🚀 Model Card for Codestral-22B-v0.1
Codestral-22B-v0.1 is a model trained on a diverse dataset of over 80 programming languages. It can handle various programming - related tasks, such as answering code - related questions and generating code snippets.
🚀 Quick Start
Installation
It is recommended to use mistralai/Codestral-22B-v0.1
with mistral-inference.
pip install mistral_inference
Download
from huggingface_hub import snapshot_download
from pathlib import Path
mistral_models_path = Path.home().joinpath('mistral_models', 'Codestral-22B-v0.1')
mistral_models_path.mkdir(parents=True, exist_ok=True)
snapshot_download(repo_id="mistralai/Codestral-22B-v0.1", allow_patterns=["params.json", "consolidated.safetensors", "tokenizer.model.v3"], local_dir=mistral_models_path)
✨ Features
- Trained on a diverse dataset of 80+ programming languages, including Python, Java, C, C++, JavaScript, and Bash.
- Can be queried as instruct to answer code - related questions or generate code following specific indications.
- Supports Fill - in - the - Middle (FIM) for predicting middle tokens between a prefix and a suffix, useful for software development add - ons.
💻 Usage Examples
Basic Usage
Encode and Decode with mistral_common
from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
from mistral_common.protocol.instruct.messages import UserMessage
from mistral_common.protocol.instruct.request import ChatCompletionRequest
mistral_models_path = "MISTRAL_MODELS_PATH"
tokenizer = MistralTokenizer.v3()
completion_request = ChatCompletionRequest(messages=[UserMessage(content="Explain Machine Learning to me in a nutshell.")])
tokens = tokenizer.encode_chat_completion(completion_request).tokens
Advanced Usage
Inference with mistral_inference
from mistral_inference.transformer import Transformer
from mistral_inference.generate import generate
model = Transformer.from_folder(mistral_models_path)
out_tokens, _ = generate([tokens], model, max_tokens=64, temperature=0.0, eos_id=tokenizer.instruct_tokenizer.tokenizer.eos_id)
result = tokenizer.decode(out_tokens[0])
print(result)
Inference with hugging face transformers
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("mistralai/Codestral-22B-v0.1")
model.to("cuda")
generated_ids = model.generate(tokens, max_new_tokens=1000, do_sample=True)
result = tokenizer.decode(generated_ids[0].tolist())
print(result)
Chat
After installing mistral_inference
, a mistral-chat
CLI command should be available in your environment.
mistral-chat $HOME/mistral_models/Codestral-22B-v0.1 --instruct --max_tokens 256
Will generate an answer to "Write me a function that computes fibonacci in Rust" and should give something along the following lines:
Sure, here's a simple implementation of a function that computes the Fibonacci sequence in Rust. This function takes an integer `n` as an argument and returns the `n`th Fibonacci number.
fn fibonacci(n: u32) -> u32 {
match n {
0 => 0,
1 => 1,
_ => fibonacci(n - 1) + fibonacci(n - 2),
}
}
fn main() {
let n = 10;
println!("The {}th Fibonacci number is: {}", n, fibonacci(n));
}
This function uses recursion to calculate the Fibonacci number. However, it's not the most efficient solution because it performs a lot of redundant calculations. A more efficient solution would use a loop to iteratively calculate the Fibonacci numbers.
Fill - in - the - middle (FIM)
After installing mistral_inference
and running pip install --upgrade mistral_common
to make sure to have mistral_common>=1.2 installed:
from mistral_inference.transformer import Transformer
from mistral_inference.generate import generate
from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
from mistral_common.tokens.instruct.request import FIMRequest
tokenizer = MistralTokenizer.v3()
model = Transformer.from_folder("~/codestral-22B-240529")
prefix = """def add("""
suffix = """ return sum"""
request = FIMRequest(prompt=prefix, suffix=suffix)
tokens = tokenizer.encode_fim(request).tokens
out_tokens, _ = generate([tokens], model, max_tokens=256, temperature=0.0, eos_id=tokenizer.instruct_tokenizer.tokenizer.eos_id)
result = tokenizer.decode(out_tokens[0])
middle = result.split(suffix)[0].strip()
print(middle)
Should give something along the following lines:
num1, num2):
# Add two numbers
sum = num1 + num2
# return the sum
Usage with transformers library
This model is also compatible with transformers
library, first run pip install -U transformers
then use the snippet below to quickly get started:
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "mistralai/Codestral-22B-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)
text = "Hello my name is"
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
By default, transformers will load the model in full precision. Therefore you might be interested to further reduce down the memory requirements to run the model through the optimizations we offer in HF ecosystem.
📚 Documentation
If you want to learn more about how we process your personal data, please read our Privacy Policy.
💡 Usage Tip
PRs to correct the transformers
tokenizer so that it gives 1 - to - 1 the same results as the mistral_common
reference implementation are very welcome!
🔧 Technical Details
Codestral-22B-v0.1 is trained on a diverse dataset of 80+ programming languages, including the most popular ones, such as Python, Java, C, C++, JavaScript, and Bash (more details in the Blogpost).
📄 License
Codestral-22B-v0.1 is released under the MNLP-0.1
license. You can find the license details at https://mistral.ai/licences/MNPL-0.1.md.
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, Henri Roussez, Jean-Malo Delignon, Jia Li, 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, Mickael Seznec, Nicolas Schuhl, Patrick von Platen, Romain Sauvestre, Pierre Stock, Sandeep Subramanian, Saurabh Garg, Sophia Yang, Szymon Antoniak, Teven Le Scao, Thibaut Lavril, Thibault Schueller, Timothée Lacroix, Théophile Gervet, Thomas Wang, Valera Nemychnikova, Wendy Shang, William El Sayed, William Marshall