Instructions to use 3amthoughts/mistral-7b-instruct-v0.3-bnb-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 3amthoughts/mistral-7b-instruct-v0.3-bnb-4bit with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="3amthoughts/mistral-7b-instruct-v0.3-bnb-4bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("3amthoughts/mistral-7b-instruct-v0.3-bnb-4bit")
model = AutoModelForCausalLM.from_pretrained("3amthoughts/mistral-7b-instruct-v0.3-bnb-4bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use 3amthoughts/mistral-7b-instruct-v0.3-bnb-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "3amthoughts/mistral-7b-instruct-v0.3-bnb-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "3amthoughts/mistral-7b-instruct-v0.3-bnb-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/3amthoughts/mistral-7b-instruct-v0.3-bnb-4bit

SGLang

How to use 3amthoughts/mistral-7b-instruct-v0.3-bnb-4bit with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "3amthoughts/mistral-7b-instruct-v0.3-bnb-4bit" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "3amthoughts/mistral-7b-instruct-v0.3-bnb-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "3amthoughts/mistral-7b-instruct-v0.3-bnb-4bit" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "3amthoughts/mistral-7b-instruct-v0.3-bnb-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use 3amthoughts/mistral-7b-instruct-v0.3-bnb-4bit with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for 3amthoughts/mistral-7b-instruct-v0.3-bnb-4bit to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for 3amthoughts/mistral-7b-instruct-v0.3-bnb-4bit to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for 3amthoughts/mistral-7b-instruct-v0.3-bnb-4bit to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="3amthoughts/mistral-7b-instruct-v0.3-bnb-4bit",
    max_seq_length=2048,
)

Docker Model Runner
How to use 3amthoughts/mistral-7b-instruct-v0.3-bnb-4bit with Docker Model Runner:
```
docker model run hf.co/3amthoughts/mistral-7b-instruct-v0.3-bnb-4bit
```

mistral-7b-instruct-v0.3-bnb-4bit

This repository contains a quantized 4-bit version of Mistral-7B-Instruct-v0.3.

Model Details

Developed by: Original weights by Mistral AI; Quantized via Unsloth, by 4amthoughts Lab
Model Type: Large Language Model (LLM) - Causal Decoder-only.
Language(s): English
License: Apache-2.0
Quantization: 4-bit NormalFloat (NF4) using BitsAndBytes.

Usage

You can use this model with the transformers library. Ensure you have bitsandbytes and accelerate installed.

from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
import torch

model_id = "3amthoughts/mistral-7b-instruct-v0.3-bnb-4bit"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    quantization_config=BitsAndBytesConfig(load_in_4bit=True),
    device_map="auto"
)

text = "Explain quantum physics to a five year old."
inputs = tokenizer(text, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=50)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

About 4-bit Quantization

This model was quantized to 4-bit to reduce VRAM usage while maintaining as much performance as possible. It allows the 7B parameter model to run on consumer GPUs with ~6GB-8GB of VRAM.

Downloads last month: 60

Safetensors

Model size

7B params

Tensor type

F32

BF16

Model tree for 3amthoughts/mistral-7b-instruct-v0.3-bnb-4bit

Base model

mistralai/Mistral-7B-v0.3

Finetuned

mistralai/Mistral-7B-Instruct-v0.3

Quantized

unsloth/mistral-7b-instruct-v0.3-bnb-4bit

Quantized

(189)

this model