Zero-Shot Classification
Transformers
Safetensors
qwen3_5
image-text-to-text
auto-round
intel
quantization
4bit
decision-model
multimodal
vision
video
vllm-semantic-router
custom_code
4-bit precision
Instructions to use Vishva007/d3-edge-W4A16-AutoRound with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Vishva007/d3-edge-W4A16-AutoRound with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-classification", model="Vishva007/d3-edge-W4A16-AutoRound", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Vishva007/d3-edge-W4A16-AutoRound", trust_remote_code=True) model = AutoModelForMultimodalLM.from_pretrained("Vishva007/d3-edge-W4A16-AutoRound", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download quantization_config.json from Vishva007/d3-edge-W4A16-AutoRound: direct link, hf CLI and curl.
- Browser
- Download file 1.6 kB
-
https://huggingface.co/Vishva007/d3-edge-W4A16-AutoRound/resolve/main/quantization_config.json
- Command line
-
hf download hf://Vishva007/d3-edge-W4A16-AutoRound/quantization_config.json
-
curl -L -o quantization_config.json https://huggingface.co/Vishva007/d3-edge-W4A16-AutoRound/resolve/main/quantization_config.json
1.6 kB
| { | |
| "bits": 4, | |
| "data_type": "int", | |
| "group_size": 32, | |
| "sym": true, | |
| "iters": 1200, | |
| "autoround_version": "0.16.0", | |
| "block_name_to_quantize": "model.language_model.layers", | |
| "quant_method": "auto-round", | |
| "packing_format": "auto_round:auto_gptq", | |
| "extra_config": { | |
| "model.language_model.layers.0.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.0.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.1.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.1.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.3.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.3.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.4.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.4.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.6.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.6.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.7.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.7.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| } | |
| } | |
| } |