Instructions to use redscroll/Mistral-7B-v0.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use redscroll/Mistral-7B-v0.2 with Transformers:

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

pipe = pipeline("text-generation", model="redscroll/Mistral-7B-v0.2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("redscroll/Mistral-7B-v0.2")
model = AutoModelForCausalLM.from_pretrained("redscroll/Mistral-7B-v0.2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use redscroll/Mistral-7B-v0.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "redscroll/Mistral-7B-v0.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "redscroll/Mistral-7B-v0.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/redscroll/Mistral-7B-v0.2

SGLang

How to use redscroll/Mistral-7B-v0.2 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 "redscroll/Mistral-7B-v0.2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "redscroll/Mistral-7B-v0.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "redscroll/Mistral-7B-v0.2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "redscroll/Mistral-7B-v0.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use redscroll/Mistral-7B-v0.2 with Docker Model Runner:
```
docker model run hf.co/redscroll/Mistral-7B-v0.2
```

Not my model(obviously); downloaded the Mistral release model from https://models.mistralcdn.com/mistral-7b-v0-2/mistral-7B-v0.2.tar and uploaded for my own sanity(and fine-tuning), since it's still not uploaded on Mistral repo.

The standard code works:

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model = AutoModelForCausalLM.from_pretrained("redscroll/Mistral-7B-v0.2", torch_dtype=torch.bfloat16, device_map = "auto")
tokenizer = AutoTokenizer.from_pretrained("redscroll/Mistral-7B-v0.2")

input_text = "In my younger and more vulnerable years"

input_ids = tokenizer(input_text, return_tensors = "pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens = 500, pad_token_id=tokenizer.eos_token_id, eos_token_id=tokenizer.eos_token_id)

print(tokenizer.decode(outputs[0]))

Downloads last month: 5

Safetensors

Model size

7B params

Tensor type

BF16