README.md

---
license: apache-2.0
language:
- en
- es
- it
- de
- fr
tags:
- moe
---

# 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.

Mixtral-8x22B-v0.1 has the following characteristics:
- 140.6B parameters
- 39.1B active parameters
- 64k context window
- 32768 vocab size
- Supports function calling

## How to use

It is recommended to use `mistralai/Mixtral-8x22B-Instruct-v0.1` with [mistral_inference](https://github.com/mistralai/mistral-inference) and [mistral_common](https://github.com/mistralai/mistral-common). For HF `transformers` code snippets, please keep scrolling.

## Generate with `mistral_inference` and `mistral_common`

### Install dependencies
```
pip install mistral_inference mistral_common
```

### Download model

```py
from huggingface_hub import snapshot_download
from pathlib import Path

mistral_models_path = Path.home().joinpath('mistral_models', '8x22B-Instruct-v0.1')
mistral_models_path.mkdir(parents=True, exist_ok=True)

snapshot_download(repo_id="mistralai/Mixtral-8x22B-Instruct-v0.1", allow_patterns=["params.json", "consolidated.safetensors", "tokenizer.model.v3"], local_dir=mistral_models_path)
```

### Chat

After installing `mistral_inference`, a `mistral-chat` CLI command should be available in your environment. You can chat with the model using

```
mistral-chat $HOME/mistral_models/8x22B-Instruct-v0.1 --instruct --max_tokens 256
```

### Instruct following

```py
from mistral_inference.model import Transformer
from mistral_inference.generate import generate

from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
from mistral_common.protocol.instruct.messages import UserMessage
from mistral_common.protocol.instruct.request import ChatCompletionRequest


tokenizer = MistralTokenizer.from_file(f"{mistral_models_path}/tokenizer.model.v3")
# tokenizer = MistralTokenizer.v3()

model = Transformer.from_folder(mistral_models_path)

completion_request = ChatCompletionRequest(messages=[UserMessage(content="Explain Machine Learning to me in a nutshell.")])

tokens = tokenizer.encode_chat_completion(completion_request).tokens

out_tokens, _ = generate([tokens], model, max_tokens=64, temperature=0.0, eos_id=tokenizer.instruct_tokenizer.tokenizer.eos_id)
result = tokenizer.instruct_tokenizer.tokenizer.decode(out_tokens[0])

print(result)
```

### Function calling

```py
from mistral_common.protocol.instruct.tool_calls import Function, Tool
from mistral_inference.model import Transformer
from mistral_inference.generate import generate

from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
from mistral_common.protocol.instruct.messages import UserMessage
from mistral_common.protocol.instruct.request import ChatCompletionRequest


tokenizer = MistralTokenizer.from_file(f"{mistral_models_path}/tokenizer.model.v3")
# tokenizer = MistralTokenizer.v3()

model = Transformer.from_folder(mistral_models_path)

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

tokens = tokenizer.encode_chat_completion(completion_request).tokens

out_tokens, _ = generate([tokens], model, max_tokens=64, temperature=0.0, eos_id=tokenizer.instruct_tokenizer.tokenizer.eos_id)
result = tokenizer.instruct_tokenizer.tokenizer.decode(out_tokens[0])

print(result)
```

## Generate with `transformers`

### Install dependencies
```
pip install transformers
```

### Instruct following

```py
from transformers import AutoModelForCausalLM, AutoTokenizer
 
model = AutoModelForCausalLM.from_pretrained("mistralai/Mixtral-8x22B-Instruct-v0.1")
model.to("cuda")

tokenizer = AutoTokenizer.from_pretrained("mistralai/Mixtral-8x22B-Instruct-v0.1")

messages = [
    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
    {"role": "user", "content": "Who are you?"},
]

messages_prompt = tokenizer.apply_chat_template(
            messages,
            tokenize=False,
            add_generation_prompt=True,
)

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

outputs = model.generate(**inputs, max_new_tokens=1000)
result = tokenizer.decode(outputs[0], skip_special_tokens=True)

print(result)
```
Or:
```py
from transformers import pipeline

messages = [
    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
    {"role": "user", "content": "Who are you?"},
]
chatbot = pipeline("text-generation", model="mistralai/Mixtral-8x22B-Instruct-v0.1")
result = chatbot(messages)

print(result)
```

## Limitations

The Mistral 8x22B Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance. 
It does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to
make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.

## The Mistral AI Team

Albert Jiang, Alexandre Sablayrolles, Alexis Tacnet, 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