license: apache-2.0
language:
- fr
- it
- de
- es
- en
Model Card for Mistral-8x7B
The Mistral-8x7B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts. The Mistral-8x7B outperforms Llama 2 70B on most benchmarks we tested.
For full details of this model please read our release blog post.
Warning
This repo contains weights that are compatible with vLLM serving of the model. It is based on the original Mixtral torrent release, but the file format and parameter names are different. Please note that model cannot (yet) be instantiated with HF.
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)
[START_SYMBOL_ID] +
tokenize("[INST]") + tokenize(USER_MESSAGE_1) + tokenize("[/INST]") +
tokenize(BOT_MESSAGE_1) + [END_SYMBOL_ID] +
…
tokenize("[INST]") + tokenize(USER_MESSAGE_N) + tokenize("[/INST]") +
tokenize(BOT_MESSAGE_N) + [END_SYMBOL_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.
This format is available as a chat template via the apply_chat_template() method:
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.1")
tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.1")
messages = [
{"role": "user", "content": "What is your favourite condiment?"},
{"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
{"role": "user", "content": "Do you have mayonnaise recipes?"}
]
encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
model_inputs = encodeds.to(device)
model.to(device)
generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])
Limitations
The Mistral-8x7B 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, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Ana, 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.