Feature Extraction
Transformers
Safetensors
qwen3_5
matilda
jev
fp4
quantized
maincode
8-bit precision
Instructions to use Maincode/matilda-jev-fp4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Maincode/matilda-jev-fp4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Maincode/matilda-jev-fp4")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("Maincode/matilda-jev-fp4") model = AutoModel.from_pretrained("Maincode/matilda-jev-fp4", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download KERNEL_AUDIT.json from Maincode/matilda-jev-fp4: direct link, hf CLI and curl.
- Browser
- Download file 658 Bytes
-
https://huggingface.co/Maincode/matilda-jev-fp4/resolve/main/KERNEL_AUDIT.json
- Command line
-
hf download hf://Maincode/matilda-jev-fp4/KERNEL_AUDIT.json
-
curl -L -o KERNEL_AUDIT.json https://huggingface.co/Maincode/matilda-jev-fp4/resolve/main/KERNEL_AUDIT.json
658 Bytes
| { | |
| "complete": true, | |
| "device": "AMD Instinct MI355X", | |
| "tests": [ | |
| { | |
| "shape": [ | |
| 128, | |
| 128 | |
| ], | |
| "bit_identical_to_ModelOpt": true, | |
| "GEMM_bit_identical": true | |
| }, | |
| { | |
| "shape": [ | |
| 6144, | |
| 5120 | |
| ], | |
| "bit_identical_to_ModelOpt": true, | |
| "GEMM_bit_identical": true | |
| }, | |
| { | |
| "shape": [ | |
| 5120, | |
| 17408 | |
| ], | |
| "bit_identical_to_ModelOpt": true, | |
| "GEMM_bit_identical": true | |
| } | |
| ], | |
| "all_fp4_codes_and_finite_positive_scale_codes_checked": true, | |
| "runtime_compute": "FP4 weight storage; one-matrix Triton dequantization followed by BF16 GEMM" | |
| } | |