Instructions to use dan-kwiat/Codestral-22B-v0.1-hf-FIM-fix-awq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dan-kwiat/Codestral-22B-v0.1-hf-FIM-fix-awq with Transformers:

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

pipe = pipeline("text-generation", model="dan-kwiat/Codestral-22B-v0.1-hf-FIM-fix-awq")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dan-kwiat/Codestral-22B-v0.1-hf-FIM-fix-awq")
model = AutoModelForCausalLM.from_pretrained("dan-kwiat/Codestral-22B-v0.1-hf-FIM-fix-awq")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use dan-kwiat/Codestral-22B-v0.1-hf-FIM-fix-awq with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dan-kwiat/Codestral-22B-v0.1-hf-FIM-fix-awq"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dan-kwiat/Codestral-22B-v0.1-hf-FIM-fix-awq",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/dan-kwiat/Codestral-22B-v0.1-hf-FIM-fix-awq

SGLang

How to use dan-kwiat/Codestral-22B-v0.1-hf-FIM-fix-awq 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 "dan-kwiat/Codestral-22B-v0.1-hf-FIM-fix-awq" \
    --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": "dan-kwiat/Codestral-22B-v0.1-hf-FIM-fix-awq",
		"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 "dan-kwiat/Codestral-22B-v0.1-hf-FIM-fix-awq" \
        --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": "dan-kwiat/Codestral-22B-v0.1-hf-FIM-fix-awq",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use dan-kwiat/Codestral-22B-v0.1-hf-FIM-fix-awq with Docker Model Runner:
```
docker model run hf.co/dan-kwiat/Codestral-22B-v0.1-hf-FIM-fix-awq
```

Codestral-22B-v0.1-hf-FIM-fix-awq / model-00002-of-00003.safetensors

dan-kwiat

Upload folder using huggingface_hub

e2a66cf verified almost 2 years ago

download

history blame contribute delete

5 GB

This file is stored with Xet . It is too big to display, but you can still download it.

Xet Pointer Details

( Raw pointer file )

Xet hash:: 70fcfc3bd2d9a8448526ac04a5d8a1ed7da0aa9adcc79c122e48cdaec24cfaa5
Size of remote file:: 5 GB
SHA256:: 424a1fcbff9b7d2f7c709141365f0b31bcd78250a714fc04223ae04804f24740

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.