FriendliAI/Mixtral-8x22B-Instruct-v0.1-fp8

Mixtral-8x22B-Instruct-v0.1 - FP8

• Model creator: Mistral AI
• Original model: Mixtral-8x22B-Instruct-v0.1

Description

This repo contains the Mixtral-8x22B-Instruct-v0.1 model quantized to FP8 by FriendliAI, significantly enhancing its inference efficiency while maintaining high accuracy. Note that FP8 is only supported by NVIDIA Ada, Hopper, and Blackwell GPU architectures. Check out FriendliAI documentation for more details.

Compatibility

This model is compatible with Friendli Container.

Prerequisites

• Before you begin, make sure you have signed up for Friendli Suite. You can use Friendli Containers free of charge for four weeks.
• Prepare a Personal Access Token following this guide.
• Prepare a Friendli Container Secret following this guide.

Preparing Personal Access Token

PAT (Personal Access Token) is the user credential for for logging into our container registry.

1. Sign in Friendli Suite.
2. Go to User Settings > Tokens and click 'Create new token'.
3. Save your created token value.

Pulling Friendli Container Image

1. Log in to the Docker client using the personal access token created as outlined in this guide.

export FRIENDLI_PAT="YOUR PAT"
docker login registry.friendli.ai -u $YOUR_EMAIL -p $FRIENDLI_PAT

2. Pull image

docker pull registry.friendli.ai/trial

Running Friendli Container

Once you've prepared the image of Friendli Container, you can launch it to create a serving endpoint.

docker run \
  --gpus '"device=0,1,2,3"' \
  -p 8000:8000 \
  -v ~/.cache/huggingface:/root/.cache/huggingface \
  -e FRIENDLI_CONTAINER_SECRET="YOUR CONTAINER SECRET" \
  registry.friendli.ai/trial \
    --web-server-port 8000 \
    --hf-model-name FriendliAI/Mixtral-8x22B-Instruct-v0.1-fp8 \
    --num-devices 4  # Use tensor parallelism degree 4

Optimizing Inference Performance with Policy Search

To serve MoE models efficiently, it is required to run a policy search to explore the optimal execution policy:

export POLICY_DIR=$PWD/policy

mkdir -p $POLICY_DIR

docker run \
  --gpus '"device=0,1,2,3"' \
  -p 8000:8000 \
  -v ~/.cache/huggingface:/root/.cache/huggingface \
  -v $POLICY_DIR:/policy \
  -e FRIENDLI_CONTAINER_SECRET="YOUR CONTAINER SECRET" \
  registry.friendli.ai/trial \
    --web-server-port 8000 \
    --hf-model-name FriendliAI/Mixtral-8x22B-Instruct-v0.1-fp8 \
    --num-devices 4  # Use tensor parallelism degree 4 \
    --algo-policy-dir /policy \
    --search-policy true

When the optimal policy is successfully searched, the policy is compiled into a policy file and saved at $POLICY_DIR. Now you can create an inference endpoint with this optimal policy as follows:

docker run \
  --gpus '"device=0,1,2,3"' \
  -p 8000:8000 \
  -v ~/.cache/huggingface:/root/.cache/huggingface \
  -v $POLICY_DIR:/policy \
  -e FRIENDLI_CONTAINER_SECRET="YOUR CONTAINER SECRET" \
  registry.friendli.ai/trial \
    --web-server-port 8000 \
    --hf-model-name FriendliAI/Mixtral-8x22B-Instruct-v0.1-fp8 \
    --num-devices 4  # Use tensor parallelism degree 4 \
    --algo-policy-dir /policy

---

Original model card: MistralAI's Mixtral-8x22B-Instruct v0.1

Model Card for Mixtral-8x22B-Instruct-v0.1

The Mixtral-8x22B-Instruct-v0.1 Large Language Model (LLM) is an instruct fine-tuned version of the Mixtral-8x22B-v0.1.

Run the model

from transformers import AutoModelForCausalLM
from mistral_common.protocol.instruct.messages import (
    AssistantMessage,
    UserMessage,
)
from mistral_common.protocol.instruct.tool_calls import (
    Tool,
    Function,
)
from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
from mistral_common.tokens.instruct.normalize import ChatCompletionRequest

device = "cuda" # the device to load the model onto

tokenizer_v3 = MistralTokenizer.v3()

mistral_query = ChatCompletionRequest(
    tools=[
        Tool(
            function=Function(
                name="get_current_weather",
                description="Get the current weather",
                parameters={
                    "type": "object",
                    "properties": {
                        "location": {
                            "type": "string",
                            "description": "The city and state, e.g. San Francisco, CA",
                        },
                        "format": {
                            "type": "string",
                            "enum": ["celsius", "fahrenheit"],
                            "description": "The temperature unit to use. Infer this from the users location.",
                        },
                    },
                    "required": ["location", "format"],
                },
            )
        )
    ],
    messages=[
        UserMessage(content="What's the weather like today in Paris"),
    ],
    model="test",
)

encodeds = tokenizer_v3.encode_chat_completion(mistral_query).tokens
model = AutoModelForCausalLM.from_pretrained("mistralai/Mixtral-8x22B-Instruct-v0.1")
model_inputs = encodeds.to(device)
model.to(device)

generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
sp_tokenizer = tokenizer_v3.instruct_tokenizer.tokenizer
decoded = sp_tokenizer.decode(generated_ids[0])
print(decoded)

Alternatively, you can run this example with the Hugging Face tokenizer. To use this example, you'll need transformers version 4.39.0 or higher.

pip install transformers==4.39.0

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "mistralai/Mixtral-8x22B-Instruct-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
conversation=[
    {"role": "user", "content": "What's the weather like in Paris?"},
    {
        "role": "tool_calls",
        "content": [
            {
                "name": "get_current_weather",
                "arguments": {"location": "Paris, France", "format": "celsius"},
                
            }
        ]
    },
    {
        "role": "tool_results",
        "content": {"content": 22}
    },
    {"role": "assistant", "content": "The current temperature in Paris, France is 22 degrees Celsius."},
    {"role": "user", "content": "What about San Francisco?"}
]


tools = [{"type": "function", "function": {"name":"get_current_weather", "description": "Get▁the▁current▁weather", "parameters": {"type": "object", "properties": {"location": {"type": "string", "description": "The city and state, e.g. San Francisco, CA"}, "format": {"type": "string", "enum": ["celsius", "fahrenheit"], "description": "The temperature unit to use. Infer this from the users location."}},"required":["location","format"]}}}]

# render the tool use prompt as a string:
tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            chat_template="tool_use",
            tools=tools,
            tokenize=False,
            add_generation_prompt=True,

)
model = AutoModelForCausalLM.from_pretrained("mistralai/Mixtral-8x22B-Instruct-v0.1")

inputs = tokenizer(tool_use_prompt, return_tensors="pt")

outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Instruct tokenizer

The HuggingFace tokenizer included in this release should match our own. To compare: pip install mistral-common

from mistral_common.protocol.instruct.messages import (
    AssistantMessage,
    UserMessage,
)
from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
from mistral_common.tokens.instruct.normalize import ChatCompletionRequest

from transformers import AutoTokenizer

tokenizer_v3 = MistralTokenizer.v3()

mistral_query = ChatCompletionRequest(
    messages=[
        UserMessage(content="How many experts ?"),
        AssistantMessage(content="8"),
        UserMessage(content="How big ?"),
        AssistantMessage(content="22B"),
        UserMessage(content="Noice 🎉 !"),
    ],
    model="test",
)
hf_messages = mistral_query.model_dump()['messages']

tokenized_mistral = tokenizer_v3.encode_chat_completion(mistral_query).tokens

tokenizer_hf = AutoTokenizer.from_pretrained('mistralai/Mixtral-8x22B-Instruct-v0.1')
tokenized_hf = tokenizer_hf.apply_chat_template(hf_messages, tokenize=True)

assert tokenized_hf == tokenized_mistral

Function calling and special tokens

This tokenizer includes more special tokens, related to function calling :

• [TOOL_CALLS]
• [AVAILABLE_TOOLS]
• [/AVAILABLE_TOOLS]
• [TOOL_RESULTS]
• [/TOOL_RESULTS]

If you want to use this model with function calling, please be sure to apply it similarly to what is done in our SentencePieceTokenizerV3.

The Mistral AI Team

Albert Jiang, Alexandre Sablayrolles, Alexis Tacnet, Antoine Roux, Arthur Mensch, Audrey Herblin-Stoop, Baptiste Bout, Baudouin de Monicault, Blanche Savary, Bam4d, Caroline Feldman, Devendra Singh Chaplot, Diego de las Casas, Eleonore Arcelin, Emma Bou Hanna, Etienne Metzger, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Harizo Rajaona, Jean-Malo Delignon, Jia Li, Justus Murke, Louis Martin, Louis Ternon, Lucile Saulnier, Lélio Renard Lavaud, Margaret Jennings, Marie Pellat, Marie Torelli, Marie-Anne Lachaux, Nicolas Schuhl, Patrick von Platen, Pierre Stock, Sandeep Subramanian, Sophia Yang, Szymon Antoniak, Teven Le Scao, Thibaut Lavril, Timothée Lacroix, Théophile Gervet, Thomas Wang, Valera Nemychnikova, William El Sayed, William Marshall