Mixtral 8x7B Instruct V0.1 HF

🚀 Hugging Face Transformers Conversion of Mixtral-8x7B-Instruct

The Mixtral-8x7B is a pretrained generative Sparse Mixture of Experts large language model. It outperforms Llama 2 70B on most tested benchmarks, offering high - performance language processing capabilities.

🚀 Quick Start

The Mixtral-8x7B Large Language Model (LLM) is a powerful pretrained generative Sparse Mixture of Experts. To understand its full potential, please read our release blog post.

✨ Features

• High - performance: Outperforms Llama 2 70B on most benchmarks.
• Instruction - following: Can follow specific instruction formats for better output.

⚠️ Warning

This repo contains weights that are compatible with vLLM serving of the model as well as Hugging Face transformers library. It is based on the original Mixtral torrent release, but the file format and parameter names are different. Please note that the model cannot (yet) be instantiated with HF.

📚 Documentation

Instruction format

This format must be strictly respected, otherwise the model will generate sub - optimal outputs.

The template used to build a prompt for the Instruct model is defined as follows:

<s> [INST] Instruction [/INST] Model answer</s> [INST] Follow - up instruction [/INST]

Note that <s> and </s> are special tokens for beginning of string (BOS) and end of string (EOS) while [INST] and [/INST] are regular strings.

As reference, here is the pseudo - code used to tokenize instructions during fine - tuning:

def tokenize(text):
    return tok.encode(text, add_special_tokens=False)

[BOS_ID] + 
tokenize("[INST]") + tokenize(USER_MESSAGE_1) + tokenize("[/INST]") +
tokenize(BOT_MESSAGE_1) + [EOS_ID] +
…
tokenize("[INST]") + tokenize(USER_MESSAGE_N) + tokenize("[/INST]") +
tokenize(BOT_MESSAGE_N) + [EOS_ID]

In the pseudo - code above, note that the tokenize method should not add a BOS or EOS token automatically, but should add a prefix space.

💻 Usage Examples

Basic Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "mistralai/Mixtral-8x7B-Instruct-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))

Advanced Usage

In half - precision

Note float16 precision only works on GPU devices

+ import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)

+ model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16).to(0)

text = "Hello my name is"
+ inputs = tokenizer(text, return_tensors="pt").to(0)

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

Lower precision using (8 - bit & 4 - bit) using bitsandbytes

+ import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)

+ model = AutoModelForCausalLM.from_pretrained(model_id, load_in_4bit=True)

text = "Hello my name is"
+ inputs = tokenizer(text, return_tensors="pt").to(0)

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

Load the model with Flash Attention 2

+ import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)

+ model = AutoModelForCausalLM.from_pretrained(model_id, use_flash_attention_2=True)

text = "Hello my name is"
+ inputs = tokenizer(text, return_tensors="pt").to(0)

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

🔧 Technical Details

The Mixtral-8x7B Instruct model is a quick demonstration that the base model can be easily fine - tuned to achieve compelling performance. However, it does not have any moderation mechanisms. The Mistral AI Team is looking forward to engaging with the community on ways to make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.

📄 License

The model is released under the apache - 2.0 license.

👥 The Mistral AI Team

Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Louis Ternon, Lucile Saulnier, Marie - Anne Lachaux, Pierre Stock, Teven Le Scao, Théophile Gervet, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.