Instructions to use 0-hero/Matter-0.2-8x22B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 0-hero/Matter-0.2-8x22B with Transformers:

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

pipe = pipeline("text-generation", model="0-hero/Matter-0.2-8x22B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("0-hero/Matter-0.2-8x22B")
model = AutoModelForCausalLM.from_pretrained("0-hero/Matter-0.2-8x22B")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use 0-hero/Matter-0.2-8x22B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "0-hero/Matter-0.2-8x22B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "0-hero/Matter-0.2-8x22B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/0-hero/Matter-0.2-8x22B

SGLang

How to use 0-hero/Matter-0.2-8x22B 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 "0-hero/Matter-0.2-8x22B" \
    --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": "0-hero/Matter-0.2-8x22B",
		"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 "0-hero/Matter-0.2-8x22B" \
        --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": "0-hero/Matter-0.2-8x22B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use 0-hero/Matter-0.2-8x22B with Docker Model Runner:
```
docker model run hf.co/0-hero/Matter-0.2-8x22B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Matter 8x22B - 0.2 (Mixtral 8x22B 0.2 Finetune)

Matter 8x22B 0.2 is finetune on the Matter 0.2 dataset, which is curated from over 35 datsets analyzing >6B tokens

Recommended Usage for best results

System Prompt - You are a helpful assistant

Training

Prompt format: This model uses ChatML prompt format.

<|im_start|>system
You are a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Function Calling

Model also supports function calling. Additional tokens for function calling

Model function call tokens

<tool_call> - Function call start token
</tool_call> - Function call end token

Function call response tokens

<tool_response> - Function response start token
</tool_response> - Function response end token

Example

<|im_start|>system
  You are a helpful assistant with access to the following functions. Use them if required -
  { "name": "get_news_headlines",
    "description": "Get the latest news headlines",
    "parameters":
      { "type": "object",
        "properties":
        { "country":
          { "type": "string",
            "description": "The country for which to fetch news"
          }
        },
      "required": [ "country" ]
    }
  }
<|im_end|>
<|im_start|>user
   Can you tell me the latest news headlines for the United States?<|im_end|>
<|im_start|>assistant
  <tool_call>{"name": "get_news_headlines", "arguments": '{"country": "United States"}'}</tool_call><|im_end|>
<|im_start|>user
  <tool_response>{
    "headlines":
      [
        "Biden announces new vaccine mandates",
        "Hurricane Ida devastates Louisiana",
        "Apple unveils new iPhone",
        "NASA's Perseverance rover collects first Mars rock sample"
      ]
  }</tool_response>
<|im_end|>
<|im_start|>assistant
  Here are the latest news headlines for the United States:
  1. Biden announces new vaccine mandates
  2. Hurricane Ida devastates Louisiana
  3. Apple unveils new iPhone
  4. NASA's Perseverance rover collects first Mars rock sample
<|im_end|>