Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,10 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tekken.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+assets/swe_bench.png filter=lfs diff=lfs merge=lfs -text
+assets/tuto_open_hands/agent_working.png filter=lfs diff=lfs merge=lfs -text
+assets/tuto_open_hands/build_app.png filter=lfs diff=lfs merge=lfs -text
+assets/tuto_open_hands/agent_prompting.png filter=lfs diff=lfs merge=lfs -text
+assets/tuto_open_hands/app_ui.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,404 @@
+---
+language:
+- en
+- fr
+- de
+- es
+- pt
+- it
+- ja
+- ko
+- ru
+- zh
+- ar
+- fa
+- id
+- ms
+- ne
+- pl
+- ro
+- sr
+- sv
+- tr
+- uk
+- vi
+- hi
+- bn
+license: apache-2.0
+library_name: vllm
+inference: false
+base_model:
+- mistralai/Devstrall-Small-2505
+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>.
+pipeline_tag: text2text-generation
+---
+
+# Devstral-Small-2505
+
+Devstral is an agentic LLM for software engineering tasks built under a collaboration between [Mistral AI](https://mistral.ai/) and [All Hands AI](https://www.all-hands.dev/) 🙌. Devstral excels at using tools to explore codebases, editing multiple files and power software engineering agents. The model achieves remarkable performance on SWE-bench which positionates it as the #1 open source model on this [benchmark](#benchmark-results). 
+
+It is finetuned from [Mistral-Small-3.1](https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Base-2503), therefore it has a long context window of up to 128k tokens. As a coding agent, Devstral is text-only and before fine-tuning from `Mistral-Small-3.1` the vision encoder was removed.
+
+For enterprises requiring specialized capabilities (increased context, domain-specific knowledge, etc.), we will release commercial models beyond what Mistral AI contributes to the community.
+
+Learn more about Devstral in our [blog post](https://mistral.ai/news/devstral).
+
+
+## Key Features:
+- **Agentic coding**: Devstral is designed to excel at agentic coding tasks, making it a great choice for software engineering agents.
+- **lightweight**: with its compact size of just 24 billion parameters, Devstral is light enough to run on a single RTX 4090 or a Mac with 32GB RAM, making it an appropriate model for local deployment and on-device use.
+- **Apache 2.0 License**: Open license allowing usage and modification for both commercial and non-commercial purposes.
+- **Context Window**: A 128k context window.
+- **Tokenizer**: Utilizes a Tekken tokenizer with a 131k vocabulary size.
+
+
+
+## Benchmark Results
+
+### SWE-Bench
+
+Devstral achieves a score of 46.8% on SWE-Bench Verified, outperforming prior open-source SoTA by 6%.
+
+| Model            | Scaffold           | SWE-Bench Verified (%) |
+|------------------|--------------------|------------------------|
+| Devstral         | OpenHands Scaffold | **46.8**               |
+| GPT-4.1-mini     | OpenAI Scaffold    | 23.6                   |
+| Claude 3.5 Haiku | Anthropic Scaffold | 40.6                   |
+| SWE-smith-LM 32B | SWE-agent Scaffold | 40.2                   |
+
+
+ When evaluated under the same test scaffold (OpenHands, provided by All Hands AI 🙌), Devstral exceeds far larger models such as Deepseek-V3-0324 and Qwen3 232B-A22B.
+
+![SWE Benchmark](assets/swe_bench.png)
+
+## Usage
+
+We recommend to use Devstral with the [OpenHands](https://github.com/All-Hands-AI/OpenHands/tree/main) scaffold.
+You can use it either through our API or by running locally. 
+
+### API 
+Follow these [instructions](https://docs.mistral.ai/getting-started/quickstart/#account-setup) to create a Mistral account and get an API key.
+
+Then run these commands to start the OpenHands docker container.
+```bash
+export MISTRAL_API_KEY=<MY_KEY>
+
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.39-nikolaik
+
+mkdir -p ~/.openhands-state && echo '{"language":"en","agent":"CodeActAgent","max_iterations":null,"security_analyzer":null,"confirmation_mode":false,"llm_model":"mistral/devstral-small-2505","llm_api_key":"'$MISTRAL_API_KEY'","remote_runtime_resource_factor":null,"github_token":null,"enable_default_condenser":true}' > ~/.openhands-state/settings.json
+
+docker run -it --rm --pull=always \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.39-nikolaik \
+    -e LOG_ALL_EVENTS=true \
+    -v /var/run/docker.sock:/var/run/docker.sock \
+    -v ~/.openhands-state:/.openhands-state \
+    -p 3000:3000 \
+    --add-host host.docker.internal:host-gateway \
+    --name openhands-app \
+    docker.all-hands.dev/all-hands-ai/openhands:0.39
+```
+
+### Local inference 
+
+The model can also be deployed with the following libraries:
+- [`vllm (recommended)`](https://github.com/vllm-project/vllm): See [here](#vllm-recommended)
+- [`mistral-inference`](https://github.com/mistralai/mistral-inference): See [here](#mistral-inference)
+- [`transformers`](https://github.com/huggingface/transformers): See [here](#transformers)
+- [`LMStudio`](https://lmstudio.ai/): See [here](#lmstudio)
+- [`ollama`](https://github.com/ollama/ollama): See [here](#ollama)
+
+
+### OpenHands (recommended)
+
+#### Launch a server to deploy Devstral-Small-2505
+
+Make sure you launched an OpenAI-compatible server such as vLLM or Ollama as described above. Then, you can use OpenHands to interact with `Devstral-Small-2505`.
+
+In the case of the tutorial we spineed up a vLLM server running the command:
+```bash
+vllm serve mistralai/Devstral-Small-2505 --tokenizer_mode mistral --config_format mistral --load_format mistral --tool-call-parser mistral --enable-auto-tool-choice --tensor-parallel-size 2
+```
+
+The server address should be in the following format: `http://<your-server-url>:8000/v1`
+
+#### Launch OpenHands
+
+You can follow installation of OpenHands [here](https://docs.all-hands.dev/modules/usage/installation).
+
+The easiest way to launch OpenHands is to use the Docker image:
+```bash
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.38-nikolaik
+
+docker run -it --rm --pull=always \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.38-nikolaik \
+    -e LOG_ALL_EVENTS=true \
+    -v /var/run/docker.sock:/var/run/docker.sock \
+    -v ~/.openhands-state:/.openhands-state \
+    -p 3000:3000 \
+    --add-host host.docker.internal:host-gateway \
+    --name openhands-app \
+    docker.all-hands.dev/all-hands-ai/openhands:0.38
+```
+
+
+Then, you can access the OpenHands UI at `http://localhost:3000`.
+
+#### Connect to the server
+
+When accessing the OpenHands UI, you will be prompted to connect to a server. You can use the advanced mode to connect to the server you launched earlier.
+
+Fill the following fields:
+- **Custom Model**: `openai/mistralai/Devstral-Small-2505`
+- **Base URL**: `http://<your-server-url>:8000/v1`
+- **API Key**: `token` (or any other token you used to launch the server if any)
+
+#### Use OpenHands powered by Devstral
+
+Now you're good to use Devstral Small inside OpenHands by **starting a new conversation**. Let's build a To-Do list app.
+
+<details>
+  <summary>To-Do list app</summary
+
+1. Let's ask Devstral to generate the app with the following prompt:
+
+```txt
+Build a To-Do list app with the following requirements:
+- Built using FastAPI and React.
+- Make it a one page app that:
+   - Allows to add a task.
+   - Allows to delete a task.
+   - Allows to mark a task as done.
+   - Displays the list of tasks.
+- Store the tasks in a SQLite database.
+```
+
+![Agent prompting](assets/tuto_open_hands/agent_prompting.png)
+
+
+2. Let's see the result
+
+You should see the agent construct the app and be able to explore the code it generated.
+
+If it doesn't do it automatically, ask Devstral to deploy the app or do it manually, and then go the front URL deployment to see the app.
+
+![Agent working](assets/tuto_open_hands/agent_working.png)
+![App UI](assets/tuto_open_hands/app_ui.png)
+
+
+3. Iterate
+
+Now that you have a first result you can iterate on it by asking your agent to improve it. For example, in the app generated we could click on a task to mark it checked but having a checkbox would improve UX. You could also ask it to add a feature to edit a task, or to add a feature to filter the tasks by status.
+
+Enjoy building with Devstral Small and OpenHands!
+
+</details>
+
+
+### vLLM (recommended)
+
+We recommend using this model with the [vLLM library](https://github.com/vllm-project/vllm)
+to implement production-ready inference pipelines.
+
+**_Installation_**
+
+Make sure you install [`vLLM >= 0.8.5`](https://github.com/vllm-project/vllm/releases/tag/v0.8.5):
+
+```
+pip install vllm --upgrade
+```
+
+Doing so should automatically install [`mistral_common >= 1.5.5`](https://github.com/mistralai/mistral-common/releases/tag/v1.5.5).
+
+To check:
+```
+python -c "import mistral_common; print(mistral_common.__version__)"
+```
+
+You can also make use of a ready-to-go [docker image](https://github.com/vllm-project/vllm/blob/main/Dockerfile) or on the [docker hub](https://hub.docker.com/layers/vllm/vllm-openai/latest/images/sha256-de9032a92ffea7b5c007dad80b38fd44aac11eddc31c435f8e52f3b7404bbf39).
+
+#### Server
+
+We recommand that you use Devstral in a server/client setting. 
+
+1. Spin up a server:
+
+```
+vllm serve mistralai/Devstral-Small-2505 --tokenizer_mode mistral --config_format mistral --load_format mistral --tool-call-parser mistral --enable-auto-tool-choice --tensor-parallel-size 2
+```
+
+
+2. To ping the client you can use a simple Python snippet.
+
+```py
+import requests
+import json
+from huggingface_hub import hf_hub_download
+
+
+url = "http://<your-server-url>:8000/v1/chat/completions"
+headers = {"Content-Type": "application/json", "Authorization": "Bearer token"}
+
+model = "mistralai/Devstral-Small-2505"
+
+def load_system_prompt(repo_id: str, filename: str) -> str:
+    file_path = hf_hub_download(repo_id=repo_id, filename=filename)
+    with open(file_path, "r") as file:
+        system_prompt = file.read()
+    return system_prompt
+
+SYSTEM_PROMPT = load_system_prompt(model, "SYSTEM_PROMPT.txt")
+
+messages = [
+    {"role": "system", "content": SYSTEM_PROMPT},
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "text",
+                "text": "<your-command>",
+            },
+        ],
+    },
+]
+
+data = {"model": model, "messages": messages, "temperature": 0.15}
+
+response = requests.post(url, headers=headers, data=json.dumps(data))
+print(response.json()["choices"][0]["message"]["content"])
+```
+
+### Mistral-inference
+
+We recommend using mistral-inference to quickly try out / "vibe-check" Devstral.
+
+#### Install
+
+Make sure to have mistral_inference >= 1.6.0 installed.
+
+```bash
+pip install mistral_inference --upgrade
+```
+
+#### Download
+
+```python
+from huggingface_hub import snapshot_download
+from pathlib import Path
+
+mistral_models_path = Path.home().joinpath('mistral_models', 'Devstral')
+mistral_models_path.mkdir(parents=True, exist_ok=True)
+
+snapshot_download(repo_id="mistralai/Devstral-Small-2505", allow_patterns=["params.json", "consolidated.safetensors", "tekken.json"], local_dir=mistral_models_path)
+```
+
+#### Python
+
+You can run the model using the following command:
+
+```bash
+mistral-chat $HOME/mistral_models/Devstral --instruct --max_tokens 300
+```
+
+You can then prompt it with anything you'd like.
+
+### Transformers
+
+To make the best use of our model with transformers make sure to have [installed](https://github.com/mistralai/mistral-common) `    mistral-common >= 1.5.5` to use our tokenizer.
+
+```bash
+pip install mistral-common --upgrade
+```
+
+Then load our tokenizer along with the model and generate:
+
+```python
+import torch
+
+from mistral_common.protocol.instruct.messages import (
+    SystemMessage, UserMessage
+)
+from mistral_common.protocol.instruct.request import ChatCompletionRequest
+from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
+from mistral_common.tokens.tokenizers.tekken import SpecialTokenPolicy
+from huggingface_hub import hf_hub_download
+from transformers import AutoModelForCausalLM
+
+def load_system_prompt(repo_id: str, filename: str) -> str:
+    file_path = hf_hub_download(repo_id=repo_id, filename=filename)
+    with open(file_path, "r") as file:
+        system_prompt = file.read()
+    return system_prompt
+
+model_id = "mistralai/Devstral-Small-2505"
+tekken_file = hf_hub_download(repo_id=model_id, filename="tekken.json")
+SYSTEM_PROMPT = load_system_prompt(model_id, "SYSTEM_PROMPT.txt")
+
+tokenizer = MistralTokenizer.from_file(tekken_file)
+
+model = AutoModelForCausalLM.from_pretrained(model_id)
+
+tokenized = tokenizer.encode_chat_completion(
+    ChatCompletionRequest(
+        messages=[
+            SystemMessage(content=SYSTEM_PROMPT),
+            UserMessage(content="<your-command>"),
+        ],
+    )
+)
+
+output = model.generate(
+    input_ids=torch.tensor([tokenized.tokens]),
+    max_new_tokens=1000,
+)[0]
+
+decoded_output = tokenizer.decode(output[len(tokenized.tokens):])
+print(decoded_output)
+```
+
+### LMStudio
+Download the weights from huggingface:
+
+```
+pip install -U "huggingface_hub[cli]"
+huggingface-cli download \
+"mistralai/Devstral-Small-2505_gguf" \
+--include "devstralQ4_K_M.gguf" \
+--local-dir "mistralai/Devstral-Small-2505_gguf/"
+```
+
+You can serve the model locally with [LMStudio](https://lmstudio.ai/).
+* Download [LM Studio](https://lmstudio.ai/) and install it
+* Install `lms cli ~/.lmstudio/bin/lms bootstrap`
+* In a bash terminal, run `lms import devstralQ4_K_M.gguf` in the directory where you've downloaded the model checkpoint (e.g. `mistralai/Devstral-Small-2505_gguf`)
+* Open the LMStudio application, click the terminal icon to get into the developer tab. Click select a model to load and select Devstral Q4 K M. Toggle the status button to start the model, in setting toggle Serve on Local Network to be on.
+* On the right tab, you will see an API identifier which should be devstralq4_k_m and an api address under API Usage. Keep note of this address, we will use it in the next step.
+
+Launch Openhands
+You can now interact with the model served from LM Studio with openhands. Start the openhands server with the docker
+
+```bash
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.38-nikolaik
+docker run -it --rm --pull=always \
+	-e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.38-nikolaik \
+	-e LOG_ALL_EVENTS=true \
+	-v /var/run/docker.sock:/var/run/docker.sock \
+	-v ~/.openhands-state:/.openhands-state \
+	-p 3000:3000 \
+	--add-host host.docker.internal:host-gateway \
+	--name openhands-app \
+	docker.all-hands.dev/all-hands-ai/openhands:0.38
+```
+
+Click “see advanced setting” on the second line. 
+In the new tab, toggle advanced to on. Set the custom model to be mistral/devstralq4_k_m and Base URL the api address we get from the last step in LM Studio. Set API Key to dummy. Click save changes.
+
+
+### Ollama
+
+You can run Devstral using the [Ollama](https://ollama.ai/) CLI.
+
+```bash
+ollama run devstral
+```

SYSTEM_PROMPT.txt

@@ -0,0 +1,73 @@
+You are Devstral, a helpful agentic model trained by Mistral AI and using the OpenHands scaffold. You can interact with a computer to solve tasks.
+
+<ROLE>
+Your primary role is to assist users by executing commands, modifying code, and solving technical problems effectively. You should be thorough, methodical, and prioritize quality over speed.
+* If the user asks a question, like "why is X happening", don't try to fix the problem. Just give an answer to the question.
+</ROLE>
+
+<EFFICIENCY>
+* Each action you take is somewhat expensive. Wherever possible, combine multiple actions into a single action, e.g. combine multiple bash commands into one, using sed and grep to edit/view multiple files at once.
+* When exploring the codebase, use efficient tools like find, grep, and git commands with appropriate filters to minimize unnecessary operations.
+</EFFICIENCY>
+
+<FILE_SYSTEM_GUIDELINES>
+* When a user provides a file path, do NOT assume it's relative to the current working directory. First explore the file system to locate the file before working on it.
+* If asked to edit a file, edit the file directly, rather than creating a new file with a different filename.
+* For global search-and-replace operations, consider using `sed` instead of opening file editors multiple times.
+</FILE_SYSTEM_GUIDELINES>
+
+<CODE_QUALITY>
+* Write clean, efficient code with minimal comments. Avoid redundancy in comments: Do not repeat information that can be easily inferred from the code itself.
+* When implementing solutions, focus on making the minimal changes needed to solve the problem.
+* Before implementing any changes, first thoroughly understand the codebase through exploration.
+* If you are adding a lot of code to a function or file, consider splitting the function or file into smaller pieces when appropriate.
+</CODE_QUALITY>
+
+<VERSION_CONTROL>
+* When configuring git credentials, use "openhands" as the user.name and "[email protected]" as the user.email by default, unless explicitly instructed otherwise.
+* Exercise caution with git operations. Do NOT make potentially dangerous changes (e.g., pushing to main, deleting repositories) unless explicitly asked to do so.
+* When committing changes, use `git status` to see all modified files, and stage all files necessary for the commit. Use `git commit -a` whenever possible.
+* Do NOT commit files that typically shouldn't go into version control (e.g., node_modules/, .env files, build directories, cache files, large binaries) unless explicitly instructed by the user.
+* If unsure about committing certain files, check for the presence of .gitignore files or ask the user for clarification.
+</VERSION_CONTROL>
+
+<PULL_REQUESTS>
+* When creating pull requests, create only ONE per session/issue unless explicitly instructed otherwise.
+* When working with an existing PR, update it with new commits rather than creating additional PRs for the same issue.
+* When updating a PR, preserve the original PR title and purpose, updating description only when necessary.
+</PULL_REQUESTS>
+
+<PROBLEM_SOLVING_WORKFLOW>
+1. EXPLORATION: Thoroughly explore relevant files and understand the context before proposing solutions
+2. ANALYSIS: Consider multiple approaches and select the most promising one
+3. TESTING:
+   * For bug fixes: Create tests to verify issues before implementing fixes
+   * For new features: Consider test-driven development when appropriate
+   * If the repository lacks testing infrastructure and implementing tests would require extensive setup, consult with the user before investing time in building testing infrastructure
+   * If the environment is not set up to run tests, consult with the user first before investing time to install all dependencies
+4. IMPLEMENTATION: Make focused, minimal changes to address the problem
+5. VERIFICATION: If the environment is set up to run tests, test your implementation thoroughly, including edge cases. If the environment is not set up to run tests, consult with the user first before investing time to run tests.
+</PROBLEM_SOLVING_WORKFLOW>
+
+<SECURITY>
+* Only use GITHUB_TOKEN and other credentials in ways the user has explicitly requested and would expect.
+* Use APIs to work with GitHub or other platforms, unless the user asks otherwise or your task requires browsing.
+</SECURITY>
+
+<ENVIRONMENT_SETUP>
+* When user asks you to run an application, don't stop if the application is not installed. Instead, please install the application and run the command again.
+* If you encounter missing dependencies:
+  1. First, look around in the repository for existing dependency files (requirements.txt, pyproject.toml, package.json, Gemfile, etc.)
+  2. If dependency files exist, use them to install all dependencies at once (e.g., `pip install -r requirements.txt`, `npm install`, etc.)
+  3. Only install individual packages directly if no dependency files are found or if only specific packages are needed
+* Similarly, if you encounter missing dependencies for essential tools requested by the user, install them when possible.
+</ENVIRONMENT_SETUP>
+
+<TROUBLESHOOTING>
+* If you've made repeated attempts to solve a problem but tests still fail or the user reports it's still broken:
+  1. Step back and reflect on 5-7 different possible sources of the problem
+  2. Assess the likelihood of each possible cause
+  3. Methodically address the most likely causes, starting with the highest probability
+  4. Document your reasoning process
+* When you run into any major issue while executing a plan from the user, please don't try to directly work around it. Instead, propose a new plan and confirm with the user before proceeding.
+</TROUBLESHOOTING>

config.json

@@ -0,0 +1,37 @@
+{
+    "architectures": [
+        "MistralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 32768,
+    "max_position_embeddings": 131072,
+    "model_type": "mistral",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000000.0,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.51.3",
+    "use_cache": true,
+    "vocab_size": 131072,
+    "quantization_config": {
+        "quant_method": "exl3",
+        "version": "0.0.2",
+        "bits": 8.0,
+        "head_bits": 8,
+        "calibration": {
+            "rows": 100,
+            "cols": 2048
+        },
+        "out_scales": "auto"
+    }
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.51.3"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbf64c9bd5e3903a93ca632fdf45e5a74527b48e80fb7d5eb4dd34489ba8ccfa
+size 8570919408

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da545bdccfb97d704ec2b232d93ca541a1a44aa6e4e30640393a5987fe769d18
+size 8340854880

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30c7747ea0954d3aa817b33e086535fe8323865c4b3368631a0810339c6e4d0f
+size 7344055520

model.safetensors.index.json

@@ -0,0 +1,932 @@
+{
+    "metadata": {
+        "total_size": 24255729664
+    },
+    "weight_map": {
+        "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.0.mlp.down_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.0.mlp.down_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.0.mlp.gate_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.0.mlp.gate_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.0.mlp.up_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.0.mlp.up_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.k_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.k_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.o_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.o_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.q_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.q_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.v_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.v_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.0.mlp.down_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.0.mlp.gate_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.0.mlp.up_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.k_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.o_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.q_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.v_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.1.mlp.down_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.1.mlp.down_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.1.mlp.gate_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.1.mlp.gate_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.1.mlp.up_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.1.mlp.up_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.k_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.k_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.o_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.o_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.q_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.q_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.v_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.v_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.1.mlp.down_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.1.mlp.gate_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.1.mlp.up_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.k_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.o_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.q_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.v_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.2.mlp.down_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.2.mlp.down_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.2.mlp.gate_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.2.mlp.gate_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.2.mlp.up_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.2.mlp.up_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.k_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.k_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.o_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.o_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.q_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.q_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.v_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.v_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.2.mlp.down_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.2.mlp.gate_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.2.mlp.up_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.k_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.o_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.q_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.v_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.3.mlp.down_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.3.mlp.down_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.3.mlp.gate_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.3.mlp.gate_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.3.mlp.up_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.3.mlp.up_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.k_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.k_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.o_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.o_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.q_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.q_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.v_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.v_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.3.mlp.down_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.3.mlp.gate_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.3.mlp.up_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.k_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.o_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.q_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.v_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.4.mlp.down_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.4.mlp.down_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.4.mlp.gate_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.4.mlp.gate_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.4.mlp.up_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.4.mlp.up_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.k_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.k_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.o_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.o_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.q_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.q_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.v_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.v_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.4.mlp.down_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.4.mlp.gate_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.4.mlp.up_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.k_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.o_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.q_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.v_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.5.mlp.down_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.5.mlp.down_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.5.mlp.gate_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.5.mlp.gate_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.5.mlp.up_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.5.mlp.up_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.k_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.k_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.o_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.o_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.q_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.q_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.v_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.v_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.5.mlp.down_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.5.mlp.gate_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.5.mlp.up_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.k_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.o_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.q_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.v_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.6.mlp.down_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.6.mlp.down_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.6.mlp.gate_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.6.mlp.gate_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.6.mlp.up_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.6.mlp.up_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.k_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.k_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.o_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.o_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.q_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.q_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.v_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.v_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.6.mlp.down_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.6.mlp.gate_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.6.mlp.up_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.k_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.o_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.q_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.v_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.7.mlp.down_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.7.mlp.down_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.7.mlp.gate_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.7.mlp.gate_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.7.mlp.up_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.7.mlp.up_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.k_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.k_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.o_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.o_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.q_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.q_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.v_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.v_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.7.mlp.down_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.7.mlp.gate_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.7.mlp.up_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.k_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.o_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.q_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.v_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.8.mlp.down_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.8.mlp.down_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.8.mlp.gate_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.8.mlp.gate_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.8.mlp.up_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.8.mlp.up_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.k_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.k_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.o_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.o_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.q_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.q_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.v_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.v_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.8.mlp.down_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.8.mlp.gate_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.8.mlp.up_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.k_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.o_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.q_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.v_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.9.mlp.down_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.9.mlp.down_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.9.mlp.gate_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.9.mlp.gate_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.9.mlp.up_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.9.mlp.up_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.k_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.k_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.o_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.o_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.q_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.q_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.v_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.v_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.9.mlp.down_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.9.mlp.gate_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.9.mlp.up_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.k_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.o_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.q_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.v_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.10.mlp.down_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.10.mlp.down_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.10.mlp.gate_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.10.mlp.gate_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.10.mlp.up_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.10.mlp.up_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.k_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.k_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.o_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.o_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.q_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.q_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.v_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.v_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.10.mlp.down_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.10.mlp.gate_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.10.mlp.up_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.k_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.o_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.q_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.v_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.11.mlp.down_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.11.mlp.down_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.11.mlp.gate_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.11.mlp.gate_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.11.mlp.up_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.11.mlp.up_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.k_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.k_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.o_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.o_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.q_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.q_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.v_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.v_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.11.mlp.down_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.11.mlp.gate_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.11.mlp.up_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.k_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.o_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.q_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.v_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.down_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.down_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.gate_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.gate_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.up_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.up_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.k_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.k_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.o_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.o_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.q_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.q_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.v_proj.suh": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.v_proj.svh": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.down_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.gate_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.up_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.k_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.o_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.q_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.v_proj.trellis": "model-00001-of-00003.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.13.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.13.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.13.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.13.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.13.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.13.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.13.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.13.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.13.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.13.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.13.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.13.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.13.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.13.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.13.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.13.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.13.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.13.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.13.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.13.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.13.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.14.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.14.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.14.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.14.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.14.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.14.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.14.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.14.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.14.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.14.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.14.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.14.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.14.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.14.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.14.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.14.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.14.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.14.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.14.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.14.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.14.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.15.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.15.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.15.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.15.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.15.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.15.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.15.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.15.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.15.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.16.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.16.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.16.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.16.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.16.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.16.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.16.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.16.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.16.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.17.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.17.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.17.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.17.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.17.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.17.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.17.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.17.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.17.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.18.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.18.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.18.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.18.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.18.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.18.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.18.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.18.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.19.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.19.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.19.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.19.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.19.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.19.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.19.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.19.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.19.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.20.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.20.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.20.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.20.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.20.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.20.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.20.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.20.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.20.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.21.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.21.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.21.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.21.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.21.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.21.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.21.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.21.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.21.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.22.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.22.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.22.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.22.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.22.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.22.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.22.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.22.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.23.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.23.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.23.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.23.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.23.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.23.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.23.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.23.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.23.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.24.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.24.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.24.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.24.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.24.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.24.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.24.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.24.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.24.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.25.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.25.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.25.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.25.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.25.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.25.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.25.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.25.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.25.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.25.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.25.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.25.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.25.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.25.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.25.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.25.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.25.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.25.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.25.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.25.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.25.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.26.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.26.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.26.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.26.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.26.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.26.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.26.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.26.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.26.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.26.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.26.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.26.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.26.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.26.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.26.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.26.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.26.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.26.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.26.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.26.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.26.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.27.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.27.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.27.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.27.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.27.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.27.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.27.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.27.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.27.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.27.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.27.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.27.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.27.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
+        "model.layers.27.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
+        "model.layers.27.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.27.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.27.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.27.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.27.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.27.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.27.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.28.mlp.down_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.28.mlp.down_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.28.mlp.gate_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.28.mlp.gate_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.28.mlp.up_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.28.mlp.up_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.28.self_attn.k_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.28.self_attn.k_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.28.self_attn.o_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.28.self_attn.o_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.28.self_attn.q_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.28.self_attn.q_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.28.self_attn.v_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.28.self_attn.v_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.28.mlp.down_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.28.mlp.gate_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.28.mlp.up_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.28.self_attn.k_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.28.self_attn.o_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.28.self_attn.q_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.28.self_attn.v_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.29.mlp.down_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.29.mlp.down_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.29.mlp.gate_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.29.mlp.gate_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.29.mlp.up_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.29.mlp.up_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.29.self_attn.k_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.29.self_attn.k_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.29.self_attn.o_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.29.self_attn.o_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.29.self_attn.q_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.29.self_attn.q_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.29.self_attn.v_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.29.self_attn.v_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.29.mlp.down_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.29.mlp.gate_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.29.mlp.up_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.29.self_attn.k_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.29.self_attn.o_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.29.self_attn.q_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.29.self_attn.v_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.30.mlp.down_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.30.mlp.down_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.30.mlp.gate_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.30.mlp.gate_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.30.mlp.up_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.30.mlp.up_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.30.self_attn.k_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.30.self_attn.k_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.30.self_attn.o_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.30.self_attn.o_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.30.self_attn.q_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.30.self_attn.q_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.30.self_attn.v_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.30.self_attn.v_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.30.mlp.down_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.30.mlp.gate_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.30.mlp.up_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.30.self_attn.k_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.30.self_attn.o_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.30.self_attn.q_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.30.self_attn.v_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.31.mlp.down_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.31.mlp.down_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.31.mlp.gate_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.31.mlp.gate_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.31.mlp.up_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.31.mlp.up_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.31.self_attn.k_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.31.self_attn.k_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.31.self_attn.o_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.31.self_attn.o_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.31.self_attn.q_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.31.self_attn.q_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.31.self_attn.v_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.31.self_attn.v_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.31.mlp.down_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.31.mlp.gate_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.31.mlp.up_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.31.self_attn.k_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.31.self_attn.o_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.31.self_attn.q_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.31.self_attn.v_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.32.mlp.down_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.32.mlp.down_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.32.mlp.gate_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.32.mlp.gate_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.32.mlp.up_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.32.mlp.up_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.32.self_attn.k_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.32.self_attn.k_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.32.self_attn.o_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.32.self_attn.o_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.32.self_attn.q_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.32.self_attn.q_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.32.self_attn.v_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.32.self_attn.v_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.32.mlp.down_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.32.mlp.gate_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.32.mlp.up_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.32.self_attn.k_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.32.self_attn.o_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.32.self_attn.q_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.32.self_attn.v_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.33.mlp.down_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.33.mlp.down_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.33.mlp.gate_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.33.mlp.gate_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.33.mlp.up_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.33.mlp.up_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.33.self_attn.k_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.33.self_attn.k_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.33.self_attn.o_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.33.self_attn.o_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.33.self_attn.q_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.33.self_attn.q_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.33.self_attn.v_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.33.self_attn.v_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.33.mlp.down_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.33.mlp.gate_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.33.mlp.up_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.33.self_attn.k_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.33.self_attn.o_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.33.self_attn.q_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.33.self_attn.v_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.34.mlp.down_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.34.mlp.down_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.34.mlp.gate_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.34.mlp.gate_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.34.mlp.up_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.34.mlp.up_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.34.self_attn.k_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.34.self_attn.k_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.34.self_attn.o_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.34.self_attn.o_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.34.self_attn.q_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.34.self_attn.q_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.34.self_attn.v_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.34.self_attn.v_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.34.mlp.down_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.34.mlp.gate_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.34.mlp.up_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.34.self_attn.k_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.34.self_attn.o_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.34.self_attn.q_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.34.self_attn.v_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.35.mlp.down_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.35.mlp.down_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.35.mlp.gate_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.35.mlp.gate_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.35.mlp.up_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.35.mlp.up_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.35.self_attn.k_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.35.self_attn.k_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.35.self_attn.o_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.35.self_attn.o_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.35.self_attn.q_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.35.self_attn.q_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.35.self_attn.v_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.35.self_attn.v_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.35.mlp.down_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.35.mlp.gate_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.35.mlp.up_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.35.self_attn.k_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.35.self_attn.o_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.35.self_attn.q_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.35.self_attn.v_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.36.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.36.mlp.down_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.36.mlp.down_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.36.mlp.gate_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.36.mlp.gate_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.36.mlp.up_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.36.mlp.up_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.36.self_attn.k_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.36.self_attn.k_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.36.self_attn.o_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.36.self_attn.o_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.36.self_attn.q_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.36.self_attn.q_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.36.self_attn.v_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.36.self_attn.v_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.36.mlp.down_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.36.mlp.gate_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.36.mlp.up_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.36.self_attn.k_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.36.self_attn.o_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.36.self_attn.q_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.36.self_attn.v_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.37.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.37.mlp.down_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.37.mlp.down_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.37.mlp.gate_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.37.mlp.gate_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.37.mlp.up_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.37.mlp.up_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.37.self_attn.k_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.37.self_attn.k_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.37.self_attn.o_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.37.self_attn.o_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.37.self_attn.q_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.37.self_attn.q_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.37.self_attn.v_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.37.self_attn.v_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.37.mlp.down_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.37.mlp.gate_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.37.mlp.up_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.37.self_attn.k_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.37.self_attn.o_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.37.self_attn.q_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.37.self_attn.v_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.38.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.38.mlp.down_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.38.mlp.down_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.38.mlp.gate_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.38.mlp.gate_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.38.mlp.up_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.38.mlp.up_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.38.self_attn.k_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.38.self_attn.k_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.38.self_attn.o_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.38.self_attn.o_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.38.self_attn.q_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.38.self_attn.q_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.38.self_attn.v_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.38.self_attn.v_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.38.mlp.down_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.38.mlp.gate_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.38.mlp.up_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.38.self_attn.k_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.38.self_attn.o_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.38.self_attn.q_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.38.self_attn.v_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.39.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.39.mlp.down_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.39.mlp.down_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.39.mlp.gate_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.39.mlp.gate_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.39.mlp.up_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.39.mlp.up_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.39.self_attn.k_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.39.self_attn.k_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.39.self_attn.o_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.39.self_attn.o_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.39.self_attn.q_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.39.self_attn.q_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.39.self_attn.v_proj.suh": "model-00003-of-00003.safetensors",
+        "model.layers.39.self_attn.v_proj.svh": "model-00003-of-00003.safetensors",
+        "model.layers.39.mlp.down_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.39.mlp.gate_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.39.mlp.up_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.39.self_attn.k_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.39.self_attn.o_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.39.self_attn.q_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.layers.39.self_attn.v_proj.trellis": "model-00003-of-00003.safetensors",
+        "model.norm.weight": "model-00003-of-00003.safetensors",
+        "lm_head.suh": "model-00003-of-00003.safetensors",
+        "lm_head.svh": "model-00003-of-00003.safetensors",
+        "lm_head.trellis": "model-00003-of-00003.safetensors"
+    }
+}

params.json

@@ -0,0 +1,12 @@
+{
+  "dim": 5120,
+  "n_layers": 40,
+  "head_dim": 128,
+  "hidden_dim": 32768,
+  "n_heads": 32,
+  "n_kv_heads": 8,
+  "rope_theta": 1000000000.0,
+  "norm_eps": 1e-05,
+  "vocab_size": 131072
+}
+

special_tokens_map.json

@@ -0,0 +1,1032 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>",
+    "[INST]",
+    "[/INST]",
+    "[AVAILABLE_TOOLS]",
+    "[/AVAILABLE_TOOLS]",
+    "[TOOL_RESULTS]",
+    "[/TOOL_RESULTS]",
+    "[TOOL_CALLS]",
+    "[IMG]",
+    "<pad>",
+    "[IMG_BREAK]",
+    "[IMG_END]",
+    "[PREFIX]",
+    "[MIDDLE]",
+    "[SUFFIX]",
+    "[SYSTEM_PROMPT]",
+    "[/SYSTEM_PROMPT]",
+    "[TOOL_CONTENT]",
+    "<SPECIAL_20>",
+    "<SPECIAL_21>",
+    "<SPECIAL_22>",
+    "<SPECIAL_23>",
+    "<SPECIAL_24>",
+    "<SPECIAL_25>",
+    "<SPECIAL_26>",
+    "<SPECIAL_27>",
+    "<SPECIAL_28>",
+    "<SPECIAL_29>",
+    "<SPECIAL_30>",
+    "<SPECIAL_31>",
+    "<SPECIAL_32>",
+    "<SPECIAL_33>",
+    "<SPECIAL_34>",
+    "<SPECIAL_35>",
+    "<SPECIAL_36>",
+    "<SPECIAL_37>",
+    "<SPECIAL_38>",
+    "<SPECIAL_39>",
+    "<SPECIAL_40>",
+    "<SPECIAL_41>",
+    "<SPECIAL_42>",
+    "<SPECIAL_43>",
+    "<SPECIAL_44>",
+    "<SPECIAL_45>",
+    "<SPECIAL_46>",
+    "<SPECIAL_47>",
+    "<SPECIAL_48>",
+    "<SPECIAL_49>",
+    "<SPECIAL_50>",
+    "<SPECIAL_51>",
+    "<SPECIAL_52>",
+    "<SPECIAL_53>",
+    "<SPECIAL_54>",
+    "<SPECIAL_55>",
+    "<SPECIAL_56>",
+    "<SPECIAL_57>",
+    "<SPECIAL_58>",
+    "<SPECIAL_59>",
+    "<SPECIAL_60>",
+    "<SPECIAL_61>",
+    "<SPECIAL_62>",
+    "<SPECIAL_63>",
+    "<SPECIAL_64>",
+    "<SPECIAL_65>",
+    "<SPECIAL_66>",
+    "<SPECIAL_67>",
+    "<SPECIAL_68>",
+    "<SPECIAL_69>",
+    "<SPECIAL_70>",
+    "<SPECIAL_71>",
+    "<SPECIAL_72>",
+    "<SPECIAL_73>",
+    "<SPECIAL_74>",
+    "<SPECIAL_75>",
+    "<SPECIAL_76>",
+    "<SPECIAL_77>",
+    "<SPECIAL_78>",
+    "<SPECIAL_79>",
+    "<SPECIAL_80>",
+    "<SPECIAL_81>",
+    "<SPECIAL_82>",
+    "<SPECIAL_83>",
+    "<SPECIAL_84>",
+    "<SPECIAL_85>",
+    "<SPECIAL_86>",
+    "<SPECIAL_87>",
+    "<SPECIAL_88>",
+    "<SPECIAL_89>",
+    "<SPECIAL_90>",
+    "<SPECIAL_91>",
+    "<SPECIAL_92>",
+    "<SPECIAL_93>",
+    "<SPECIAL_94>",
+    "<SPECIAL_95>",
+    "<SPECIAL_96>",
+    "<SPECIAL_97>",
+    "<SPECIAL_98>",
+    "<SPECIAL_99>",
+    "<SPECIAL_100>",
+    "<SPECIAL_101>",
+    "<SPECIAL_102>",
+    "<SPECIAL_103>",
+    "<SPECIAL_104>",
+    "<SPECIAL_105>",
+    "<SPECIAL_106>",
+    "<SPECIAL_107>",
+    "<SPECIAL_108>",
+    "<SPECIAL_109>",
+    "<SPECIAL_110>",
+    "<SPECIAL_111>",
+    "<SPECIAL_112>",
+    "<SPECIAL_113>",
+    "<SPECIAL_114>",
+    "<SPECIAL_115>",
+    "<SPECIAL_116>",
+    "<SPECIAL_117>",
+    "<SPECIAL_118>",
+    "<SPECIAL_119>",
+    "<SPECIAL_120>",
+    "<SPECIAL_121>",
+    "<SPECIAL_122>",
+    "<SPECIAL_123>",
+    "<SPECIAL_124>",
+    "<SPECIAL_125>",
+    "<SPECIAL_126>",
+    "<SPECIAL_127>",
+    "<SPECIAL_128>",
+    "<SPECIAL_129>",
+    "<SPECIAL_130>",
+    "<SPECIAL_131>",
+    "<SPECIAL_132>",
+    "<SPECIAL_133>",
+    "<SPECIAL_134>",
+    "<SPECIAL_135>",
+    "<SPECIAL_136>",
+    "<SPECIAL_137>",
+    "<SPECIAL_138>",
+    "<SPECIAL_139>",
+    "<SPECIAL_140>",
+    "<SPECIAL_141>",
+    "<SPECIAL_142>",
+    "<SPECIAL_143>",
+    "<SPECIAL_144>",
+    "<SPECIAL_145>",
+    "<SPECIAL_146>",
+    "<SPECIAL_147>",
+    "<SPECIAL_148>",
+    "<SPECIAL_149>",
+    "<SPECIAL_150>",
+    "<SPECIAL_151>",
+    "<SPECIAL_152>",
+    "<SPECIAL_153>",
+    "<SPECIAL_154>",
+    "<SPECIAL_155>",
+    "<SPECIAL_156>",
+    "<SPECIAL_157>",
+    "<SPECIAL_158>",
+    "<SPECIAL_159>",
+    "<SPECIAL_160>",
+    "<SPECIAL_161>",
+    "<SPECIAL_162>",
+    "<SPECIAL_163>",
+    "<SPECIAL_164>",
+    "<SPECIAL_165>",
+    "<SPECIAL_166>",
+    "<SPECIAL_167>",
+    "<SPECIAL_168>",
+    "<SPECIAL_169>",
+    "<SPECIAL_170>",
+    "<SPECIAL_171>",
+    "<SPECIAL_172>",
+    "<SPECIAL_173>",
+    "<SPECIAL_174>",
+    "<SPECIAL_175>",
+    "<SPECIAL_176>",
+    "<SPECIAL_177>",
+    "<SPECIAL_178>",
+    "<SPECIAL_179>",
+    "<SPECIAL_180>",
+    "<SPECIAL_181>",
+    "<SPECIAL_182>",
+    "<SPECIAL_183>",
+    "<SPECIAL_184>",
+    "<SPECIAL_185>",
+    "<SPECIAL_186>",
+    "<SPECIAL_187>",
+    "<SPECIAL_188>",
+    "<SPECIAL_189>",
+    "<SPECIAL_190>",
+    "<SPECIAL_191>",
+    "<SPECIAL_192>",
+    "<SPECIAL_193>",
+    "<SPECIAL_194>",
+    "<SPECIAL_195>",
+    "<SPECIAL_196>",
+    "<SPECIAL_197>",
+    "<SPECIAL_198>",
+    "<SPECIAL_199>",
+    "<SPECIAL_200>",
+    "<SPECIAL_201>",
+    "<SPECIAL_202>",
+    "<SPECIAL_203>",
+    "<SPECIAL_204>",
+    "<SPECIAL_205>",
+    "<SPECIAL_206>",
+    "<SPECIAL_207>",
+    "<SPECIAL_208>",
+    "<SPECIAL_209>",
+    "<SPECIAL_210>",
+    "<SPECIAL_211>",
+    "<SPECIAL_212>",
+    "<SPECIAL_213>",
+    "<SPECIAL_214>",
+    "<SPECIAL_215>",
+    "<SPECIAL_216>",
+    "<SPECIAL_217>",
+    "<SPECIAL_218>",
+    "<SPECIAL_219>",
+    "<SPECIAL_220>",
+    "<SPECIAL_221>",
+    "<SPECIAL_222>",
+    "<SPECIAL_223>",
+    "<SPECIAL_224>",
+    "<SPECIAL_225>",
+    "<SPECIAL_226>",
+    "<SPECIAL_227>",
+    "<SPECIAL_228>",
+    "<SPECIAL_229>",
+    "<SPECIAL_230>",
+    "<SPECIAL_231>",
+    "<SPECIAL_232>",
+    "<SPECIAL_233>",
+    "<SPECIAL_234>",
+    "<SPECIAL_235>",
+    "<SPECIAL_236>",
+    "<SPECIAL_237>",
+    "<SPECIAL_238>",
+    "<SPECIAL_239>",
+    "<SPECIAL_240>",
+    "<SPECIAL_241>",
+    "<SPECIAL_242>",
+    "<SPECIAL_243>",
+    "<SPECIAL_244>",
+    "<SPECIAL_245>",
+    "<SPECIAL_246>",
+    "<SPECIAL_247>",
+    "<SPECIAL_248>",
+    "<SPECIAL_249>",
+    "<SPECIAL_250>",
+    "<SPECIAL_251>",
+    "<SPECIAL_252>",
+    "<SPECIAL_253>",
+    "<SPECIAL_254>",
+    "<SPECIAL_255>",
+    "<SPECIAL_256>",
+    "<SPECIAL_257>",
+    "<SPECIAL_258>",
+    "<SPECIAL_259>",
+    "<SPECIAL_260>",
+    "<SPECIAL_261>",
+    "<SPECIAL_262>",
+    "<SPECIAL_263>",
+    "<SPECIAL_264>",
+    "<SPECIAL_265>",
+    "<SPECIAL_266>",
+    "<SPECIAL_267>",
+    "<SPECIAL_268>",
+    "<SPECIAL_269>",
+    "<SPECIAL_270>",
+    "<SPECIAL_271>",
+    "<SPECIAL_272>",
+    "<SPECIAL_273>",
+    "<SPECIAL_274>",
+    "<SPECIAL_275>",
+    "<SPECIAL_276>",
+    "<SPECIAL_277>",
+    "<SPECIAL_278>",
+    "<SPECIAL_279>",
+    "<SPECIAL_280>",
+    "<SPECIAL_281>",
+    "<SPECIAL_282>",
+    "<SPECIAL_283>",
+    "<SPECIAL_284>",
+    "<SPECIAL_285>",
+    "<SPECIAL_286>",
+    "<SPECIAL_287>",
+    "<SPECIAL_288>",
+    "<SPECIAL_289>",
+    "<SPECIAL_290>",
+    "<SPECIAL_291>",
+    "<SPECIAL_292>",
+    "<SPECIAL_293>",
+    "<SPECIAL_294>",
+    "<SPECIAL_295>",
+    "<SPECIAL_296>",
+    "<SPECIAL_297>",
+    "<SPECIAL_298>",
+    "<SPECIAL_299>",
+    "<SPECIAL_300>",
+    "<SPECIAL_301>",
+    "<SPECIAL_302>",
+    "<SPECIAL_303>",
+    "<SPECIAL_304>",
+    "<SPECIAL_305>",
+    "<SPECIAL_306>",
+    "<SPECIAL_307>",
+    "<SPECIAL_308>",
+    "<SPECIAL_309>",
+    "<SPECIAL_310>",
+    "<SPECIAL_311>",
+    "<SPECIAL_312>",
+    "<SPECIAL_313>",
+    "<SPECIAL_314>",
+    "<SPECIAL_315>",
+    "<SPECIAL_316>",
+    "<SPECIAL_317>",
+    "<SPECIAL_318>",
+    "<SPECIAL_319>",
+    "<SPECIAL_320>",
+    "<SPECIAL_321>",
+    "<SPECIAL_322>",
+    "<SPECIAL_323>",
+    "<SPECIAL_324>",
+    "<SPECIAL_325>",
+    "<SPECIAL_326>",
+    "<SPECIAL_327>",
+    "<SPECIAL_328>",
+    "<SPECIAL_329>",
+    "<SPECIAL_330>",
+    "<SPECIAL_331>",
+    "<SPECIAL_332>",
+    "<SPECIAL_333>",
+    "<SPECIAL_334>",
+    "<SPECIAL_335>",
+    "<SPECIAL_336>",
+    "<SPECIAL_337>",
+    "<SPECIAL_338>",
+    "<SPECIAL_339>",
+    "<SPECIAL_340>",
+    "<SPECIAL_341>",
+    "<SPECIAL_342>",
+    "<SPECIAL_343>",
+    "<SPECIAL_344>",
+    "<SPECIAL_345>",
+    "<SPECIAL_346>",
+    "<SPECIAL_347>",
+    "<SPECIAL_348>",
+    "<SPECIAL_349>",
+    "<SPECIAL_350>",
+    "<SPECIAL_351>",
+    "<SPECIAL_352>",
+    "<SPECIAL_353>",
+    "<SPECIAL_354>",
+    "<SPECIAL_355>",
+    "<SPECIAL_356>",
+    "<SPECIAL_357>",
+    "<SPECIAL_358>",
+    "<SPECIAL_359>",
+    "<SPECIAL_360>",
+    "<SPECIAL_361>",
+    "<SPECIAL_362>",
+    "<SPECIAL_363>",
+    "<SPECIAL_364>",
+    "<SPECIAL_365>",
+    "<SPECIAL_366>",
+    "<SPECIAL_367>",
+    "<SPECIAL_368>",
+    "<SPECIAL_369>",
+    "<SPECIAL_370>",
+    "<SPECIAL_371>",
+    "<SPECIAL_372>",
+    "<SPECIAL_373>",
+    "<SPECIAL_374>",
+    "<SPECIAL_375>",
+    "<SPECIAL_376>",
+    "<SPECIAL_377>",
+    "<SPECIAL_378>",
+    "<SPECIAL_379>",
+    "<SPECIAL_380>",
+    "<SPECIAL_381>",
+    "<SPECIAL_382>",
+    "<SPECIAL_383>",
+    "<SPECIAL_384>",
+    "<SPECIAL_385>",
+    "<SPECIAL_386>",
+    "<SPECIAL_387>",
+    "<SPECIAL_388>",
+    "<SPECIAL_389>",
+    "<SPECIAL_390>",
+    "<SPECIAL_391>",
+    "<SPECIAL_392>",
+    "<SPECIAL_393>",
+    "<SPECIAL_394>",
+    "<SPECIAL_395>",
+    "<SPECIAL_396>",
+    "<SPECIAL_397>",
+    "<SPECIAL_398>",
+    "<SPECIAL_399>",
+    "<SPECIAL_400>",
+    "<SPECIAL_401>",
+    "<SPECIAL_402>",
+    "<SPECIAL_403>",
+    "<SPECIAL_404>",
+    "<SPECIAL_405>",
+    "<SPECIAL_406>",
+    "<SPECIAL_407>",
+    "<SPECIAL_408>",
+    "<SPECIAL_409>",
+    "<SPECIAL_410>",
+    "<SPECIAL_411>",
+    "<SPECIAL_412>",
+    "<SPECIAL_413>",
+    "<SPECIAL_414>",
+    "<SPECIAL_415>",
+    "<SPECIAL_416>",
+    "<SPECIAL_417>",
+    "<SPECIAL_418>",
+    "<SPECIAL_419>",
+    "<SPECIAL_420>",
+    "<SPECIAL_421>",
+    "<SPECIAL_422>",
+    "<SPECIAL_423>",
+    "<SPECIAL_424>",
+    "<SPECIAL_425>",
+    "<SPECIAL_426>",
+    "<SPECIAL_427>",
+    "<SPECIAL_428>",
+    "<SPECIAL_429>",
+    "<SPECIAL_430>",
+    "<SPECIAL_431>",
+    "<SPECIAL_432>",
+    "<SPECIAL_433>",
+    "<SPECIAL_434>",
+    "<SPECIAL_435>",
+    "<SPECIAL_436>",
+    "<SPECIAL_437>",
+    "<SPECIAL_438>",
+    "<SPECIAL_439>",
+    "<SPECIAL_440>",
+    "<SPECIAL_441>",
+    "<SPECIAL_442>",
+    "<SPECIAL_443>",
+    "<SPECIAL_444>",
+    "<SPECIAL_445>",
+    "<SPECIAL_446>",
+    "<SPECIAL_447>",
+    "<SPECIAL_448>",
+    "<SPECIAL_449>",
+    "<SPECIAL_450>",
+    "<SPECIAL_451>",
+    "<SPECIAL_452>",
+    "<SPECIAL_453>",
+    "<SPECIAL_454>",
+    "<SPECIAL_455>",
+    "<SPECIAL_456>",
+    "<SPECIAL_457>",
+    "<SPECIAL_458>",
+    "<SPECIAL_459>",
+    "<SPECIAL_460>",
+    "<SPECIAL_461>",
+    "<SPECIAL_462>",
+    "<SPECIAL_463>",
+    "<SPECIAL_464>",
+    "<SPECIAL_465>",
+    "<SPECIAL_466>",
+    "<SPECIAL_467>",
+    "<SPECIAL_468>",
+    "<SPECIAL_469>",
+    "<SPECIAL_470>",
+    "<SPECIAL_471>",
+    "<SPECIAL_472>",
+    "<SPECIAL_473>",
+    "<SPECIAL_474>",
+    "<SPECIAL_475>",
+    "<SPECIAL_476>",
+    "<SPECIAL_477>",
+    "<SPECIAL_478>",
+    "<SPECIAL_479>",
+    "<SPECIAL_480>",
+    "<SPECIAL_481>",
+    "<SPECIAL_482>",
+    "<SPECIAL_483>",
+    "<SPECIAL_484>",
+    "<SPECIAL_485>",
+    "<SPECIAL_486>",
+    "<SPECIAL_487>",
+    "<SPECIAL_488>",
+    "<SPECIAL_489>",
+    "<SPECIAL_490>",
+    "<SPECIAL_491>",
+    "<SPECIAL_492>",
+    "<SPECIAL_493>",
+    "<SPECIAL_494>",
+    "<SPECIAL_495>",
+    "<SPECIAL_496>",
+    "<SPECIAL_497>",
+    "<SPECIAL_498>",
+    "<SPECIAL_499>",
+    "<SPECIAL_500>",
+    "<SPECIAL_501>",
+    "<SPECIAL_502>",
+    "<SPECIAL_503>",
+    "<SPECIAL_504>",
+    "<SPECIAL_505>",
+    "<SPECIAL_506>",
+    "<SPECIAL_507>",
+    "<SPECIAL_508>",
+    "<SPECIAL_509>",
+    "<SPECIAL_510>",
+    "<SPECIAL_511>",
+    "<SPECIAL_512>",
+    "<SPECIAL_513>",
+    "<SPECIAL_514>",
+    "<SPECIAL_515>",
+    "<SPECIAL_516>",
+    "<SPECIAL_517>",
+    "<SPECIAL_518>",
+    "<SPECIAL_519>",
+    "<SPECIAL_520>",
+    "<SPECIAL_521>",
+    "<SPECIAL_522>",
+    "<SPECIAL_523>",
+    "<SPECIAL_524>",
+    "<SPECIAL_525>",
+    "<SPECIAL_526>",
+    "<SPECIAL_527>",
+    "<SPECIAL_528>",
+    "<SPECIAL_529>",
+    "<SPECIAL_530>",
+    "<SPECIAL_531>",
+    "<SPECIAL_532>",
+    "<SPECIAL_533>",
+    "<SPECIAL_534>",
+    "<SPECIAL_535>",
+    "<SPECIAL_536>",
+    "<SPECIAL_537>",
+    "<SPECIAL_538>",
+    "<SPECIAL_539>",
+    "<SPECIAL_540>",
+    "<SPECIAL_541>",
+    "<SPECIAL_542>",
+    "<SPECIAL_543>",
+    "<SPECIAL_544>",
+    "<SPECIAL_545>",
+    "<SPECIAL_546>",
+    "<SPECIAL_547>",
+    "<SPECIAL_548>",
+    "<SPECIAL_549>",
+    "<SPECIAL_550>",
+    "<SPECIAL_551>",
+    "<SPECIAL_552>",
+    "<SPECIAL_553>",
+    "<SPECIAL_554>",
+    "<SPECIAL_555>",
+    "<SPECIAL_556>",
+    "<SPECIAL_557>",
+    "<SPECIAL_558>",
+    "<SPECIAL_559>",
+    "<SPECIAL_560>",
+    "<SPECIAL_561>",
+    "<SPECIAL_562>",
+    "<SPECIAL_563>",
+    "<SPECIAL_564>",
+    "<SPECIAL_565>",
+    "<SPECIAL_566>",
+    "<SPECIAL_567>",
+    "<SPECIAL_568>",
+    "<SPECIAL_569>",
+    "<SPECIAL_570>",
+    "<SPECIAL_571>",
+    "<SPECIAL_572>",
+    "<SPECIAL_573>",
+    "<SPECIAL_574>",
+    "<SPECIAL_575>",
+    "<SPECIAL_576>",
+    "<SPECIAL_577>",
+    "<SPECIAL_578>",
+    "<SPECIAL_579>",
+    "<SPECIAL_580>",
+    "<SPECIAL_581>",
+    "<SPECIAL_582>",
+    "<SPECIAL_583>",
+    "<SPECIAL_584>",
+    "<SPECIAL_585>",
+    "<SPECIAL_586>",
+    "<SPECIAL_587>",
+    "<SPECIAL_588>",
+    "<SPECIAL_589>",
+    "<SPECIAL_590>",
+    "<SPECIAL_591>",
+    "<SPECIAL_592>",
+    "<SPECIAL_593>",
+    "<SPECIAL_594>",
+    "<SPECIAL_595>",
+    "<SPECIAL_596>",
+    "<SPECIAL_597>",
+    "<SPECIAL_598>",
+    "<SPECIAL_599>",
+    "<SPECIAL_600>",
+    "<SPECIAL_601>",
+    "<SPECIAL_602>",
+    "<SPECIAL_603>",
+    "<SPECIAL_604>",
+    "<SPECIAL_605>",
+    "<SPECIAL_606>",
+    "<SPECIAL_607>",
+    "<SPECIAL_608>",
+    "<SPECIAL_609>",
+    "<SPECIAL_610>",
+    "<SPECIAL_611>",
+    "<SPECIAL_612>",
+    "<SPECIAL_613>",
+    "<SPECIAL_614>",
+    "<SPECIAL_615>",
+    "<SPECIAL_616>",
+    "<SPECIAL_617>",
+    "<SPECIAL_618>",
+    "<SPECIAL_619>",
+    "<SPECIAL_620>",
+    "<SPECIAL_621>",
+    "<SPECIAL_622>",
+    "<SPECIAL_623>",
+    "<SPECIAL_624>",
+    "<SPECIAL_625>",
+    "<SPECIAL_626>",
+    "<SPECIAL_627>",
+    "<SPECIAL_628>",
+    "<SPECIAL_629>",
+    "<SPECIAL_630>",
+    "<SPECIAL_631>",
+    "<SPECIAL_632>",
+    "<SPECIAL_633>",
+    "<SPECIAL_634>",
+    "<SPECIAL_635>",
+    "<SPECIAL_636>",
+    "<SPECIAL_637>",
+    "<SPECIAL_638>",
+    "<SPECIAL_639>",
+    "<SPECIAL_640>",
+    "<SPECIAL_641>",
+    "<SPECIAL_642>",
+    "<SPECIAL_643>",
+    "<SPECIAL_644>",
+    "<SPECIAL_645>",
+    "<SPECIAL_646>",
+    "<SPECIAL_647>",
+    "<SPECIAL_648>",
+    "<SPECIAL_649>",
+    "<SPECIAL_650>",
+    "<SPECIAL_651>",
+    "<SPECIAL_652>",
+    "<SPECIAL_653>",
+    "<SPECIAL_654>",
+    "<SPECIAL_655>",
+    "<SPECIAL_656>",
+    "<SPECIAL_657>",
+    "<SPECIAL_658>",
+    "<SPECIAL_659>",
+    "<SPECIAL_660>",
+    "<SPECIAL_661>",
+    "<SPECIAL_662>",
+    "<SPECIAL_663>",
+    "<SPECIAL_664>",
+    "<SPECIAL_665>",
+    "<SPECIAL_666>",
+    "<SPECIAL_667>",
+    "<SPECIAL_668>",
+    "<SPECIAL_669>",
+    "<SPECIAL_670>",
+    "<SPECIAL_671>",
+    "<SPECIAL_672>",
+    "<SPECIAL_673>",
+    "<SPECIAL_674>",
+    "<SPECIAL_675>",
+    "<SPECIAL_676>",
+    "<SPECIAL_677>",
+    "<SPECIAL_678>",
+    "<SPECIAL_679>",
+    "<SPECIAL_680>",
+    "<SPECIAL_681>",
+    "<SPECIAL_682>",
+    "<SPECIAL_683>",
+    "<SPECIAL_684>",
+    "<SPECIAL_685>",
+    "<SPECIAL_686>",
+    "<SPECIAL_687>",
+    "<SPECIAL_688>",
+    "<SPECIAL_689>",
+    "<SPECIAL_690>",
+    "<SPECIAL_691>",
+    "<SPECIAL_692>",
+    "<SPECIAL_693>",
+    "<SPECIAL_694>",
+    "<SPECIAL_695>",
+    "<SPECIAL_696>",
+    "<SPECIAL_697>",
+    "<SPECIAL_698>",
+    "<SPECIAL_699>",
+    "<SPECIAL_700>",
+    "<SPECIAL_701>",
+    "<SPECIAL_702>",
+    "<SPECIAL_703>",
+    "<SPECIAL_704>",
+    "<SPECIAL_705>",
+    "<SPECIAL_706>",
+    "<SPECIAL_707>",
+    "<SPECIAL_708>",
+    "<SPECIAL_709>",
+    "<SPECIAL_710>",
+    "<SPECIAL_711>",
+    "<SPECIAL_712>",
+    "<SPECIAL_713>",
+    "<SPECIAL_714>",
+    "<SPECIAL_715>",
+    "<SPECIAL_716>",
+    "<SPECIAL_717>",
+    "<SPECIAL_718>",
+    "<SPECIAL_719>",
+    "<SPECIAL_720>",
+    "<SPECIAL_721>",
+    "<SPECIAL_722>",
+    "<SPECIAL_723>",
+    "<SPECIAL_724>",
+    "<SPECIAL_725>",
+    "<SPECIAL_726>",
+    "<SPECIAL_727>",
+    "<SPECIAL_728>",
+    "<SPECIAL_729>",
+    "<SPECIAL_730>",
+    "<SPECIAL_731>",
+    "<SPECIAL_732>",
+    "<SPECIAL_733>",
+    "<SPECIAL_734>",
+    "<SPECIAL_735>",
+    "<SPECIAL_736>",
+    "<SPECIAL_737>",
+    "<SPECIAL_738>",
+    "<SPECIAL_739>",
+    "<SPECIAL_740>",
+    "<SPECIAL_741>",
+    "<SPECIAL_742>",
+    "<SPECIAL_743>",
+    "<SPECIAL_744>",
+    "<SPECIAL_745>",
+    "<SPECIAL_746>",
+    "<SPECIAL_747>",
+    "<SPECIAL_748>",
+    "<SPECIAL_749>",
+    "<SPECIAL_750>",
+    "<SPECIAL_751>",
+    "<SPECIAL_752>",
+    "<SPECIAL_753>",
+    "<SPECIAL_754>",
+    "<SPECIAL_755>",
+    "<SPECIAL_756>",
+    "<SPECIAL_757>",
+    "<SPECIAL_758>",
+    "<SPECIAL_759>",
+    "<SPECIAL_760>",
+    "<SPECIAL_761>",
+    "<SPECIAL_762>",
+    "<SPECIAL_763>",
+    "<SPECIAL_764>",
+    "<SPECIAL_765>",
+    "<SPECIAL_766>",
+    "<SPECIAL_767>",
+    "<SPECIAL_768>",
+    "<SPECIAL_769>",
+    "<SPECIAL_770>",
+    "<SPECIAL_771>",
+    "<SPECIAL_772>",
+    "<SPECIAL_773>",
+    "<SPECIAL_774>",
+    "<SPECIAL_775>",
+    "<SPECIAL_776>",
+    "<SPECIAL_777>",
+    "<SPECIAL_778>",
+    "<SPECIAL_779>",
+    "<SPECIAL_780>",
+    "<SPECIAL_781>",
+    "<SPECIAL_782>",
+    "<SPECIAL_783>",
+    "<SPECIAL_784>",
+    "<SPECIAL_785>",
+    "<SPECIAL_786>",
+    "<SPECIAL_787>",
+    "<SPECIAL_788>",
+    "<SPECIAL_789>",
+    "<SPECIAL_790>",
+    "<SPECIAL_791>",
+    "<SPECIAL_792>",
+    "<SPECIAL_793>",
+    "<SPECIAL_794>",
+    "<SPECIAL_795>",
+    "<SPECIAL_796>",
+    "<SPECIAL_797>",
+    "<SPECIAL_798>",
+    "<SPECIAL_799>",
+    "<SPECIAL_800>",
+    "<SPECIAL_801>",
+    "<SPECIAL_802>",
+    "<SPECIAL_803>",
+    "<SPECIAL_804>",
+    "<SPECIAL_805>",
+    "<SPECIAL_806>",
+    "<SPECIAL_807>",
+    "<SPECIAL_808>",
+    "<SPECIAL_809>",
+    "<SPECIAL_810>",
+    "<SPECIAL_811>",
+    "<SPECIAL_812>",
+    "<SPECIAL_813>",
+    "<SPECIAL_814>",
+    "<SPECIAL_815>",
+    "<SPECIAL_816>",
+    "<SPECIAL_817>",
+    "<SPECIAL_818>",
+    "<SPECIAL_819>",
+    "<SPECIAL_820>",
+    "<SPECIAL_821>",
+    "<SPECIAL_822>",
+    "<SPECIAL_823>",
+    "<SPECIAL_824>",
+    "<SPECIAL_825>",
+    "<SPECIAL_826>",
+    "<SPECIAL_827>",
+    "<SPECIAL_828>",
+    "<SPECIAL_829>",
+    "<SPECIAL_830>",
+    "<SPECIAL_831>",
+    "<SPECIAL_832>",
+    "<SPECIAL_833>",
+    "<SPECIAL_834>",
+    "<SPECIAL_835>",
+    "<SPECIAL_836>",
+    "<SPECIAL_837>",
+    "<SPECIAL_838>",
+    "<SPECIAL_839>",
+    "<SPECIAL_840>",
+    "<SPECIAL_841>",
+    "<SPECIAL_842>",
+    "<SPECIAL_843>",
+    "<SPECIAL_844>",
+    "<SPECIAL_845>",
+    "<SPECIAL_846>",
+    "<SPECIAL_847>",
+    "<SPECIAL_848>",
+    "<SPECIAL_849>",
+    "<SPECIAL_850>",
+    "<SPECIAL_851>",
+    "<SPECIAL_852>",
+    "<SPECIAL_853>",
+    "<SPECIAL_854>",
+    "<SPECIAL_855>",
+    "<SPECIAL_856>",
+    "<SPECIAL_857>",
+    "<SPECIAL_858>",
+    "<SPECIAL_859>",
+    "<SPECIAL_860>",
+    "<SPECIAL_861>",
+    "<SPECIAL_862>",
+    "<SPECIAL_863>",
+    "<SPECIAL_864>",
+    "<SPECIAL_865>",
+    "<SPECIAL_866>",
+    "<SPECIAL_867>",
+    "<SPECIAL_868>",
+    "<SPECIAL_869>",
+    "<SPECIAL_870>",
+    "<SPECIAL_871>",
+    "<SPECIAL_872>",
+    "<SPECIAL_873>",
+    "<SPECIAL_874>",
+    "<SPECIAL_875>",
+    "<SPECIAL_876>",
+    "<SPECIAL_877>",
+    "<SPECIAL_878>",
+    "<SPECIAL_879>",
+    "<SPECIAL_880>",
+    "<SPECIAL_881>",
+    "<SPECIAL_882>",
+    "<SPECIAL_883>",
+    "<SPECIAL_884>",
+    "<SPECIAL_885>",
+    "<SPECIAL_886>",
+    "<SPECIAL_887>",
+    "<SPECIAL_888>",
+    "<SPECIAL_889>",
+    "<SPECIAL_890>",
+    "<SPECIAL_891>",
+    "<SPECIAL_892>",
+    "<SPECIAL_893>",
+    "<SPECIAL_894>",
+    "<SPECIAL_895>",
+    "<SPECIAL_896>",
+    "<SPECIAL_897>",
+    "<SPECIAL_898>",
+    "<SPECIAL_899>",
+    "<SPECIAL_900>",
+    "<SPECIAL_901>",
+    "<SPECIAL_902>",
+    "<SPECIAL_903>",
+    "<SPECIAL_904>",
+    "<SPECIAL_905>",
+    "<SPECIAL_906>",
+    "<SPECIAL_907>",
+    "<SPECIAL_908>",
+    "<SPECIAL_909>",
+    "<SPECIAL_910>",
+    "<SPECIAL_911>",
+    "<SPECIAL_912>",
+    "<SPECIAL_913>",
+    "<SPECIAL_914>",
+    "<SPECIAL_915>",
+    "<SPECIAL_916>",
+    "<SPECIAL_917>",
+    "<SPECIAL_918>",
+    "<SPECIAL_919>",
+    "<SPECIAL_920>",
+    "<SPECIAL_921>",
+    "<SPECIAL_922>",
+    "<SPECIAL_923>",
+    "<SPECIAL_924>",
+    "<SPECIAL_925>",
+    "<SPECIAL_926>",
+    "<SPECIAL_927>",
+    "<SPECIAL_928>",
+    "<SPECIAL_929>",
+    "<SPECIAL_930>",
+    "<SPECIAL_931>",
+    "<SPECIAL_932>",
+    "<SPECIAL_933>",
+    "<SPECIAL_934>",
+    "<SPECIAL_935>",
+    "<SPECIAL_936>",
+    "<SPECIAL_937>",
+    "<SPECIAL_938>",
+    "<SPECIAL_939>",
+    "<SPECIAL_940>",
+    "<SPECIAL_941>",
+    "<SPECIAL_942>",
+    "<SPECIAL_943>",
+    "<SPECIAL_944>",
+    "<SPECIAL_945>",
+    "<SPECIAL_946>",
+    "<SPECIAL_947>",
+    "<SPECIAL_948>",
+    "<SPECIAL_949>",
+    "<SPECIAL_950>",
+    "<SPECIAL_951>",
+    "<SPECIAL_952>",
+    "<SPECIAL_953>",
+    "<SPECIAL_954>",
+    "<SPECIAL_955>",
+    "<SPECIAL_956>",
+    "<SPECIAL_957>",
+    "<SPECIAL_958>",
+    "<SPECIAL_959>",
+    "<SPECIAL_960>",
+    "<SPECIAL_961>",
+    "<SPECIAL_962>",
+    "<SPECIAL_963>",
+    "<SPECIAL_964>",
+    "<SPECIAL_965>",
+    "<SPECIAL_966>",
+    "<SPECIAL_967>",
+    "<SPECIAL_968>",
+    "<SPECIAL_969>",
+    "<SPECIAL_970>",
+    "<SPECIAL_971>",
+    "<SPECIAL_972>",
+    "<SPECIAL_973>",
+    "<SPECIAL_974>",
+    "<SPECIAL_975>",
+    "<SPECIAL_976>",
+    "<SPECIAL_977>",
+    "<SPECIAL_978>",
+    "<SPECIAL_979>",
+    "<SPECIAL_980>",
+    "<SPECIAL_981>",
+    "<SPECIAL_982>",
+    "<SPECIAL_983>",
+    "<SPECIAL_984>",
+    "<SPECIAL_985>",
+    "<SPECIAL_986>",
+    "<SPECIAL_987>",
+    "<SPECIAL_988>",
+    "<SPECIAL_989>",
+    "<SPECIAL_990>",
+    "<SPECIAL_991>",
+    "<SPECIAL_992>",
+    "<SPECIAL_993>",
+    "<SPECIAL_994>",
+    "<SPECIAL_995>",
+    "<SPECIAL_996>",
+    "<SPECIAL_997>",
+    "<SPECIAL_998>",
+    "<SPECIAL_999>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tekken.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4b90a968dbc67ef3975129d0b78a2e3cbb6bea340ab9205f22e8a0308b1ffc5
+size 14801223

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949
+size 17078037