Image-Text-to-Text
Transformers
English
mllama
text-generation-inference
unsloth
4-bit precision
bitsandbytes
Instructions to use timdzhum/unsloth_finetune with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use timdzhum/unsloth_finetune with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="timdzhum/unsloth_finetune")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("timdzhum/unsloth_finetune") model = AutoModelForMultimodalLM.from_pretrained("timdzhum/unsloth_finetune", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use timdzhum/unsloth_finetune with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "timdzhum/unsloth_finetune" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "timdzhum/unsloth_finetune", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/timdzhum/unsloth_finetune
- SGLang
How to use timdzhum/unsloth_finetune 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 "timdzhum/unsloth_finetune" \ --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": "timdzhum/unsloth_finetune", "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 "timdzhum/unsloth_finetune" \ --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": "timdzhum/unsloth_finetune", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Unsloth Desktop
- Docker Model Runner
How to use timdzhum/unsloth_finetune with Docker Model Runner:
docker model run hf.co/timdzhum/unsloth_finetune
Download generation_config.json from timdzhum/unsloth_finetune: direct link, hf CLI and curl.
- Browser
- Download file 210 Bytes
-
https://huggingface.co/timdzhum/unsloth_finetune/resolve/main/generation_config.json
- Command line
-
hf download hf://timdzhum/unsloth_finetune/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/timdzhum/unsloth_finetune/resolve/main/generation_config.json
210 Bytes
| { | |
| "bos_token_id": 128000, | |
| "do_sample": true, | |
| "eos_token_id": [ | |
| 128001, | |
| 128008, | |
| 128009 | |
| ], | |
| "pad_token_id": 128004, | |
| "temperature": 0.6, | |
| "top_p": 0.9, | |
| "transformers_version": "4.47.1" | |
| } | |