safetensors",
+    "layers.64.attention.wo.weight": "consolidated-00035-of-00051.safetensors",
+    "layers.64.attention.wq.weight": "consolidated-00035-of-00051.safetensors",
+    "layers.64.attention.wv.weight": "consolidated-00035-of-00051.safetensors",
+    "layers.64.attention_norm.weight": "consolidated-00035-of-00051.safetensors",
+    "layers.64.feed_forward.w1.weight": "consolidated-00036-of-00051.safetensors",
+    "layers.64.feed_forward.w2.weight": "consolidated-00036-of-00051.safetensors",
+    "layers.64.feed_forward.w3.weight": "consolidated-00036-of-00051.safetensors",
+    "layers.64.ffn_norm.weight": "consolidated-00036-of-00051.safetensors",
+    "layers.65.attention.wk.weight": "consolidated-00036-of-00051.safetensors",
+    "layers.65.attention.wo.weight": "consolidated-00036-of-00051.safetensors",
+    "layers.65.attention.wq.weight": "consolidated-00036-of-00051.safetensors",
+    "layers.65.attention.wv.weight": "consolidated-00036-of-00051.safetensors",
+    "layers.65.attention_norm.weight": "consolidated-00036-of-00051.safetensors",
+    "layers.65.feed_forward.w1.weight": "consolidated-00036-of-00051.safetensors",
+    "layers.65.feed_forward.w2.weight": "consolidated-00036-of-00051.safetensors",
+    "layers.65.feed_forward.w3.weight": "consolidated-00036-of-00051.safetensors",
+    "layers.65.ffn_norm.weight": "consolidated-00036-of-00051.safetensors",
+    "layers.66.attention.wk.weight": "consolidated-00036-of-00051.safetensors",
+    "layers.66.attention.wo.weight": "consolidated-00037-of-00051.safetensors",
+    "layers.66.attention.wq.weight": "consolidated-00037-of-00051.safetensors",
+    "layers.66.attention.wv.weight": "consolidated-00037-of-00051.safetensors",
+    "layers.66.attention_norm.weight": "consolidated-00037-of-00051.safetensors",
+    "layers.66.feed_forward.w1.weight": "consolidated-00037-of-00051.safetensors",
+    "layers.66.feed_forward.w2.weight": "consolidated-00037-of-00051.safetensors",
+    "layers.66.feed_forward.w3.weight": "consolidated-00037-of-00051.safetensors",
+    "layers.66.ffn_norm.weight": "consolidated-00037-of-00051.safetensors",
+    "layers.67.attention.wk.weight": "consolidated-00037-of-00051.safetensors",
+    "layers.67.attention.wo.weight": "consolidated-00037-of-00051.safetensors",
+    "layers.67.attention.wq.weight": "consolidated-00037-of-00051.safetensors",
+    "layers.67.attention.wv.weight": "consolidated-00037-of-00051.safetensors",
+    "layers.67.attention_norm.weight": "consolidated-00037-of-00051.safetensors",
+    "layers.67.feed_forward.w1.weight": "consolidated-00037-of-00051.safetensors",
+    "layers.67.feed_forward.w2.weight": "consolidated-00037-of-00051.safetensors",
+    "layers.67.feed_forward.w3.weight": "consolidated-00038-of-00051.safetensors",
+    "layers.67.ffn_norm.weight": "consolidated-00038-of-00051.safetensors",
+    "layers.68.attention.wk.weight": "consolidated-00038-of-00051.safetensors",
+    "layers.68.attention.wo.weight": "consolidated-00038-of-00051.safetensors",
+    "layers.68.attention.wq.weight": "consolidated-00038-of-00051.safetensors",
+    "layers.68.attention.wv.weight": "consolidated-00038-of-00051.safetensors",
+    "layers.68.attention_norm.weight": "consolidated-00038-of-00051.safetensors",
+    "layers.68.feed_forward.w1.weight": "consolidated-00038-of-00051.safetensors",
+    "layers.68.feed_forward.w2.weight": "consolidated-00038-of-00051.safetensors",
+    "layers.68.feed_forward.w3.weight": "consolidated-00038-of-00051.safetensors",
+    "layers.68.ffn_norm.weight": "consolidated-00038-of-00051.safetensors",
+    "layers.69.attention.wk.weight": "consolidated-00038-of-00051.safetensors",
+    "layers.69.attention.wo.weight": "consolidated-00038-of-00051.safetensors",
+    "layers.69.attention.wq.weight": "consolidated-00038-of-00051.safetensors",
+    "layers.69.attention.wv.weight": "consolidated-00038-of-00051.safetensors",
+    "layers.69.attention_norm.weight": "consolidated-00038-of-00051.safetensors",
+    "layers.69.feed_forward.w1.weight": "consolidated-00038-of-00051.safetensors",
+    "layers.69.feed_forward.w2.weight": "consolidated-00039-of-00051.safetensors",
+    "layers.69.feed_forward.w3.weight": "consolidated-00039-of-00051.safetensors",
+    "layers.69.ffn_norm.weight": "consolidated-00039-of-00051.safetensors",
+    "layers.7.attention.wk.weight": "consolidated-00039-of-00051.safetensors",
+    "layers.7.attention.wo.weight": "consolidated-00039-of-00051.safetensors",
+    "layers.7.attention.wq.weight": "consolidated-00039-of-00051.safetensors",
+    "layers.7.attention.wv.weight": "consolidated-00039-of-00051.safetensors",
+    "layers.7.attention_norm.weight": "consolidated-00039-of-00051.safetensors",
+    "layers.7.feed_forward.w1.weight": "consolidated-00039-of-00051.safetensors",
+    "layers.7.feed_forward.w2.weight": "consolidated-00039-of-00051.safetensors",
+    "layers.7.feed_forward.w3.weight": "consolidated-00039-of-00051.safetensors",
+    "layers.7.ffn_norm.weight": "consolidated-00039-of-00051.safetensors",
+    "layers.70.attention.wk.weight": "consolidated-00039-of-00051.safetensors",
+    "layers.70.attention.wo.weight": "consolidated-00039-of-00051.safetensors",
+    "layers.70.attention.wq.weight": "consolidated-00039-of-00051.safetensors",
+    "layers.70.attention.wv.weight": "consolidated-00039-of-00051.safetensors",
+    "layers.70.attention_norm.weight": "consolidated-00039-of-00051.safetensors",
+    "layers.70.feed_forward.w1.weight": "consolidated-00040-of-00051.safetensors",
+    "layers.70.feed_forward.w2.weight": "consolidated-00040-of-00051.safetensors",
+    "layers.70.feed_forward.w3.weight": "consolidated-00040-of-00051.safetensors",
+    "layers.70.ffn_norm.weight": "consolidated-00040-of-00051.safetensors",
+    "layers.71.attention.wk.weight": "consolidated-00040-of-00051.safetensors",
+    "layers.71.attention.wo.weight": "consolidated-00040-of-00051.safetensors",
+    "layers.71.attention.wq.weight": "consolidated-00040-of-00051.safetensors",
+    "layers.71.attention.wv.weight": "consolidated-00040-of-00051.safetensors",
+    "layers.71.attention_norm.weight": "consolidated-00040-of-00051.safetensors",
+    "layers.71.feed_forward.w1.weight": "consolidated-00040-of-00051.safetensors",
+    "layers.71.feed_forward.w2.weight": "consolidated-00040-of-00051.safetensors",
+    "layers.71.feed_forward.w3.weight": "consolidated-00040-of-00051.safetensors",
+    "layers.71.ffn_norm.weight": "consolidated-00040-of-00051.safetensors",
+    "layers.72.attention.wk.weight": "consolidated-00040-of-00051.safetensors",
+    "layers.72.attention.wo.weight": "consolidated-00041-of-00051.safetensors",
+    "layers.72.attention.wq.weight": "consolidated-00041-of-00051.safetensors",
+    "layers.72.attention.wv.weight": "consolidated-00041-of-00051.safetensors",
+    "layers.72.attention_norm.weight": "consolidated-00041-of-00051.safetensors",
+    "layers.72.feed_forward.w1.weight": "consolidated-00041-of-00051.safetensors",
+    "layers.72.feed_forward.w2.weight": "consolidated-00041-of-00051.safetensors",
+    "layers.72.feed_forward.w3.weight": "consolidated-00041-of-00051.safetensors",
+    "layers.72.ffn_norm.weight": "consolidated-00041-of-00051.safetensors",
+    "layers.73.attention.wk.weight": "consolidated-00041-of-00051.safetensors",
+    "layers.73.attention.wo.weight": "consolidated-00041-of-00051.safetensors",
+    "layers.73.attention.wq.weight": "consolidated-00041-of-00051.safetensors",
+    "layers.73.attention.wv.weight": "consolidated-00041-of-00051.safetensors",
+    "layers.73.attention_norm.weight": "consolidated-00041-of-00051.safetensors",
+    "layers.73.feed_forward.w1.weight": "consolidated-00041-of-00051.safetensors",
+    "layers.73.feed_forward.w2.weight": "consolidated-00041-of-00051.safetensors",
+    "layers.73.feed_forward.w3.weight": "consolidated-00042-of-00051.safetensors",
+    "layers.73.ffn_norm.weight": "consolidated-00042-of-00051.safetensors",
+    "layers.74.attention.wk.weight": "consolidated-00042-of-00051.safetensors",
+    "layers.74.attention.wo.weight": "consolidated-00042-of-00051.safetensors",
+    "layers.74.attention.wq.weight": "consolidated-00042-of-00051.safetensors",
+    "layers.74.attention.wv.weight": "consolidated-00042-of-00051.safetensors",
+    "layers.74.attention_norm.weight": "consolidated-00042-of-00051.safetensors",
+    "layers.74.feed_forward.w1.weight": "consolidated-00042-of-00051.safetensors",
+    "layers.74.feed_forward.w2.weight": "consolidated-00042-of-00051.safetensors",
+    "layers.74.feed_forward.w3.weight": "consolidated-00042-of-00051.safetensors",
+    "layers.74.ffn_norm.weight": "consolidated-00042-of-00051.safetensors",
+    "layers.75.attention.wk.weight": "consolidated-00042-of-00051.safetensors",
+    "layers.75.attention.wo.weight": "consolidated-00042-of-00051.safetensors",
+    "layers.75.attention.wq.weight": "consolidated-00042-of-00051.safetensors",
+    "layers.75.attention.wv.weight": "consolidated-00042-of-00051.safetensors",
+    "layers.75.attention_norm.weight": "consolidated-00042-of-00051.safetensors",
+    "layers.75.feed_forward.w1.weight": "consolidated-00042-of-00051.safetensors",
+    "layers.75.feed_forward.w2.weight": "consolidated-00043-of-00051.safetensors",
+    "layers.75.feed_forward.w3.weight": "consolidated-00043-of-00051.safetensors",
+    "layers.75.ffn_norm.weight": "consolidated-00043-of-00051.safetensors",
+    "layers.76.attention.wk.weight": "consolidated-00043-of-00051.safetensors",
+    "layers.76.attention.wo.weight": "consolidated-00043-of-00051.safetensors",
+    "layers.76.attention.wq.weight": "consolidated-00043-of-00051.safetensors",
+    "layers.76.attention.wv.weight": "consolidated-00043-of-00051.safetensors",
+    "layers.76.attention_norm.weight": "consolidated-00043-of-00051.safetensors",
+    "layers.76.feed_forward.w1.weight": "consolidated-00043-of-00051.safetensors",
+    "layers.76.feed_forward.w2.weight": "consolidated-00043-of-00051.safetensors",
+    "layers.76.feed_forward.w3.weight": "consolidated-00043-of-00051.safetensors",
+    "layers.76.ffn_norm.weight": "consolidated-00043-of-00051.safetensors",
+    "layers.77.attention.wk.weight": "consolidated-00043-of-00051.safetensors",
+    "layers.77.attention.wo.weight": "consolidated-00043-of-00051.safetensors",
+    "layers.77.attention.wq.weight": "consolidated-00043-of-00051.safetensors",
+    "layers.77.attention.wv.weight": "consolidated-00043-of-00051.safetensors",
+    "layers.77.attention_norm.weight": "consolidated-00043-of-00051.safetensors",
+    "layers.77.feed_forward.w1.weight": "consolidated-00044-of-00051.safetensors",
+    "layers.77.feed_forward.w2.weight": "consolidated-00044-of-00051.safetensors",
+    "layers.77.feed_forward.w3.weight": "consolidated-00044-of-00051.safetensors",
+    "layers.77.ffn_norm.weight": "consolidated-00044-of-00051.safetensors",
+    "layers.78.attention.wk.weight": "consolidated-00044-of-00051.safetensors",
+    "layers.78.attention.wo.weight": "consolidated-00044-of-00051.safetensors",
+    "layers.78.attention.wq.weight": "consolidated-00044-of-00051.safetensors",
+    "layers.78.attention.wv.weight": "consolidated-00044-of-00051.safetensors",
+    "layers.78.attention_norm.weight": "consolidated-00044-of-00051.safetensors",
+    "layers.78.feed_forward.w1.weight": "consolidated-00044-of-00051.safetensors",
+    "layers.78.feed_forward.w2.weight": "consolidated-00044-of-00051.safetensors",
+    "layers.78.feed_forward.w3.weight": "consolidated-00044-of-00051.safetensors",
+    "layers.78.ffn_norm.weight": "consolidated-00044-of-00051.safetensors",
+    "layers.79.attention.wk.weight": "consolidated-00044-of-00051.safetensors",
+    "layers.79.attention.wo.weight": "consolidated-00045-of-00051.safetensors",
+    "layers.79.attention.wq.weight": "consolidated-00045-of-00051.safetensors",
+    "layers.79.attention.wv.weight": "consolidated-00045-of-00051.safetensors",
+    "layers.79.attention_norm.weight": "consolidated-00045-of-00051.safetensors",
+    "layers.79.feed_forward.w1.weight": "consolidated-00045-of-00051.safetensors",
+    "layers.79.feed_forward.w2.weight": "consolidated-00045-of-00051.safetensors",
+    "layers.79.feed_forward.w3.weight": "consolidated-00045-of-00051.safetensors",
+    "layers.79.ffn_norm.weight": "consolidated-00045-of-00051.safetensors",
+    "layers.8.attention.wk.weight": "consolidated-00045-of-00051.safetensors",
+    "layers.8.attention.wo.weight": "consolidated-00045-of-00051.safetensors",
+    "layers.8.attention.wq.weight": "consolidated-00045-of-00051.safetensors",
+    "layers.8.attention.wv.weight": "consolidated-00045-of-00051.safetensors",
+    "layers.8.attention_norm.weight": "consolidated-00045-of-00051.safetensors",
+    "layers.8.feed_forward.w1.weight": "consolidated-00045-of-00051.safetensors",
+    "layers.8.feed_forward.w2.weight": "consolidated-00045-of-00051.safetensors",
+    "layers.8.feed_forward.w3.weight": "consolidated-00046-of-00051.safetensors",
+    "layers.8.ffn_norm.weight": "consolidated-00046-of-00051.safetensors",
+    "layers.80.attention.wk.weight": "consolidated-00046-of-00051.safetensors",
+    "layers.80.attention.wo.weight": "consolidated-00046-of-00051.safetensors",
+    "layers.80.attention.wq.weight": "consolidated-00046-of-00051.safetensors",
+    "layers.80.attention.wv.weight": "consolidated-00046-of-00051.safetensors",
+    "layers.80.attention_norm.weight": "consolidated-00046-of-00051.safetensors",
+    "layers.80.feed_forward.w1.weight": "consolidated-00046-of-00051.safetensors",
+    "layers.80.feed_forward.w2.weight": "consolidated-00046-of-00051.safetensors",
+    "layers.80.feed_forward.w3.weight": "consolidated-00046-of-00051.safetensors",
+    "layers.80.ffn_norm.weight": "consolidated-00046-of-00051.safetensors",
+    "layers.81.attention.wk.weight": "consolidated-00046-of-00051.safetensors",
+    "layers.81.attention.wo.weight": "consolidated-00046-of-00051.safetensors",
+    "layers.81.attention.wq.weight": "consolidated-00046-of-00051.safetensors",
+    "layers.81.attention.wv.weight": "consolidated-00046-of-00051.safetensors",
+    "layers.81.attention_norm.weight": "consolidated-00046-of-00051.safetensors",
+    "layers.81.feed_forward.w1.weight": "consolidated-00046-of-00051.safetensors",
+    "layers.81.feed_forward.w2.weight": "consolidated-00047-of-00051.safetensors",
+    "layers.81.feed_forward.w3.weight": "consolidated-00047-of-00051.safetensors",
+    "layers.81.ffn_norm.weight": "consolidated-00047-of-00051.safetensors",
+    "layers.82.attention.wk.weight": "consolidated-00047-of-00051.safetensors",
+    "layers.82.attention.wo.weight": "consolidated-00047-of-00051.safetensors",
+    "layers.82.attention.wq.weight": "consolidated-00047-of-00051.safetensors",
+    "layers.82.attention.wv.weight": "consolidated-00047-of-00051.safetensors",
+    "layers.82.attention_norm.weight": "consolidated-00047-of-00051.safetensors",
+    "layers.82.feed_forward.w1.weight": "consolidated-00047-of-00051.safetensors",
+    "layers.82.feed_forward.w2.weight": "consolidated-00047-of-00051.safetensors",
+    "layers.82.feed_forward.w3.weight": "consolidated-00047-of-00051.safetensors",
+    "layers.82.ffn_norm.weight": "consolidated-00047-of-00051.safetensors",
+    "layers.83.attention.wk.weight": "consolidated-00047-of-00051.safetensors",
+    "layers.83.attention.wo.weight": "consolidated-00047-of-00051.safetensors",
+    "layers.83.attention.wq.weight": "consolidated-00047-of-00051.safetensors",
+    "layers.83.attention.wv.weight": "consolidated-00047-of-00051.safetensors",
+    "layers.83.attention_norm.weight": "consolidated-00047-of-00051.safetensors",
+    "layers.83.feed_forward.w1.weight": "consolidated-00048-of-00051.safetensors",
+    "layers.83.feed_forward.w2.weight": "consolidated-00048-of-00051.safetensors",
+    "layers.83.feed_forward.w3.weight": "consolidated-00048-of-00051.safetensors",
+    "layers.83.ffn_norm.weight": "consolidated-00048-of-00051.safetensors",
+    "layers.84.attention.wk.weight": "consolidated-00048-of-00051.safetensors",
+    "layers.84.attention.wo.weight": "consolidated-00048-of-00051.safetensors",
+    "layers.84.attention.wq.weight": "consolidated-00048-of-00051.safetensors",
+    "layers.84.attention.wv.weight": "consolidated-00048-of-00051.safetensors",
+    "layers.84.attention_norm.weight": "consolidated-00048-of-00051.safetensors",
+    "layers.84.feed_forward.w1.weight": "consolidated-00048-of-00051.safetensors",
+    "layers.84.feed_forward.w2.weight": "consolidated-00048-of-00051.safetensors",
+    "layers.84.feed_forward.w3.weight": "consolidated-00048-of-00051.safetensors",
+    "layers.84.ffn_norm.weight": "consolidated-00048-of-00051.safetensors",
+    "layers.85.attention.wk.weight": "consolidated-00048-of-00051.safetensors",
+    "layers.85.attention.wo.weight": "consolidated-00049-of-00051.safetensors",
+    "layers.85.attention.wq.weight": "consolidated-00049-of-00051.safetensors",
+    "layers.85.attention.wv.weight": "consolidated-00049-of-00051.safetensors",
+    "layers.85.attention_norm.weight": "consolidated-00049-of-00051.safetensors",
+    "layers.85.feed_forward.w1.weight": "consolidated-00049-of-00051.safetensors",
+    "layers.85.feed_forward.w2.weight": "consolidated-00049-of-00051.safetensors",
+    "layers.85.feed_forward.w3.weight": "consolidated-00049-of-00051.safetensors",
+    "layers.85.ffn_norm.weight": "consolidated-00049-of-00051.safetensors",
+    "layers.86.attention.wk.weight": "consolidated-00049-of-00051.safetensors",
+    "layers.86.attention.wo.weight": "consolidated-00049-of-00051.safetensors",
+    "layers.86.attention.wq.weight": "consolidated-00049-of-00051.safetensors",
+    "layers.86.attention.wv.weight": "consolidated-00049-of-00051.safetensors",
+    "layers.86.attention_norm.weight": "consolidated-00049-of-00051.safetensors",
+    "layers.86.feed_forward.w1.weight": "consolidated-00049-of-00051.safetensors",
+    "layers.86.feed_forward.w2.weight": "consolidated-00049-of-00051.safetensors",
+    "layers.86.feed_forward.w3.weight": "consolidated-00050-of-00051.safetensors",
+    "layers.86.ffn_norm.weight": "consolidated-00050-of-00051.safetensors",
+    "layers.87.attention.wk.weight": "consolidated-00050-of-00051.safetensors",
+    "layers.87.attention.wo.weight": "consolidated-00050-of-00051.safetensors",
+    "layers.87.attention.wq.weight": "consolidated-00050-of-00051.safetensors",
+    "layers.87.attention.wv.weight": "consolidated-00050-of-00051.safetensors",
+    "layers.87.attention_norm.weight": "consolidated-00050-of-00051.safetensors",
+    "layers.87.feed_forward.w1.weight": "consolidated-00050-of-00051.safetensors",
+    "layers.87.feed_forward.w2.weight": "consolidated-00050-of-00051.safetensors",
+    "layers.87.feed_forward.w3.weight": "consolidated-00050-of-00051.safetensors",
+    "layers.87.ffn_norm.weight": "consolidated-00050-of-00051.safetensors",
+    "layers.9.attention.wk.weight": "consolidated-00050-of-00051.safetensors",
+    "layers.9.attention.wo.weight": "consolidated-00050-of-00051.safetensors",
+    "layers.9.attention.wq.weight": "consolidated-00050-of-00051.safetensors",
+    "layers.9.attention.wv.weight": "consolidated-00050-of-00051.safetensors",
+    "layers.9.attention_norm.weight": "consolidated-00050-of-00051.safetensors",
+    "layers.9.feed_forward.w1.weight": "consolidated-00050-of-00051.safetensors",
+    "layers.9.feed_forward.w2.weight": "consolidated-00051-of-00051.safetensors",
+    "layers.9.feed_forward.w3.weight": "consolidated-00051-of-00051.safetensors",
+    "layers.9.ffn_norm.weight": "consolidated-00051-of-00051.safetensors",
+    "norm.weight": "consolidated-00051-of-00051.safetensors",
+    "output.weight": "consolidated-00051-of-00051.safetensors",
+    "tok_embeddings.weight": "consolidated-00051-of-00051.safetensors"
+  }
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.42.3"
+}

model.safetensors.index.json

@@ -0,0 +1,802 @@
+{
+  "metadata": {
+    "total_size": 245220139008
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00051-of-00051.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00051.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00051.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00051.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00051.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00051.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00051.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00051.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00051.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00051.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00051.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00051.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00051.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00051.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00051.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00051.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00051.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00051.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00051.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00051.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00007-of-00051.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00007-of-00051.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00007-of-00051.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00007-of-00051.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00051.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00051.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00051.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00051.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00051.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00007-of-00051.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00007-of-00051.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00007-of-00051.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00007-of-00051.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00007-of-00051.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00007-of-00051.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00051.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00007-of-00051.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00007-of-00051.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00008-of-00051.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00008-of-00051.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00008-of-00051.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00008-of-00051.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00008-of-00051.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00008-of-00051.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00008-of-00051.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00008-of-00051.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00008-of-00051.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00009-of-00051.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00009-of-00051.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00008-of-00051.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00008-of-00051.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00009-of-00051.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00008-of-00051.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00051.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00008-of-00051.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00051.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00009-of-00051.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00009-of-00051.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00009-of-00051.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00009-of-00051.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00051.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00009-of-00051.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00009-of-00051.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00009-of-00051.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00009-of-00051.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00010-of-00051.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00010-of-00051.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00009-of-00051.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00010-of-00051.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00051.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00009-of-00051.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00009-of-00051.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00009-of-00051.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00009-of-00051.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00010-of-00051.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00010-of-00051.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00010-of-00051.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00010-of-00051.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00010-of-00051.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00010-of-00051.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00010-of-00051.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00010-of-00051.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00010-of-00051.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00011-of-00051.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00011-of-00051.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00011-of-00051.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00011-of-00051.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00011-of-00051.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00010-of-00051.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00010-of-00051.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00010-of-00051.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00010-of-00051.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00011-of-00051.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00011-of-00051.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00011-of-00051.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00011-of-00051.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00011-of-00051.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00011-of-00051.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00011-of-00051.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00011-of-00051.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00011-of-00051.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00012-of-00051.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00012-of-00051.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00012-of-00051.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00012-of-00051.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00012-of-00051.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00012-of-00051.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00012-of-00051.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00012-of-00051.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00012-of-00051.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00051.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00051.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00051.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00051.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00051.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00051.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00051.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00051.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00051.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00013-of-00051.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00013-of-00051.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00012-of-00051.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00012-of-00051.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00051.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00012-of-00051.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00012-of-00051.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00012-of-00051.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00012-of-00051.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00013-of-00051.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00013-of-00051.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00013-of-00051.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00013-of-00051.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00013-of-00051.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00051.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00051.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00051.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00051.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00014-of-00051.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00014-of-00051.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00013-of-00051.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00014-of-00051.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00051.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00013-of-00051.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00013-of-00051.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00013-of-00051.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00013-of-00051.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00014-of-00051.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00014-of-00051.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00014-of-00051.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00014-of-00051.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00014-of-00051.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00014-of-00051.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00014-of-00051.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00014-of-00051.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00014-of-00051.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00015-of-00051.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00015-of-00051.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00015-of-00051.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00015-of-00051.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00015-of-00051.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00014-of-00051.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00014-of-00051.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00014-of-00051.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00014-of-00051.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00015-of-00051.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00015-of-00051.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00015-of-00051.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00015-of-00051.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00015-of-00051.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00015-of-00051.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00015-of-00051.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00015-of-00051.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00015-of-00051.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00016-of-00051.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00016-of-00051.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00016-of-00051.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00016-of-00051.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00016-of-00051.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00016-of-00051.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00016-of-00051.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00016-of-00051.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00016-of-00051.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00017-of-00051.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00017-of-00051.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00016-of-00051.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00016-of-00051.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00017-of-00051.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00016-of-00051.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00016-of-00051.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00016-of-00051.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00016-of-00051.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00017-of-00051.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00017-of-00051.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00017-of-00051.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00017-of-00051.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00017-of-00051.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00017-of-00051.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00017-of-00051.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00017-of-00051.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00017-of-00051.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00018-of-00051.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00018-of-00051.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00017-of-00051.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00018-of-00051.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00018-of-00051.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00017-of-00051.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00017-of-00051.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00017-of-00051.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00017-of-00051.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00051.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00051.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00051.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00051.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00051.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00051.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00051.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00051.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00051.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00018-of-00051.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00018-of-00051.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00018-of-00051.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00018-of-00051.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00018-of-00051.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00018-of-00051.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00018-of-00051.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00018-of-00051.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00018-of-00051.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00019-of-00051.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00019-of-00051.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00019-of-00051.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00019-of-00051.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00019-of-00051.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00018-of-00051.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00018-of-00051.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00018-of-00051.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00018-of-00051.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00019-of-00051.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00019-of-00051.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00019-of-00051.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00019-of-00051.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00019-of-00051.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00019-of-00051.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00019-of-00051.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00019-of-00051.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00019-of-00051.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00020-of-00051.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00020-of-00051.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00020-of-00051.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00020-of-00051.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00020-of-00051.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00020-of-00051.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00020-of-00051.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00020-of-00051.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00020-of-00051.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00021-of-00051.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00021-of-00051.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00020-of-00051.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00020-of-00051.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00021-of-00051.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00020-of-00051.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00020-of-00051.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00020-of-00051.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00020-of-00051.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00021-of-00051.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00021-of-00051.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00021-of-00051.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00021-of-00051.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00021-of-00051.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00021-of-00051.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00021-of-00051.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00021-of-00051.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00021-of-00051.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00022-of-00051.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00022-of-00051.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00021-of-00051.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00022-of-00051.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00022-of-00051.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00021-of-00051.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00021-of-00051.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00021-of-00051.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00021-of-00051.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00022-of-00051.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00022-of-00051.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00022-of-00051.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00022-of-00051.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00022-of-00051.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00022-of-00051.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00022-of-00051.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00022-of-00051.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00022-of-00051.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00023-of-00051.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00023-of-00051.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00023-of-00051.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00023-of-00051.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00023-of-00051.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00022-of-00051.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00022-of-00051.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00022-of-00051.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00022-of-00051.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00023-of-00051.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00023-of-00051.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00023-of-00051.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00023-of-00051.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00023-of-00051.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00023-of-00051.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00023-of-00051.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00023-of-00051.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00023-of-00051.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00051.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00051.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00051.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00051.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00051.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00051.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00051.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00051.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00051.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00024-of-00051.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00024-of-00051.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00024-of-00051.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00024-of-00051.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00024-of-00051.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00024-of-00051.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00024-of-00051.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00024-of-00051.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00024-of-00051.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00025-of-00051.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00025-of-00051.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00024-of-00051.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00024-of-00051.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00025-of-00051.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00024-of-00051.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00024-of-00051.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00024-of-00051.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00024-of-00051.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00025-of-00051.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00025-of-00051.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00025-of-00051.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00025-of-00051.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00025-of-00051.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00025-of-00051.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00025-of-00051.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00025-of-00051.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00025-of-00051.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00026-of-00051.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00026-of-00051.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00025-of-00051.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00026-of-00051.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00026-of-00051.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00025-of-00051.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00025-of-00051.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00025-of-00051.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00025-of-00051.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00026-of-00051.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00026-of-00051.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00026-of-00051.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00026-of-00051.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00026-of-00051.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00026-of-00051.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00026-of-00051.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00026-of-00051.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00026-of-00051.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00027-of-00051.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00027-of-00051.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00027-of-00051.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00027-of-00051.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00027-of-00051.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00026-of-00051.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00026-of-00051.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00026-of-00051.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00026-of-00051.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00027-of-00051.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00027-of-00051.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00027-of-00051.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00027-of-00051.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00027-of-00051.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00027-of-00051.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00027-of-00051.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00027-of-00051.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00027-of-00051.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00028-of-00051.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00028-of-00051.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00028-of-00051.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00028-of-00051.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00028-of-00051.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00028-of-00051.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00028-of-00051.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00028-of-00051.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00028-of-00051.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00029-of-00051.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00029-of-00051.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00028-of-00051.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00028-of-00051.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00029-of-00051.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00028-of-00051.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00028-of-00051.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00028-of-00051.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00028-of-00051.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00029-of-00051.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00029-of-00051.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00029-of-00051.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00029-of-00051.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00029-of-00051.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00029-of-00051.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00029-of-00051.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00029-of-00051.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00029-of-00051.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00004-of-00051.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00004-of-00051.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00051.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00004-of-00051.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00051.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00051.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00051.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00051.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00051.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00030-of-00051.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00030-of-00051.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00029-of-00051.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00030-of-00051.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00030-of-00051.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00029-of-00051.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00029-of-00051.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00029-of-00051.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00029-of-00051.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00030-of-00051.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00030-of-00051.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00030-of-00051.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00030-of-00051.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00030-of-00051.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00030-of-00051.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00030-of-00051.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00030-of-00051.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00030-of-00051.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00031-of-00051.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00031-of-00051.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00031-of-00051.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00031-of-00051.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00031-of-00051.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00030-of-00051.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00030-of-00051.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00030-of-00051.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00030-of-00051.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00031-of-00051.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00031-of-00051.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00031-of-00051.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00031-of-00051.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00031-of-00051.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00031-of-00051.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00031-of-00051.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00031-of-00051.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00031-of-00051.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00032-of-00051.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00032-of-00051.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00032-of-00051.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00032-of-00051.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00032-of-00051.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00032-of-00051.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00032-of-00051.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00032-of-00051.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00032-of-00051.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00033-of-00051.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00033-of-00051.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00032-of-00051.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00032-of-00051.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00033-of-00051.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00032-of-00051.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00032-of-00051.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00032-of-00051.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00032-of-00051.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00033-of-00051.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00033-of-00051.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00033-of-00051.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00033-of-00051.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00033-of-00051.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00033-of-00051.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00033-of-00051.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00033-of-00051.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00033-of-00051.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00034-of-00051.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00034-of-00051.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00033-of-00051.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00034-of-00051.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00034-of-00051.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00033-of-00051.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00033-of-00051.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00033-of-00051.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00033-of-00051.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00034-of-00051.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00034-of-00051.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00034-of-00051.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00034-of-00051.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00034-of-00051.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00034-of-00051.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00034-of-00051.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00034-of-00051.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00034-of-00051.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00035-of-00051.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00035-of-00051.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00035-of-00051.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00035-of-00051.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00035-of-00051.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00034-of-00051.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00034-of-00051.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00034-of-00051.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00034-of-00051.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00005-of-00051.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00005-of-00051.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00051.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00004-of-00051.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00051.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00051.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00051.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00051.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00051.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00035-of-00051.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00035-of-00051.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00035-of-00051.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00035-of-00051.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00035-of-00051.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00035-of-00051.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00035-of-00051.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00035-of-00051.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00035-of-00051.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00036-of-00051.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00036-of-00051.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00036-of-00051.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00036-of-00051.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00036-of-00051.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00036-of-00051.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00036-of-00051.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00036-of-00051.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00036-of-00051.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00037-of-00051.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00037-of-00051.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00036-of-00051.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00036-of-00051.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00037-of-00051.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00036-of-00051.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00036-of-00051.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00036-of-00051.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00036-of-00051.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00037-of-00051.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00037-of-00051.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00037-of-00051.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00037-of-00051.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00037-of-00051.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00037-of-00051.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00037-of-00051.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00037-of-00051.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00037-of-00051.safetensors",
+    "model.layers.64.input_layernorm.weight": "model-00038-of-00051.safetensors",
+    "model.layers.64.mlp.down_proj.weight": "model-00038-of-00051.safetensors",
+    "model.layers.64.mlp.gate_proj.weight": "model-00037-of-00051.safetensors",
+    "model.layers.64.mlp.up_proj.weight": "model-00038-of-00051.safetensors",
+    "model.layers.64.post_attention_layernorm.weight": "model-00038-of-00051.safetensors",
+    "model.layers.64.self_attn.k_proj.weight": "model-00037-of-00051.safetensors",
+    "model.layers.64.self_attn.o_proj.weight": "model-00037-of-00051.safetensors",
+    "model.layers.64.self_attn.q_proj.weight": "model-00037-of-00051.safetensors",
+    "model.layers.64.self_attn.v_proj.weight": "model-00037-of-00051.safetensors",
+    "model.layers.65.input_layernorm.weight": "model-00038-of-00051.safetensors",
+    "model.layers.65.mlp.down_proj.weight": "model-00038-of-00051.safetensors",
+    "model.layers.65.mlp.gate_proj.weight": "model-00038-of-00051.safetensors",
+    "model.layers.65.mlp.up_proj.weight": "model-00038-of-00051.safetensors",
+    "model.layers.65.post_attention_layernorm.weight": "model-00038-of-00051.safetensors",
+    "model.layers.65.self_attn.k_proj.weight": "model-00038-of-00051.safetensors",
+    "model.layers.65.self_attn.o_proj.weight": "model-00038-of-00051.safetensors",
+    "model.layers.65.self_attn.q_proj.weight": "model-00038-of-00051.safetensors",
+    "model.layers.65.self_attn.v_proj.weight": "model-00038-of-00051.safetensors",
+    "model.layers.66.input_layernorm.weight": "model-00039-of-00051.safetensors",
+    "model.layers.66.mlp.down_proj.weight": "model-00039-of-00051.safetensors",
+    "model.layers.66.mlp.gate_proj.weight": "model-00039-of-00051.safetensors",
+    "model.layers.66.mlp.up_proj.weight": "model-00039-of-00051.safetensors",
+    "model.layers.66.post_attention_layernorm.weight": "model-00039-of-00051.safetensors",
+    "model.layers.66.self_attn.k_proj.weight": "model-00038-of-00051.safetensors",
+    "model.layers.66.self_attn.o_proj.weight": "model-00038-of-00051.safetensors",
+    "model.layers.66.self_attn.q_proj.weight": "model-00038-of-00051.safetensors",
+    "model.layers.66.self_attn.v_proj.weight": "model-00038-of-00051.safetensors",
+    "model.layers.67.input_layernorm.weight": "model-00039-of-00051.safetensors",
+    "model.layers.67.mlp.down_proj.weight": "model-00039-of-00051.safetensors",
+    "model.layers.67.mlp.gate_proj.weight": "model-00039-of-00051.safetensors",
+    "model.layers.67.mlp.up_proj.weight": "model-00039-of-00051.safetensors",
+    "model.layers.67.post_attention_layernorm.weight": "model-00039-of-00051.safetensors",
+    "model.layers.67.self_attn.k_proj.weight": "model-00039-of-00051.safetensors",
+    "model.layers.67.self_attn.o_proj.weight": "model-00039-of-00051.safetensors",
+    "model.layers.67.self_attn.q_proj.weight": "model-00039-of-00051.safetensors",
+    "model.layers.67.self_attn.v_proj.weight": "model-00039-of-00051.safetensors",
+    "model.layers.68.input_layernorm.weight": "model-00040-of-00051.safetensors",
+    "model.layers.68.mlp.down_proj.weight": "model-00040-of-00051.safetensors",
+    "model.layers.68.mlp.gate_proj.weight": "model-00040-of-00051.safetensors",
+    "model.layers.68.mlp.up_proj.weight": "model-00040-of-00051.safetensors",
+    "model.layers.68.post_attention_layernorm.weight": "model-00040-of-00051.safetensors",
+    "model.layers.68.self_attn.k_proj.weight": "model-00040-of-00051.safetensors",
+    "model.layers.68.self_attn.o_proj.weight": "model-00040-of-00051.safetensors",
+    "model.layers.68.self_attn.q_proj.weight": "model-00040-of-00051.safetensors",
+    "model.layers.68.self_attn.v_proj.weight": "model-00040-of-00051.safetensors",
+    "model.layers.69.input_layernorm.weight": "model-00041-of-00051.safetensors",
+    "model.layers.69.mlp.down_proj.weight": "model-00041-of-00051.safetensors",
+    "model.layers.69.mlp.gate_proj.weight": "model-00040-of-00051.safetensors",
+    "model.layers.69.mlp.up_proj.weight": "model-00040-of-00051.safetensors",
+    "model.layers.69.post_attention_layernorm.weight": "model-00041-of-00051.safetensors",
+    "model.layers.69.self_attn.k_proj.weight": "model-00040-of-00051.safetensors",
+    "model.layers.69.self_attn.o_proj.weight": "model-00040-of-00051.safetensors",
+    "model.layers.69.self_attn.q_proj.weight": "model-00040-of-00051.safetensors",
+    "model.layers.69.self_attn.v_proj.weight": "model-00040-of-00051.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00005-of-00051.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00005-of-00051.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00051.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00005-of-00051.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00051.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00051.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00051.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00051.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00051.safetensors",
+    "model.layers.70.input_layernorm.weight": "model-00041-of-00051.safetensors",
+    "model.layers.70.mlp.down_proj.weight": "model-00041-of-00051.safetensors",
+    "model.layers.70.mlp.gate_proj.weight": "model-00041-of-00051.safetensors",
+    "model.layers.70.mlp.up_proj.weight": "model-00041-of-00051.safetensors",
+    "model.layers.70.post_attention_layernorm.weight": "model-00041-of-00051.safetensors",
+    "model.layers.70.self_attn.k_proj.weight": "model-00041-of-00051.safetensors",
+    "model.layers.70.self_attn.o_proj.weight": "model-00041-of-00051.safetensors",
+    "model.layers.70.self_attn.q_proj.weight": "model-00041-of-00051.safetensors",
+    "model.layers.70.self_attn.v_proj.weight": "model-00041-of-00051.safetensors",
+    "model.layers.71.input_layernorm.weight": "model-00042-of-00051.safetensors",
+    "model.layers.71.mlp.down_proj.weight": "model-00042-of-00051.safetensors",
+    "model.layers.71.mlp.gate_proj.weight": "model-00041-of-00051.safetensors",
+    "model.layers.71.mlp.up_proj.weight": "model-00042-of-00051.safetensors",
+    "model.layers.71.post_attention_layernorm.weight": "model-00042-of-00051.safetensors",
+    "model.layers.71.self_attn.k_proj.weight": "model-00041-of-00051.safetensors",
+    "model.layers.71.self_attn.o_proj.weight": "model-00041-of-00051.safetensors",
+    "model.layers.71.self_attn.q_proj.weight": "model-00041-of-00051.safetensors",
+    "model.layers.71.self_attn.v_proj.weight": "model-00041-of-00051.safetensors",
+    "model.layers.72.input_layernorm.weight": "model-00042-of-00051.safetensors",
+    "model.layers.72.mlp.down_proj.weight": "model-00042-of-00051.safetensors",
+    "model.layers.72.mlp.gate_proj.weight": "model-00042-of-00051.safetensors",
+    "model.layers.72.mlp.up_proj.weight": "model-00042-of-00051.safetensors",
+    "model.layers.72.post_attention_layernorm.weight": "model-00042-of-00051.safetensors",
+    "model.layers.72.self_attn.k_proj.weight": "model-00042-of-00051.safetensors",
+    "model.layers.72.self_attn.o_proj.weight": "model-00042-of-00051.safetensors",
+    "model.layers.72.self_attn.q_proj.weight": "model-00042-of-00051.safetensors",
+    "model.layers.72.self_attn.v_proj.weight": "model-00042-of-00051.safetensors",
+    "model.layers.73.input_layernorm.weight": "model-00043-of-00051.safetensors",
+    "model.layers.73.mlp.down_proj.weight": "model-00043-of-00051.safetensors",
+    "model.layers.73.mlp.gate_proj.weight": "model-00043-of-00051.safetensors",
+    "model.layers.73.mlp.up_proj.weight": "model-00043-of-00051.safetensors",
+    "model.layers.73.post_attention_layernorm.weight": "model-00043-of-00051.safetensors",
+    "model.layers.73.self_attn.k_proj.weight": "model-00042-of-00051.safetensors",
+    "model.layers.73.self_attn.o_proj.weight": "model-00042-of-00051.safetensors",
+    "model.layers.73.self_attn.q_proj.weight": "model-00042-of-00051.safetensors",
+    "model.layers.73.self_attn.v_proj.weight": "model-00042-of-00051.safetensors",
+    "model.layers.74.input_layernorm.weight": "model-00043-of-00051.safetensors",
+    "model.layers.74.mlp.down_proj.weight": "model-00043-of-00051.safetensors",
+    "model.layers.74.mlp.gate_proj.weight": "model-00043-of-00051.safetensors",
+    "model.layers.74.mlp.up_proj.weight": "model-00043-of-00051.safetensors",
+    "model.layers.74.post_attention_layernorm.weight": "model-00043-of-00051.safetensors",
+    "model.layers.74.self_attn.k_proj.weight": "model-00043-of-00051.safetensors",
+    "model.layers.74.self_attn.o_proj.weight": "model-00043-of-00051.safetensors",
+    "model.layers.74.self_attn.q_proj.weight": "model-00043-of-00051.safetensors",
+    "model.layers.74.self_attn.v_proj.weight": "model-00043-of-00051.safetensors",
+    "model.layers.75.input_layernorm.weight": "model-00044-of-00051.safetensors",
+    "model.layers.75.mlp.down_proj.weight": "model-00044-of-00051.safetensors",
+    "model.layers.75.mlp.gate_proj.weight": "model-00044-of-00051.safetensors",
+    "model.layers.75.mlp.up_proj.weight": "model-00044-of-00051.safetensors",
+    "model.layers.75.post_attention_layernorm.weight": "model-00044-of-00051.safetensors",
+    "model.layers.75.self_attn.k_proj.weight": "model-00044-of-00051.safetensors",
+    "model.layers.75.self_attn.o_proj.weight": "model-00044-of-00051.safetensors",
+    "model.layers.75.self_attn.q_proj.weight": "model-00044-of-00051.safetensors",
+    "model.layers.75.self_attn.v_proj.weight": "model-00044-of-00051.safetensors",
+    "model.layers.76.input_layernorm.weight": "model-00045-of-00051.safetensors",
+    "model.layers.76.mlp.down_proj.weight": "model-00045-of-00051.safetensors",
+    "model.layers.76.mlp.gate_proj.weight": "model-00044-of-00051.safetensors",
+    "model.layers.76.mlp.up_proj.weight": "model-00044-of-00051.safetensors",
+    "model.layers.76.post_attention_layernorm.weight": "model-00045-of-00051.safetensors",
+    "model.layers.76.self_attn.k_proj.weight": "model-00044-of-00051.safetensors",
+    "model.layers.76.self_attn.o_proj.weight": "model-00044-of-00051.safetensors",
+    "model.layers.76.self_attn.q_proj.weight": "model-00044-of-00051.safetensors",
+    "model.layers.76.self_attn.v_proj.weight": "model-00044-of-00051.safetensors",
+    "model.layers.77.input_layernorm.weight": "model-00045-of-00051.safetensors",
+    "model.layers.77.mlp.down_proj.weight": "model-00045-of-00051.safetensors",
+    "model.layers.77.mlp.gate_proj.weight": "model-00045-of-00051.safetensors",
+    "model.layers.77.mlp.up_proj.weight": "model-00045-of-00051.safetensors",
+    "model.layers.77.post_attention_layernorm.weight": "model-00045-of-00051.safetensors",
+    "model.layers.77.self_attn.k_proj.weight": "model-00045-of-00051.safetensors",
+    "model.layers.77.self_attn.o_proj.weight": "model-00045-of-00051.safetensors",
+    "model.layers.77.self_attn.q_proj.weight": "model-00045-of-00051.safetensors",
+    "model.layers.77.self_attn.v_proj.weight": "model-00045-of-00051.safetensors",
+    "model.layers.78.input_layernorm.weight": "model-00046-of-00051.safetensors",
+    "model.layers.78.mlp.down_proj.weight": "model-00046-of-00051.safetensors",
+    "model.layers.78.mlp.gate_proj.weight": "model-00045-of-00051.safetensors",
+    "model.layers.78.mlp.up_proj.weight": "model-00046-of-00051.safetensors",
+    "model.layers.78.post_attention_layernorm.weight": "model-00046-of-00051.safetensors",
+    "model.layers.78.self_attn.k_proj.weight": "model-00045-of-00051.safetensors",
+    "model.layers.78.self_attn.o_proj.weight": "model-00045-of-00051.safetensors",
+    "model.layers.78.self_attn.q_proj.weight": "model-00045-of-00051.safetensors",
+    "model.layers.78.self_attn.v_proj.weight": "model-00045-of-00051.safetensors",
+    "model.layers.79.input_layernorm.weight": "model-00046-of-00051.safetensors",
+    "model.layers.79.mlp.down_proj.weight": "model-00046-of-00051.safetensors",
+    "model.layers.79.mlp.gate_proj.weight": "model-00046-of-00051.safetensors",
+    "model.layers.79.mlp.up_proj.weight": "model-00046-of-00051.safetensors",
+    "model.layers.79.post_attention_layernorm.weight": "model-00046-of-00051.safetensors",
+    "model.layers.79.self_attn.k_proj.weight": "model-00046-of-00051.safetensors",
+    "model.layers.79.self_attn.o_proj.weight": "model-00046-of-00051.safetensors",
+    "model.layers.79.self_attn.q_proj.weight": "model-00046-of-00051.safetensors",
+    "model.layers.79.self_attn.v_proj.weight": "model-00046-of-00051.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00006-of-00051.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00006-of-00051.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00051.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00006-of-00051.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00051.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00051.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00051.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00051.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00051.safetensors",
+    "model.layers.80.input_layernorm.weight": "model-00047-of-00051.safetensors",
+    "model.layers.80.mlp.down_proj.weight": "model-00047-of-00051.safetensors",
+    "model.layers.80.mlp.gate_proj.weight": "model-00047-of-00051.safetensors",
+    "model.layers.80.mlp.up_proj.weight": "model-00047-of-00051.safetensors",
+    "model.layers.80.post_attention_layernorm.weight": "model-00047-of-00051.safetensors",
+    "model.layers.80.self_attn.k_proj.weight": "model-00046-of-00051.safetensors",
+    "model.layers.80.self_attn.o_proj.weight": "model-00046-of-00051.safetensors",
+    "model.layers.80.self_attn.q_proj.weight": "model-00046-of-00051.safetensors",
+    "model.layers.80.self_attn.v_proj.weight": "model-00046-of-00051.safetensors",
+    "model.layers.81.input_layernorm.weight": "model-00047-of-00051.safetensors",
+    "model.layers.81.mlp.down_proj.weight": "model-00047-of-00051.safetensors",
+    "model.layers.81.mlp.gate_proj.weight": "model-00047-of-00051.safetensors",
+    "model.layers.81.mlp.up_proj.weight": "model-00047-of-00051.safetensors",
+    "model.layers.81.post_attention_layernorm.weight": "model-00047-of-00051.safetensors",
+    "model.layers.81.self_attn.k_proj.weight": "model-00047-of-00051.safetensors",
+    "model.layers.81.self_attn.o_proj.weight": "model-00047-of-00051.safetensors",
+    "model.layers.81.self_attn.q_proj.weight": "model-00047-of-00051.safetensors",
+    "model.layers.81.self_attn.v_proj.weight": "model-00047-of-00051.safetensors",
+    "model.layers.82.input_layernorm.weight": "model-00048-of-00051.safetensors",
+    "model.layers.82.mlp.down_proj.weight": "model-00048-of-00051.safetensors",
+    "model.layers.82.mlp.gate_proj.weight": "model-00048-of-00051.safetensors",
+    "model.layers.82.mlp.up_proj.weight": "model-00048-of-00051.safetensors",
+    "model.layers.82.post_attention_layernorm.weight": "model-00048-of-00051.safetensors",
+    "model.layers.82.self_attn.k_proj.weight": "model-00048-of-00051.safetensors",
+    "model.layers.82.self_attn.o_proj.weight": "model-00048-of-00051.safetensors",
+    "model.layers.82.self_attn.q_proj.weight": "model-00048-of-00051.safetensors",
+    "model.layers.82.self_attn.v_proj.weight": "model-00048-of-00051.safetensors",
+    "model.layers.83.input_layernorm.weight": "model-00049-of-00051.safetensors",
+    "model.layers.83.mlp.down_proj.weight": "model-00049-of-00051.safetensors",
+    "model.layers.83.mlp.gate_proj.weight": "model-00048-of-00051.safetensors",
+    "model.layers.83.mlp.up_proj.weight": "model-00048-of-00051.safetensors",
+    "model.layers.83.post_attention_layernorm.weight": "model-00049-of-00051.safetensors",
+    "model.layers.83.self_attn.k_proj.weight": "model-00048-of-00051.safetensors",
+    "model.layers.83.self_attn.o_proj.weight": "model-00048-of-00051.safetensors",
+    "model.layers.83.self_attn.q_proj.weight": "model-00048-of-00051.safetensors",
+    "model.layers.83.self_attn.v_proj.weight": "model-00048-of-00051.safetensors",
+    "model.layers.84.input_layernorm.weight": "model-00049-of-00051.safetensors",
+    "model.layers.84.mlp.down_proj.weight": "model-00049-of-00051.safetensors",
+    "model.layers.84.mlp.gate_proj.weight": "model-00049-of-00051.safetensors",
+    "model.layers.84.mlp.up_proj.weight": "model-00049-of-00051.safetensors",
+    "model.layers.84.post_attention_layernorm.weight": "model-00049-of-00051.safetensors",
+    "model.layers.84.self_attn.k_proj.weight": "model-00049-of-00051.safetensors",
+    "model.layers.84.self_attn.o_proj.weight": "model-00049-of-00051.safetensors",
+    "model.layers.84.self_attn.q_proj.weight": "model-00049-of-00051.safetensors",
+    "model.layers.84.self_attn.v_proj.weight": "model-00049-of-00051.safetensors",
+    "model.layers.85.input_layernorm.weight": "model-00050-of-00051.safetensors",
+    "model.layers.85.mlp.down_proj.weight": "model-00050-of-00051.safetensors",
+    "model.layers.85.mlp.gate_proj.weight": "model-00049-of-00051.safetensors",
+    "model.layers.85.mlp.up_proj.weight": "model-00050-of-00051.safetensors",
+    "model.layers.85.post_attention_layernorm.weight": "model-00050-of-00051.safetensors",
+    "model.layers.85.self_attn.k_proj.weight": "model-00049-of-00051.safetensors",
+    "model.layers.85.self_attn.o_proj.weight": "model-00049-of-00051.safetensors",
+    "model.layers.85.self_attn.q_proj.weight": "model-00049-of-00051.safetensors",
+    "model.layers.85.self_attn.v_proj.weight": "model-00049-of-00051.safetensors",
+    "model.layers.86.input_layernorm.weight": "model-00050-of-00051.safetensors",
+    "model.layers.86.mlp.down_proj.weight": "model-00050-of-00051.safetensors",
+    "model.layers.86.mlp.gate_proj.weight": "model-00050-of-00051.safetensors",
+    "model.layers.86.mlp.up_proj.weight": "model-00050-of-00051.safetensors",
+    "model.layers.86.post_attention_layernorm.weight": "model-00050-of-00051.safetensors",
+    "model.layers.86.self_attn.k_proj.weight": "model-00050-of-00051.safetensors",
+    "model.layers.86.self_attn.o_proj.weight": "model-00050-of-00051.safetensors",
+    "model.layers.86.self_attn.q_proj.weight": "model-00050-of-00051.safetensors",
+    "model.layers.86.self_attn.v_proj.weight": "model-00050-of-00051.safetensors",
+    "model.layers.87.input_layernorm.weight": "model-00051-of-00051.safetensors",
+    "model.layers.87.mlp.down_proj.weight": "model-00051-of-00051.safetensors",
+    "model.layers.87.mlp.gate_proj.weight": "model-00051-of-00051.safetensors",
+    "model.layers.87.mlp.up_proj.weight": "model-00051-of-00051.safetensors",
+    "model.layers.87.post_attention_layernorm.weight": "model-00051-of-00051.safetensors",
+    "model.layers.87.self_attn.k_proj.weight": "model-00050-of-00051.safetensors",
+    "model.layers.87.self_attn.o_proj.weight": "model-00050-of-00051.safetensors",
+    "model.layers.87.self_attn.q_proj.weight": "model-00050-of-00051.safetensors",
+    "model.layers.87.self_attn.v_proj.weight": "model-00050-of-00051.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00006-of-00051.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00006-of-00051.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00006-of-00051.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00006-of-00051.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00051.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00051.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00051.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00051.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00051.safetensors",
+    "model.norm.weight": "model-00051-of-00051.safetensors"
+  }
+}

params.json

@@ -0,0 +1,11 @@
+{
+    "dim": 12288,
+    "n_layers": 88,
+    "head_dim": 128,
+    "hidden_dim": 28672,
+    "n_heads": 96,
+    "n_kv_heads": 8,
+    "norm_eps": 1e-05,
+    "vocab_size": 32768,
+    "rope_theta": 1000000.0
+}

test.py

@@ -0,0 +1,26 @@
+import json
+from typing import Dict
+
+from safetensors.torch import load_file, save_file
+from huggingface_hub import split_torch_state_dict_into_shards
+import torch
+import os
+
+def save_state_dict(state_dict: Dict[str, torch.Tensor], save_directory: str):
+    state_dict_split = split_torch_state_dict_into_shards(state_dict, filename_pattern='consolidated{suffix}.safetensors')
+    for filename, tensors in state_dict_split.filename_to_tensors.items():
+        shard = {tensor: state_dict[tensor] for tensor in tensors}
+        print("Saving", save_directory, filename)
+        save_file(shard, os.path.join(save_directory, filename))
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        with open(os.path.join(save_directory, "consolidated.safetensors.index.json"), "w") as f:
+            f.write(json.dumps(index, indent=2))
+
+big_file = 'consolidated.safetensors'
+loaded = load_file(big_file)
+
+save_state_dict(loaded, save_directory=f'.')

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59f95e28944c062244741268596badc900df86c7f5ded05088d2da22a7379e06
+size 587583