Instructions to use mlabonne/Mistralpaca-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mlabonne/Mistralpaca-7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="mlabonne/Mistralpaca-7B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("mlabonne/Mistralpaca-7B") model = AutoModelForCausalLM.from_pretrained("mlabonne/Mistralpaca-7B") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use mlabonne/Mistralpaca-7B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "mlabonne/Mistralpaca-7B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "mlabonne/Mistralpaca-7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/mlabonne/Mistralpaca-7B
- SGLang
How to use mlabonne/Mistralpaca-7B 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 "mlabonne/Mistralpaca-7B" \ --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": "mlabonne/Mistralpaca-7B", "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 "mlabonne/Mistralpaca-7B" \ --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": "mlabonne/Mistralpaca-7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use mlabonne/Mistralpaca-7B with Docker Model Runner:
docker model run hf.co/mlabonne/Mistralpaca-7B
OpenGVLab/InternVL3_5-30B-A3B-Instruct Abliteration
I was wondering if you have any plans to start abliterate the InternVL3_5 models—specifically the OpenGVLab/InternVL3_5-30B-A3B-Instruct version.
I’d love to help you with the abliteration process on these models. Alternatively, if you could share some insights about the methods and datasets you typically use for abliterate, that would also be super helpful.
Thanks a lot!
Thanks for responding.
I noticed that you also worked on mlabonne/Qwen3-30B-A3B-abliterated, but it was still in progress.
if you can please share the process and dataset you followed, so that I can replicate them for InternVL3_5-30B-A3B-Instruct?