Instructions to use usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit")
model = AutoModelForCausalLM.from_pretrained("usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

MLX

How to use usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

vLLM

How to use usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit

SGLang

How to use usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

How to use usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit with Docker Model Runner:
```
docker model run hf.co/usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit
```

Hermes Agent

How to use usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

usermma commited on Jun 3

Commit

5f1cafa

verified ·

1 Parent(s): 90dfa09

Upload folder using huggingface_hub

Browse files

Files changed (10) hide show

.gitattributes +1 -0
README.md +52 -0
chat_template.jinja +115 -0
config.json +247 -0
generation_config.json +10 -0
model-00001-of-00002.safetensors +3 -0
model-00002-of-00002.safetensors +3 -0
model.safetensors.index.json +574 -0
tokenizer.json +3 -0
tokenizer_config.json +11 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ 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

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md ADDED Viewed

	@@ -0,0 +1,52 @@

+---
+library_name: transformers
+license: other
+license_name: lfm1.0
+license_link: LICENSE
+language:
+- en
+- ar
+- zh
+- fr
+- de
+- ja
+- ko
+- es
+- pt
+pipeline_tag: text-generation
+tags:
+- liquid
+- lfm2.5
+- edge
+- abliterated
+- uncensored
+- mlx
+- mlx-my-repo
+base_model: huihui-ai/Huihui-LFM2.5-8B-A1B-abliterated
+---
+# usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit
+The Model [usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit](https://huggingface.co/usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit) was converted to MLX format from [huihui-ai/Huihui-LFM2.5-8B-A1B-abliterated](https://huggingface.co/huihui-ai/Huihui-LFM2.5-8B-A1B-abliterated) using mlx-lm version **0.31.2**.
+## Use with mlx
+```bash
+pip install mlx-lm
+```
+```python
+from mlx_lm import load, generate
+model, tokenizer = load("usermma/Huihui-LFM2.5-8B-A1B-abliterated-mlx-6Bit")
+prompt="hello"
+if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, tokenize=False, add_generation_prompt=True
+    )
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

chat_template.jinja ADDED Viewed

	@@ -0,0 +1,115 @@

+{{- bos_token -}}
+{%- set preserve_thinking = preserve_thinking | default(false) -%}
+{%- macro format_arg_value(arg_value) -%}
+    {%- if arg_value is string -%}
+        {{- "'" + arg_value + "'" -}}
+    {%- elif arg_value is mapping -%}
+        {{- arg_value | tojson -}}
+    {%- else -%}
+        {{- arg_value | string -}}
+    {%- endif -%}
+{%- endmacro -%}
+{%- macro parse_content(content) -%}
+    {%- if content is string -%}
+        {{- content -}}
+    {%- else -%}
+        {%- set _ns = namespace(result="") -%}
+        {%- for item in content -%}
+            {%- if item["type"] == "image" -%}
+                {%- set _ns.result = _ns.result + "<image>" -%}
+            {%- elif item["type"] == "text" -%}
+                {%- set _ns.result = _ns.result + item["text"] -%}
+            {%- else -%}
+                {%- set _ns.result = _ns.result + item | tojson -%}
+            {%- endif -%}
+        {%- endfor -%}
+        {{- _ns.result -}}
+    {%- endif -%}
+{%- endmacro -%}
+{%- macro render_tool_calls(tool_calls) -%}
+    {%- set tool_calls_ns = namespace(tool_calls=[]) -%}
+    {%- for tool_call in tool_calls -%}
+        {%- set func_name = tool_call["function"]["name"] -%}
+        {%- set func_args = tool_call["function"]["arguments"] -%}
+        {%- set args_ns = namespace(arg_strings=[]) -%}
+        {%- for arg_name, arg_value in func_args.items() -%}
+            {%- set args_ns.arg_strings = args_ns.arg_strings + [arg_name + "=" + format_arg_value(arg_value)] -%}
+        {%- endfor -%}
+        {%- set tool_calls_ns.tool_calls = tool_calls_ns.tool_calls + [func_name + "(" + (args_ns.arg_strings | join(", ")) + ")"] -%}
+    {%- endfor -%}
+    {{- "<|tool_call_start|>[" + (tool_calls_ns.tool_calls | join(", ")) + "]<|tool_call_end|>" -}}
+{%- endmacro -%}
+{%- set ns = namespace(system_prompt="", last_user_index=-1) -%}
+{%- if messages[0]["role"] == "system" -%}
+    {%- if messages[0].get("content") -%}
+        {%- set ns.system_prompt = parse_content(messages[0]["content"]) -%}
+    {%- endif -%}
+    {%- set messages = messages[1:] -%}
+{%- endif -%}
+{%- if tools -%}
+    {%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: [" -%}
+    {%- for tool in tools -%}
+        {%- if tool is not string -%}
+            {%- set tool = tool | tojson -%}
+        {%- endif -%}
+        {%- set ns.system_prompt = ns.system_prompt + tool -%}
+        {%- if not loop.last -%}
+            {%- set ns.system_prompt = ns.system_prompt + ", " -%}
+        {%- endif -%}
+    {%- endfor -%}
+    {%- set ns.system_prompt = ns.system_prompt + "]" -%}
+{%- endif -%}
+{%- if ns.system_prompt -%}
+    {{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
+{%- endif -%}
+{%- for message in messages -%}
+    {%- if message["role"] == "user" -%}
+        {%- set ns.last_user_index = loop.index0 -%}
+    {%- endif -%}
+{%- endfor -%}
+{%- for message in messages -%}
+    {{- "<|im_start|>" + message.role + "\n" -}}
+    {%- if message.role == "assistant" -%}
+        {%- generation -%}
+        {%- if message.thinking is defined and (preserve_thinking or loop.index0 > ns.last_user_index) -%}
+            {{- "<think>" + message.thinking + "</think>" -}}
+        {%- endif -%}
+        {%- set _cfm_tag = "CONTINUE_FINAL_MESSAGE_TAG " -%}
+        {%- set _has_cfm = false -%}
+        {%- if message.content is defined -%}
+            {%- set content = parse_content(message.content) -%}
+            {%- if not (preserve_thinking or loop.index0 > ns.last_user_index) -%}
+                {%- if "</think>" in content -%}
+                    {%- set content = content.split("</think>")[-1] | trim -%}
+                {%- endif -%}
+            {%- endif -%}
+            {%- if message.tool_calls is defined and content.endswith(_cfm_tag) -%}
+                {%- set _has_cfm = true -%}
+                {%- set _trunc_len = (content | length) - (_cfm_tag | length) -%}
+                {{- content[:_trunc_len] -}}
+            {%- else -%}
+                {{- content -}}
+            {%- endif -%}
+        {%- endif -%}
+        {%- if message.tool_calls is defined -%}
+            {{- render_tool_calls(message.tool_calls) -}}
+        {%- endif -%}
+        {%- if _has_cfm -%}
+            {{- _cfm_tag -}}
+        {%- endif -%}
+        {{- "<|im_end|>\n" -}}
+        {%- endgeneration -%}
+    {%- else %}
+        {%- if message.get("content") -%}
+            {{- parse_content(message["content"]) -}}
+        {%- endif -%}
+        {{- "<|im_end|>\n" -}}
+    {%- endif %}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{- "<|im_start|>assistant\n" -}}
+{%- endif -%}

config.json ADDED Viewed

	@@ -0,0 +1,247 @@

+{
+    "architectures": [
+        "Lfm2MoeForCausalLM"
+    ],
+    "bos_token_id": 124894,
+    "conv_L_cache": 3,
+    "conv_bias": false,
+    "dtype": "bfloat16",
+    "eos_token_id": 124900,
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "intermediate_size": 7168,
+    "layer_types": [
+        "conv",
+        "conv",
+        "full_attention",
+        "conv",
+        "conv",
+        "conv",
+        "full_attention",
+        "conv",
+        "conv",
+        "conv",
+        "full_attention",
+        "conv",
+        "conv",
+        "conv",
+        "full_attention",
+        "conv",
+        "conv",
+        "conv",
+        "full_attention",
+        "conv",
+        "conv",
+        "full_attention",
+        "conv",
+        "conv"
+    ],
+    "max_position_embeddings": 128000,
+    "model_type": "lfm2_moe",
+    "moe_intermediate_size": 1792,
+    "norm_eps": 1e-05,
+    "norm_topk_prob": true,
+    "num_attention_heads": 32,
+    "num_dense_layers": 2,
+    "num_experts": 32,
+    "num_experts_per_tok": 4,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 8,
+    "pad_token_id": 124893,
+    "quantization": {
+        "group_size": 64,
+        "bits": 6,
+        "mode": "affine",
+        "model.layers.2.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.3.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.4.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.5.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.6.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.7.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.8.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.9.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.10.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.11.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.12.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.13.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.14.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.15.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.16.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.17.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.18.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.19.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.20.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.21.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.22.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.23.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        }
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 6,
+        "mode": "affine",
+        "model.layers.2.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.3.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.4.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.5.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.6.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.7.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.8.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.9.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.10.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.11.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.12.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.13.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.14.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.15.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.16.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.17.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.18.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.19.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.20.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.21.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.22.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.23.feed_forward.gate": {
+            "group_size": 64,
+            "bits": 8
+        }
+    },
+    "rope_parameters": {
+        "rope_theta": 5000000,
+        "rope_type": "default"
+    },
+    "routed_scaling_factor": 1.0,
+    "tie_word_embeddings": true,
+    "transformers_version": "5.9.0",
+    "use_cache": true,
+    "use_expert_bias": true,
+    "vocab_size": 128000
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,10 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 124894,
+  "eos_token_id": 124900,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 124893,
+  "transformers_version": "5.9.0",
+  "use_cache": true
+}

model-00001-of-00002.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c30f416f2d7365fc3f533ab565fd9419caa58328edeb784c9c711d57e7044ac7
+size 5290576997

model-00002-of-00002.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1f233780191b92ff3e9ac6f389d179223bdb30df0aa8e22a3948ac4580b198d3
+size 1590238796

model.safetensors.index.json ADDED Viewed

	@@ -0,0 +1,574 @@

+{
+    "metadata": {
+        "total_size": 6880747776,
+        "total_parameters": 8467856128
+    },
+    "weight_map": {
+        "model.embed_tokens.biases": "model-00001-of-00002.safetensors",
+        "model.embed_tokens.scales": "model-00001-of-00002.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+        "model.embedding_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.0.conv.conv.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.conv.in_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.0.conv.in_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.conv.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.conv.out_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.0.conv.out_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.conv.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.feed_forward.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.0.feed_forward.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.feed_forward.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.0.feed_forward.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.feed_forward.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.0.feed_forward.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.ffn_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.operator_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.conv.conv.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.conv.in_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.1.conv.in_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.conv.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.conv.out_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.1.conv.out_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.conv.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.feed_forward.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.1.feed_forward.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.feed_forward.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.1.feed_forward.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.feed_forward.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.1.feed_forward.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.ffn_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.operator_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
+        "model.layers.10.feed_forward.gate.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.feed_forward.gate.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.ffn_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.operator_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.conv.conv.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.conv.in_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.conv.in_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.conv.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.conv.out_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.conv.out_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.conv.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
+        "model.layers.11.feed_forward.gate.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.feed_forward.gate.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.ffn_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.operator_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.conv.conv.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.conv.in_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.conv.in_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.conv.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.conv.out_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.conv.out_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.conv.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
+        "model.layers.12.feed_forward.gate.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.feed_forward.gate.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.ffn_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.operator_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.conv.conv.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.conv.in_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.conv.in_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.conv.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.conv.out_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.conv.out_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.conv.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
+        "model.layers.13.feed_forward.gate.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.feed_forward.gate.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.ffn_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.operator_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
+        "model.layers.14.feed_forward.gate.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.feed_forward.gate.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.ffn_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.operator_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.conv.conv.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.conv.in_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.conv.in_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.conv.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.conv.out_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.conv.out_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.conv.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
+        "model.layers.15.feed_forward.gate.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.feed_forward.gate.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.ffn_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.operator_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.conv.conv.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.conv.in_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.16.conv.in_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.conv.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.conv.out_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.16.conv.out_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.conv.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
+        "model.layers.16.feed_forward.gate.biases": "model-00001-of-00002.safetensors",
+        "model.layers.16.feed_forward.gate.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.16.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.16.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.16.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.ffn_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.operator_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.conv.conv.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.conv.in_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.17.conv.in_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.conv.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.conv.out_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.17.conv.out_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.conv.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
+        "model.layers.17.feed_forward.gate.biases": "model-00001-of-00002.safetensors",
+        "model.layers.17.feed_forward.gate.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.17.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.17.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.17.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.ffn_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.operator_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.feed_forward.expert_bias": "model-00002-of-00002.safetensors",
+        "model.layers.18.feed_forward.gate.biases": "model-00001-of-00002.safetensors",
+        "model.layers.18.feed_forward.gate.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.feed_forward.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.18.feed_forward.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.18.feed_forward.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.18.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.18.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.18.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.ffn_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.18.operator_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.18.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.conv.conv.weight": "model-00002-of-00002.safetensors",
+        "model.layers.19.conv.in_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.19.conv.in_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.19.conv.in_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.19.conv.out_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.19.conv.out_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.19.conv.out_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.19.feed_forward.expert_bias": "model-00002-of-00002.safetensors",
+        "model.layers.19.feed_forward.gate.biases": "model-00002-of-00002.safetensors",
+        "model.layers.19.feed_forward.gate.scales": "model-00002-of-00002.safetensors",
+        "model.layers.19.feed_forward.gate.weight": "model-00002-of-00002.safetensors",
+        "model.layers.19.feed_forward.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.19.feed_forward.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.19.feed_forward.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.19.feed_forward.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.19.feed_forward.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.19.feed_forward.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.19.feed_forward.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.19.feed_forward.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.19.feed_forward.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.19.ffn_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.19.operator_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.2.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
+        "model.layers.2.feed_forward.gate.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.feed_forward.gate.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.ffn_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.operator_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.conv.conv.weight": "model-00002-of-00002.safetensors",
+        "model.layers.20.conv.in_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.20.conv.in_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.20.conv.in_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.20.conv.out_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.20.conv.out_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.20.conv.out_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.20.feed_forward.expert_bias": "model-00002-of-00002.safetensors",
+        "model.layers.20.feed_forward.gate.biases": "model-00002-of-00002.safetensors",
+        "model.layers.20.feed_forward.gate.scales": "model-00002-of-00002.safetensors",
+        "model.layers.20.feed_forward.gate.weight": "model-00002-of-00002.safetensors",
+        "model.layers.20.feed_forward.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.20.feed_forward.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.20.feed_forward.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.20.feed_forward.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.20.feed_forward.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.20.feed_forward.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.20.feed_forward.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.20.feed_forward.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.20.feed_forward.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.20.ffn_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.20.operator_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.feed_forward.expert_bias": "model-00002-of-00002.safetensors",
+        "model.layers.21.feed_forward.gate.biases": "model-00002-of-00002.safetensors",
+        "model.layers.21.feed_forward.gate.scales": "model-00002-of-00002.safetensors",
+        "model.layers.21.feed_forward.gate.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.feed_forward.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.21.feed_forward.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.21.feed_forward.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.feed_forward.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.21.feed_forward.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.21.feed_forward.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.feed_forward.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.21.feed_forward.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.21.feed_forward.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.ffn_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.operator_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.k_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.out_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.out_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.q_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.conv.conv.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.conv.in_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.22.conv.in_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.22.conv.in_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.conv.out_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.22.conv.out_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.22.conv.out_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.feed_forward.expert_bias": "model-00002-of-00002.safetensors",
+        "model.layers.22.feed_forward.gate.biases": "model-00002-of-00002.safetensors",
+        "model.layers.22.feed_forward.gate.scales": "model-00002-of-00002.safetensors",
+        "model.layers.22.feed_forward.gate.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.feed_forward.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.22.feed_forward.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.22.feed_forward.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.feed_forward.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.22.feed_forward.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.22.feed_forward.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.feed_forward.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.22.feed_forward.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.22.feed_forward.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.ffn_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.operator_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.conv.conv.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.conv.in_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.23.conv.in_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.23.conv.in_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.conv.out_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.23.conv.out_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.23.conv.out_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.feed_forward.expert_bias": "model-00002-of-00002.safetensors",
+        "model.layers.23.feed_forward.gate.biases": "model-00002-of-00002.safetensors",
+        "model.layers.23.feed_forward.gate.scales": "model-00002-of-00002.safetensors",
+        "model.layers.23.feed_forward.gate.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.feed_forward.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.23.feed_forward.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.23.feed_forward.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.feed_forward.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.23.feed_forward.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.23.feed_forward.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.feed_forward.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.23.feed_forward.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.23.feed_forward.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.ffn_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.operator_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.3.conv.conv.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.conv.in_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.conv.in_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.conv.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.conv.out_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.conv.out_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.conv.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
+        "model.layers.3.feed_forward.gate.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.feed_forward.gate.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.ffn_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.operator_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.conv.conv.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.conv.in_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.conv.in_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.conv.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.conv.out_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.conv.out_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.conv.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
+        "model.layers.4.feed_forward.gate.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.feed_forward.gate.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.ffn_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.operator_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.conv.conv.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.conv.in_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.conv.in_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.conv.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.conv.out_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.conv.out_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.conv.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
+        "model.layers.5.feed_forward.gate.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.feed_forward.gate.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.ffn_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.operator_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
+        "model.layers.6.feed_forward.gate.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.feed_forward.gate.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.ffn_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.operator_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.conv.conv.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.conv.in_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.conv.in_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.conv.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.conv.out_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.conv.out_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.conv.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
+        "model.layers.7.feed_forward.gate.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.feed_forward.gate.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.ffn_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.operator_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.conv.conv.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.conv.in_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.conv.in_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.conv.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.conv.out_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.conv.out_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.conv.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
+        "model.layers.8.feed_forward.gate.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.feed_forward.gate.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.ffn_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.operator_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.conv.conv.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.conv.in_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.conv.in_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.conv.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.conv.out_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.conv.out_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.conv.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
+        "model.layers.9.feed_forward.gate.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.feed_forward.gate.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.ffn_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.operator_norm.weight": "model-00001-of-00002.safetensors"
+    }
+}

tokenizer.json ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:695be7802a0e4b8a81048f0ff5ebb7fc811a0ba5a6be63dbb24deb5a81096f41
+size 17905598

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,11 @@

+{
+  "backend": "tokenizers",
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "is_local": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "TokenizersBackend",
+  "use_default_system_prompt": false
+}