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 development-report.json from Maincode/matilda-jev-fp4: direct link, hf CLI and curl.
- Browser
- Download file 4.45 kB
-
https://huggingface.co/Maincode/matilda-jev-fp4/resolve/main/development-report.json
- Command line
-
hf download hf://Maincode/matilda-jev-fp4/development-report.json
-
curl -L -o development-report.json https://huggingface.co/Maincode/matilda-jev-fp4/resolve/main/development-report.json
4.45 kB
| { | |
| "complete": true, | |
| "checked_utc": "2026-10-06T15:57:51.614032+00:00", | |
| "scope": "all", | |
| "split": "development", | |
| "backend": "FP4 packed weights, BF16 activations/GEMM, Triton per-matrix dequantization on AMD", | |
| "same_native_prompt_readout_temperature_API": true, | |
| "hardware_speed_validated": false, | |
| "full_decision_index": null, | |
| "overall": { | |
| "n": 608, | |
| "agreement_percent": 95.88815789473684, | |
| "bf16_accuracy_percent": 80.92105263157895, | |
| "fp4_accuracy_percent": 81.57894736842105, | |
| "mean_KL_bf16_to_fp4": 0.015593464629358985 | |
| }, | |
| "by_domain": { | |
| "ACOS": { | |
| "n": 32, | |
| "agreement_percent": 93.75, | |
| "bf16_accuracy_percent": 78.125, | |
| "fp4_accuracy_percent": 84.375, | |
| "mean_KL_bf16_to_fp4": 0.013701164049475172 | |
| }, | |
| "When2Call": { | |
| "n": 32, | |
| "agreement_percent": 100.0, | |
| "bf16_accuracy_percent": 93.75, | |
| "fp4_accuracy_percent": 93.75, | |
| "mean_KL_bf16_to_fp4": 0.0016987235865958965 | |
| }, | |
| "guard/mmlu_development": { | |
| "n": 32, | |
| "agreement_percent": 96.875, | |
| "bf16_accuracy_percent": 68.75, | |
| "fp4_accuracy_percent": 71.875, | |
| "mean_KL_bf16_to_fp4": 0.04259847080039246 | |
| }, | |
| "ContractNLI": { | |
| "n": 32, | |
| "agreement_percent": 100.0, | |
| "bf16_accuracy_percent": 93.75, | |
| "fp4_accuracy_percent": 93.75, | |
| "mean_KL_bf16_to_fp4": 0.010235464961968524 | |
| }, | |
| "VAST": { | |
| "n": 32, | |
| "agreement_percent": 96.875, | |
| "bf16_accuracy_percent": 90.625, | |
| "fp4_accuracy_percent": 87.5, | |
| "mean_KL_bf16_to_fp4": 0.013530445497465765 | |
| }, | |
| "sarcasm_en": { | |
| "n": 32, | |
| "agreement_percent": 96.875, | |
| "bf16_accuracy_percent": 68.75, | |
| "fp4_accuracy_percent": 65.625, | |
| "mean_KL_bf16_to_fp4": 0.010841849286577542 | |
| }, | |
| "ANLI": { | |
| "n": 32, | |
| "agreement_percent": 90.625, | |
| "bf16_accuracy_percent": 81.25, | |
| "fp4_accuracy_percent": 87.5, | |
| "mean_KL_bf16_to_fp4": 0.007467320146816308 | |
| }, | |
| "HoVer": { | |
| "n": 32, | |
| "agreement_percent": 100.0, | |
| "bf16_accuracy_percent": 96.875, | |
| "fp4_accuracy_percent": 96.875, | |
| "mean_KL_bf16_to_fp4": 0.010262760266491694 | |
| }, | |
| "RAGTruth": { | |
| "n": 32, | |
| "agreement_percent": 100.0, | |
| "bf16_accuracy_percent": 93.75, | |
| "fp4_accuracy_percent": 93.75, | |
| "mean_KL_bf16_to_fp4": 0.0026213688997479747 | |
| }, | |
| "ESCI": { | |
| "n": 32, | |
| "agreement_percent": 96.875, | |
| "bf16_accuracy_percent": 53.125, | |
| "fp4_accuracy_percent": 53.125, | |
| "mean_KL_bf16_to_fp4": 0.013929468238803712 | |
| }, | |
| "guard/science": { | |
| "n": 32, | |
| "agreement_percent": 100.0, | |
| "bf16_accuracy_percent": 96.875, | |
| "fp4_accuracy_percent": 96.875, | |
| "mean_KL_bf16_to_fp4": 0.00532867118309089 | |
| }, | |
| "guard/solver_development": { | |
| "n": 32, | |
| "agreement_percent": 96.875, | |
| "bf16_accuracy_percent": 93.75, | |
| "fp4_accuracy_percent": 90.625, | |
| "mean_KL_bf16_to_fp4": 0.009307941474104636 | |
| }, | |
| "guard/chess_development": { | |
| "n": 32, | |
| "agreement_percent": 84.375, | |
| "bf16_accuracy_percent": 53.125, | |
| "fp4_accuracy_percent": 46.875, | |
| "mean_KL_bf16_to_fp4": 0.04428748497978523 | |
| }, | |
| "Habermas": { | |
| "n": 32, | |
| "agreement_percent": 75.0, | |
| "bf16_accuracy_percent": 21.875, | |
| "fp4_accuracy_percent": 40.625, | |
| "mean_KL_bf16_to_fp4": 0.041353885293041556 | |
| }, | |
| "guard/broad_development": { | |
| "n": 32, | |
| "agreement_percent": 100.0, | |
| "bf16_accuracy_percent": 90.625, | |
| "fp4_accuracy_percent": 90.625, | |
| "mean_KL_bf16_to_fp4": 0.016964693950754887 | |
| }, | |
| "SATA": { | |
| "n": 32, | |
| "agreement_percent": 100.0, | |
| "bf16_accuracy_percent": 93.75, | |
| "fp4_accuracy_percent": 93.75, | |
| "mean_KL_bf16_to_fp4": 0.005437098679933294 | |
| }, | |
| "Phishing": { | |
| "n": 32, | |
| "agreement_percent": 100.0, | |
| "bf16_accuracy_percent": 100.0, | |
| "fp4_accuracy_percent": 100.0, | |
| "mean_KL_bf16_to_fp4": 0.0025803647593062337 | |
| }, | |
| "guard/general_development": { | |
| "n": 32, | |
| "agreement_percent": 100.0, | |
| "bf16_accuracy_percent": 87.5, | |
| "fp4_accuracy_percent": 87.5, | |
| "mean_KL_bf16_to_fp4": 0.003838940957747038 | |
| }, | |
| "sarcasm_ar": { | |
| "n": 32, | |
| "agreement_percent": 93.75, | |
| "bf16_accuracy_percent": 81.25, | |
| "fp4_accuracy_percent": 75.0, | |
| "mean_KL_bf16_to_fp4": 0.040289710945721875 | |
| } | |
| } | |
| } | |