Instructions to use lelapa/InkubaLM-0.4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lelapa/InkubaLM-0.4B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="lelapa/InkubaLM-0.4B", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("lelapa/InkubaLM-0.4B", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("lelapa/InkubaLM-0.4B", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use lelapa/InkubaLM-0.4B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "lelapa/InkubaLM-0.4B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "lelapa/InkubaLM-0.4B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/lelapa/InkubaLM-0.4B
- SGLang
How to use lelapa/InkubaLM-0.4B 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 "lelapa/InkubaLM-0.4B" \ --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": "lelapa/InkubaLM-0.4B", "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 "lelapa/InkubaLM-0.4B" \ --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": "lelapa/InkubaLM-0.4B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use lelapa/InkubaLM-0.4B with Docker Model Runner:
docker model run hf.co/lelapa/InkubaLM-0.4B
Cannot access to repo while fine tuning with Unsloth and SFT
I'm facing this issue : Access to model lelapa/InkubaLM-0.4B is restricted. You must be authenticated to access it. - silently ignoring the lookup for the file config.json in lelapa/InkubaLM-0.4B.
warnings.warn(
/usr/local/lib/python3.10/dist-packages/peft/utils/save_and_load.py:218: UserWarning: Could not find a config file in lelapa/InkubaLM-0.4B - will assume that the vocabulary was not modified.
warnings.warn(
While i'm doing fine-tuning using Unsloth. I have well specify the HG_TOKEN in the model and tokenizer phase. Do i need to add a token too for in SFTcode ?
Hey @Atnafu , not yet, i still have the same issue
The error message is :
/usr/local/lib/python3.10/dist-packages/peft/utils/other.py:619: UserWarning: Unable to fetch remote file due to the following error 401 Client Error. (Request ID: Root=1-66ee9848-33da7ec03de9cdf53b092eb9;0749b44a-f495-484d-9e0a-3b585e45ae38)
Cannot access gated repo for url https://huggingface.co/lelapa/InkubaLM-0.4B/resolve/main/config.json.
Access to model lelapa/InkubaLM-0.4B is restricted. You must have access to it and be authenticated to access it. Please log in. - silently ignoring the lookup for the file config.json in lelapa/InkubaLM-0.4B.
warnings.warn(
/usr/local/lib/python3.10/dist-packages/peft/utils/save_and_load.py:218: UserWarning: Could not find a config file in lelapa/InkubaLM-0.4B - will assume that the vocabulary was not modified.
warnings.warn(
/usr/local/lib/python3.10/dist-packages/peft/utils/other.py:619: UserWarning: Unable to fetch remote file due to the following error 401 Client Error. (Request ID: Root=1-66ee9953-1febd5d36d4541194c30a2cd;909de8c4-808c-4cd4-ba9b-53ee822796f6)
create hugging face credentials and login to your account with google colab to use gated repo. i think that will fix the issue
