UPDATE: Official version is out, use it instead: https://huggingface.co./mistralai/Mistral-7B-v0.1

---

---

---

---

mistral-7B-v0.1-hf

Huggingface compatible version of Mistral's 7B model: https://twitter.com/MistralAI/status/1706877320844509405

Usage

Load in bfloat16 (16GB VRAM or higher)

import torch
from transformers import LlamaForCausalLM, LlamaTokenizer, pipeline, TextStreamer

tokenizer = LlamaTokenizer.from_pretrained("kittn/mistral-7B-v0.1-hf")
model = LlamaForCausalLM.from_pretrained(
    "kittn/mistral-7B-v0.1-hf",
    torch_dtype=torch.bfloat16,
    device_map={"": 0}
)

pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)

pipe("Hi, my name", streamer=TextStreamer(tokenizer), max_new_tokens=128)

Load in bitsandbytes nf4 (6GB VRAM or higher, maybe less with double_quant)

import torch
from transformers import LlamaForCausalLM, LlamaTokenizer, pipeline, TextStreamer, BitsAndBytesConfig

tokenizer = LlamaTokenizer.from_pretrained("kittn/mistral-7B-v0.1-hf")
model = LlamaForCausalLM.from_pretrained(
    "kittn/mistral-7B-v0.1-hf",
    device_map={"": 0},
    quantization_config=BitsAndBytesConfig(
        load_in_4bit=True,
        bnb_4bit_compute_dtype=torch.float16,
        bnb_4bit_quant_type="nf4",
        bnb_4bit_use_double_quant=False, # set to True to save more VRAM at the cost of some speed/accuracy
    ),
)

pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)

pipe("Hi, my name", streamer=TextStreamer(tokenizer), max_new_tokens=128)

Load in bitsandbytes int8 (8GB VRAM or higher). Quite slow; not recommended.

import torch
from transformers import LlamaForCausalLM, LlamaTokenizer, pipeline, TextStreamer, BitsAndBytesConfig

tokenizer = LlamaTokenizer.from_pretrained("kittn/mistral-7B-v0.1-hf")
model = LlamaForCausalLM.from_pretrained(
    "kittn/mistral-7B-v0.1-hf",
    device_map={"": 0},
    quantization_config=BitsAndBytesConfig(
        load_in_8bit=True,
    ),
)

pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)

pipe("Hi, my name", streamer=TextStreamer(tokenizer), max_new_tokens=128)

Notes

• The original huggingface conversion script converts the model from bf16 to fp16 before saving it. This script doesn't
• The tokenizer is created with legacy=False, more about this here
• Saved in safetensors format

Conversion script [link]

Unlike meta-llama/Llama-2-7b, this model uses GQA. This breaks some assumptions in the original conversion script, requiring a few changes.

Conversion script: link

Original conversion script: link