Image-Text-to-Text
Transformers
Safetensors
Turkish
English
lora
vision-language
math
exam
yks
turkish
Instructions to use cgalabs/yks-vlm-lora-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cgalabs/yks-vlm-lora-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="cgalabs/yks-vlm-lora-v2")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("cgalabs/yks-vlm-lora-v2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use cgalabs/yks-vlm-lora-v2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "cgalabs/yks-vlm-lora-v2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "cgalabs/yks-vlm-lora-v2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/cgalabs/yks-vlm-lora-v2
- SGLang
How to use cgalabs/yks-vlm-lora-v2 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 "cgalabs/yks-vlm-lora-v2" \ --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": "cgalabs/yks-vlm-lora-v2", "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 "cgalabs/yks-vlm-lora-v2" \ --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": "cgalabs/yks-vlm-lora-v2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use cgalabs/yks-vlm-lora-v2 with Docker Model Runner:
docker model run hf.co/cgalabs/yks-vlm-lora-v2
Download stats.json from cgalabs/yks-vlm-lora-v2: direct link, hf CLI and curl.
- Browser
- Download file 463 Bytes
-
https://huggingface.co/cgalabs/yks-vlm-lora-v2/resolve/main/stats.json
- Command line
-
hf download hf://cgalabs/yks-vlm-lora-v2/stats.json
-
curl -L -o stats.json https://huggingface.co/cgalabs/yks-vlm-lora-v2/resolve/main/stats.json
463 Bytes
| {"world_size": 1, "epochs": 3, "steps": 15, "seqs": 696, "tokens": 402027, "last_epoch_steps": 0, "last_epoch_seqs": 0, "last_epoch_tokens": 0, "total_seqs": 232, "nan_in_loss_seqs": 0, "experiment_tracking_run_id": null, "loss_ema": 0.6296908100446065, "loss_sum": 9.445362150669098, "mtp_loss_ema": 0, "mtp_loss_sum": 0, "eval_losses_avg": [0.6934893727302551, 0.6750823259353638, 0.6382126808166504, 0.6356888711452484, 0.6220795810222626, 0.6190989017486572]} |