Mistral-Large-Instruct-2407 is an advanced dense Large Language Model (LLM) of 123B parameters with state-of-the-art reasoning, knowledge and coding capabilities.
For more details about this model please refer to our release blog post.
| Benchmark | Score |
|---|---|
| MMLU | 84.0% |
| Benchmark | Score |
|---|---|
| French | 82.8% |
| German | 81.6% |
| Spanish | 82.7% |
| Italian | 82.7% |
| Dutch | 80.7% |
| Portuguese | 81.6% |
| Russian | 79.0% |
| Korean | 60.1% |
| Japanese | 78.8% |
| Chinese | 74.8% |
| Benchmark | Score |
|---|---|
| MT Bench | 8.63 |
| Wild Bench | 56.3 |
| Arena Hard | 73.2 |
| Benchmark | Score |
|---|---|
| Human Eval | 92% |
| Human Eval Plus | 87% |
| MBPP Base | 80% |
| MBPP Plus | 69% |
| Benchmark | Score |
|---|---|
| GSM8K | 93% |
| Math Instruct (0-shot, no CoT) | 70% |
| Math Instruct (0-shot, CoT) | 71.5% |
The model can be used with two different frameworks
mistral_inference: See heretransformers: See hereIt is recommended to use mistralai/Mistral-Large-Instruct-2407 with mistral-inference. For HF transformers code snippets, please keep scrolling.
pip install mistral_inference
from huggingface_hub import snapshot_download
from pathlib import Path
mistral_models_path = Path.home().joinpath('mistral_models', 'Large')
mistral_models_path.mkdir(parents=True, exist_ok=True)
snapshot_download(repo_id="mistralai/Mistral-Large-Instruct-2407", allow_patterns=["params.json", "consolidated-*.safetensors", "tokenizer.model.v3"], local_dir=mistral_models_path)
After installing mistral_inference, a mistral-chat CLI command should be available in your environment.
Given the size of this model, you will need a node with several GPUs (more than 300GB cumulated vRAM).
If you have 8 GPUs on your machine, you can chat with the model using
torchrun --nproc-per-node 8 --no-python mistral-chat $HOME/mistral_models/Large --instruct --max_tokens 256 --temperature 0.7
E.g. Try out something like:
How expensive would it be to ask a window cleaner to clean all windows in Paris. Make a reasonable guess in US Dollar.
from mistral_inference.transformer 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")
model = Transformer.from_folder(mistral_models_path)
prompt = "How expensive would it be to ask a window cleaner to clean all windows in Paris. Make a reasonable guess in US Dollar."
completion_request = ChatCompletionRequest(messages=[UserMessage(content=prompt)])
tokens = tokenizer.encode_chat_completion(completion_request).tokens
out_tokens, _ = generate([tokens], model, max_tokens=64, temperature=0.7, eos_id=tokenizer.instruct_tokenizer.tokenizer.eos_id)
result = tokenizer.decode(out_tokens[0])
print(result)
from mistral_common.protocol.instruct.tool_calls import Function, Tool
from mistral_inference.transformer 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")
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=256, temperature=0.7, eos_id=tokenizer.instruct_tokenizer.tokenizer.eos_id)
result = tokenizer.decode(out_tokens[0])
print(result)
If you want to use Hugging Face transformers to generate text, you can do something like this.
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/Mistral-Large-Instruct-2407")
chatbot(messages)
transformers
To use this example, you'll need transformers version 4.42.0 or higher. Please see the
function calling guide
in the transformers docs for more information.
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_id = "mistralai/Mistral-Large-Instruct-2407"
tokenizer = AutoTokenizer.from_pretrained(model_id)
def get_current_weather(location: str, format: str):
"""
Get the current weather
Args:
location: The city and state, e.g. San Francisco, CA
format: The temperature unit to use. Infer this from the users location. (choices: ["celsius", "fahrenheit"])
"""
pass
conversation = [{"role": "user", "content": "What's the weather like in Paris?"}]
tools = [get_current_weather]
# format and tokenize the tool use prompt
inputs = tokenizer.apply_chat_template(
conversation,
tools=tools,
add_generation_prompt=True,
return_dict=True,
return_tensors="pt",
)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")
inputs.to(model.device)
outputs = model.generate(**inputs, max_new_tokens=1000)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
Note that, for reasons of space, this example does not show a complete cycle of calling a tool and adding the tool call and tool results to the chat history so that the model can use them in its next generation. For a full tool calling example, please see the function calling guide, and note that Mistral does use tool call IDs, so these must be included in your tool calls and tool results. They should be exactly 9 alphanumeric characters.
The Mistral Large 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.
Albert Jiang, Alexandre Sablayrolles, Alexis Tacnet, Alok Kothari, Antoine Roux, Arthur Mensch, Audrey Herblin-Stoop, Augustin Garreau, Austin Birky, Bam4d, Baptiste Bout, Baudouin de Monicault, Blanche Savary, Carole Rambaud, Caroline Feldman, Devendra Singh Chaplot, Diego de las Casas, Diogo Costa, Eleonore Arcelin, Emma Bou Hanna, Etienne Metzger, Gaspard Blanchet, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Harizo Rajaona, Henri Roussez, Hichem Sattouf, Ian Mack, Jean-Malo Delignon, Jessica Chudnovsky, Justus Murke, Kartik Khandelwal, Lawrence Stewart, Louis Martin, Louis Ternon, Lucile Saulnier, Lélio Renard Lavaud, Margaret Jennings, Marie Pellat, Marie Torelli, Marie-Anne Lachaux, Marjorie Janiewicz, Mickaël Seznec, Nicolas Schuhl, Niklas Muhs, Olivier de Garrigues, Patrick von Platen, Paul Jacob, Pauline Buche, Pavan Kumar Reddy, Perry Savas, Pierre Stock, Romain Sauvestre, Sagar Vaze, Sandeep Subramanian, Saurabh Garg, Sophia Yang, Szymon Antoniak, Teven Le Scao, Thibault Schueller, Thibaut Lavril, Thomas Wang, Théophile Gervet, Timothée Lacroix, Valera Nemychnikova, Wendy Shang, William El Sayed, William Marshall