Image-Text-to-Text
PEFT
Safetensors
MLX
English
typed-decisions
jev
decision-model
vision-language
calibrated-probabilities
lora
Eval Results
Instructions to use mohit67890/imajev-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use mohit67890/imajev-4b with PEFT:
Task type is invalid.
- MLX
How to use mohit67890/imajev-4b with MLX:
# Make sure mlx-vlm is installed # pip install --upgrade mlx-vlm from mlx_vlm import load, generate from mlx_vlm.prompt_utils import apply_chat_template from mlx_vlm.utils import load_config # Load the model model, processor = load("mohit67890/imajev-4b") config = load_config("mohit67890/imajev-4b") # Prepare input image = ["http://images.cocodataset.org/val2017/000000039769.jpg"] prompt = "Describe this image." # Apply chat template formatted_prompt = apply_chat_template( processor, config, prompt, num_images=1 ) # Generate output output = generate(model, processor, formatted_prompt, image) print(output) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
imajev-4b: phase-3 adapter (rank-64 LoRA, 256-code readout, round 2 of failure-driven hard data), calibration, MLX copy, model card
c9e5f13 verified Download ckpt.json from mohit67890/imajev-4b: direct link, hf CLI and curl.
- Browser
- Download file 153 Bytes
-
https://huggingface.co/mohit67890/imajev-4b/resolve/main/ckpt.json
- Command line
-
hf download hf://mohit67890/imajev-4b/ckpt.json
-
curl -L -o ckpt.json https://huggingface.co/mohit67890/imajev-4b/resolve/main/ckpt.json
153 Bytes
| {"prefix": "r2", "step": 291, "of": 291, "dev_loss": 0.40176147454728683, "dev_accuracy": 0.83, "dev2_loss": 0.3391509154195955, "dev2_accuracy": 0.875} | |