Instructions to use failspy/Codestral-22B-v0.1-abliterated-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use failspy/Codestral-22B-v0.1-abliterated-v3 with Transformers:

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

pipe = pipeline("text-generation", model="failspy/Codestral-22B-v0.1-abliterated-v3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("failspy/Codestral-22B-v0.1-abliterated-v3")
model = AutoModelForCausalLM.from_pretrained("failspy/Codestral-22B-v0.1-abliterated-v3", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use failspy/Codestral-22B-v0.1-abliterated-v3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "failspy/Codestral-22B-v0.1-abliterated-v3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "failspy/Codestral-22B-v0.1-abliterated-v3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/failspy/Codestral-22B-v0.1-abliterated-v3

SGLang

How to use failspy/Codestral-22B-v0.1-abliterated-v3 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 "failspy/Codestral-22B-v0.1-abliterated-v3" \
    --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": "failspy/Codestral-22B-v0.1-abliterated-v3",
		"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 "failspy/Codestral-22B-v0.1-abliterated-v3" \
        --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": "failspy/Codestral-22B-v0.1-abliterated-v3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use failspy/Codestral-22B-v0.1-abliterated-v3 with Docker Model Runner:
```
docker model run hf.co/failspy/Codestral-22B-v0.1-abliterated-v3
```

refused more than original

by Insanelycool - opened Jun 5, 2024

Discussion

Insanelycool

Jun 5, 2024

•

edited Jun 5, 2024

It might just be the model but this might be one of the worst coding models ive tried. it will refuse to code, claim things are hard and just generalize too much. even the non obliterated one. Just poor in general compared to most others from the little testing ive done so far. To be fair I'm simply asking it to code a snake game in various languages to test it (one at a time of course).

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment