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 confirmation-report.json from Maincode/matilda-jev-fp4: direct link, hf CLI and curl.
- Browser
- Download file 4 kB
-
https://huggingface.co/Maincode/matilda-jev-fp4/resolve/main/confirmation-report.json
- Command line
-
hf download hf://Maincode/matilda-jev-fp4/confirmation-report.json
-
curl -L -o confirmation-report.json https://huggingface.co/Maincode/matilda-jev-fp4/resolve/main/confirmation-report.json
4 kB
| { | |
| "complete": true, | |
| "checked_utc": "2026-10-06T15:59:45.382575+00:00", | |
| "scope": "all", | |
| "split": "confirmation", | |
| "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": 544, | |
| "agreement_percent": 97.24264705882354, | |
| "bf16_accuracy_percent": 77.57352941176471, | |
| "fp4_accuracy_percent": 76.83823529411765, | |
| "mean_KL_bf16_to_fp4": 0.011581205562651279 | |
| }, | |
| "by_domain": { | |
| "ESCI": { | |
| "n": 32, | |
| "agreement_percent": 96.875, | |
| "bf16_accuracy_percent": 59.375, | |
| "fp4_accuracy_percent": 56.25, | |
| "mean_KL_bf16_to_fp4": 0.008368359788850645 | |
| }, | |
| "HoVer": { | |
| "n": 32, | |
| "agreement_percent": 93.75, | |
| "bf16_accuracy_percent": 81.25, | |
| "fp4_accuracy_percent": 75.0, | |
| "mean_KL_bf16_to_fp4": 0.023173074279276965 | |
| }, | |
| "Habermas": { | |
| "n": 32, | |
| "agreement_percent": 100.0, | |
| "bf16_accuracy_percent": 31.25, | |
| "fp4_accuracy_percent": 31.25, | |
| "mean_KL_bf16_to_fp4": 0.02629049770095534 | |
| }, | |
| "When2Call": { | |
| "n": 32, | |
| "agreement_percent": 100.0, | |
| "bf16_accuracy_percent": 93.75, | |
| "fp4_accuracy_percent": 93.75, | |
| "mean_KL_bf16_to_fp4": 0.002222273564954566 | |
| }, | |
| "sarcasm_ar": { | |
| "n": 32, | |
| "agreement_percent": 90.625, | |
| "bf16_accuracy_percent": 62.5, | |
| "fp4_accuracy_percent": 59.375, | |
| "mean_KL_bf16_to_fp4": 0.012054604471233589 | |
| }, | |
| "old_general/choice": { | |
| "n": 32, | |
| "agreement_percent": 100.0, | |
| "bf16_accuracy_percent": 84.375, | |
| "fp4_accuracy_percent": 84.375, | |
| "mean_KL_bf16_to_fp4": 0.002750536940483584 | |
| }, | |
| "guard/humor": { | |
| "n": 32, | |
| "agreement_percent": 93.75, | |
| "bf16_accuracy_percent": 40.625, | |
| "fp4_accuracy_percent": 40.625, | |
| "mean_KL_bf16_to_fp4": 0.027150870865254688 | |
| }, | |
| "Phishing": { | |
| "n": 32, | |
| "agreement_percent": 100.0, | |
| "bf16_accuracy_percent": 96.875, | |
| "fp4_accuracy_percent": 96.875, | |
| "mean_KL_bf16_to_fp4": 0.006934639060563293 | |
| }, | |
| "old_general/noul": { | |
| "n": 32, | |
| "agreement_percent": 96.875, | |
| "bf16_accuracy_percent": 93.75, | |
| "fp4_accuracy_percent": 90.625, | |
| "mean_KL_bf16_to_fp4": 0.0035566811986626184 | |
| }, | |
| "ANLI": { | |
| "n": 32, | |
| "agreement_percent": 100.0, | |
| "bf16_accuracy_percent": 84.375, | |
| "fp4_accuracy_percent": 84.375, | |
| "mean_KL_bf16_to_fp4": 0.009098772482953045 | |
| }, | |
| "VAST": { | |
| "n": 32, | |
| "agreement_percent": 93.75, | |
| "bf16_accuracy_percent": 71.875, | |
| "fp4_accuracy_percent": 68.75, | |
| "mean_KL_bf16_to_fp4": 0.009012711907023834 | |
| }, | |
| "SATA": { | |
| "n": 32, | |
| "agreement_percent": 100.0, | |
| "bf16_accuracy_percent": 96.875, | |
| "fp4_accuracy_percent": 96.875, | |
| "mean_KL_bf16_to_fp4": 0.006667878952544886 | |
| }, | |
| "ContractNLI": { | |
| "n": 32, | |
| "agreement_percent": 93.75, | |
| "bf16_accuracy_percent": 87.5, | |
| "fp4_accuracy_percent": 93.75, | |
| "mean_KL_bf16_to_fp4": 0.005304457598214596 | |
| }, | |
| "ACOS": { | |
| "n": 32, | |
| "agreement_percent": 100.0, | |
| "bf16_accuracy_percent": 84.375, | |
| "fp4_accuracy_percent": 84.375, | |
| "mean_KL_bf16_to_fp4": 0.011603451698692325 | |
| }, | |
| "RAGTruth": { | |
| "n": 32, | |
| "agreement_percent": 100.0, | |
| "bf16_accuracy_percent": 90.625, | |
| "fp4_accuracy_percent": 90.625, | |
| "mean_KL_bf16_to_fp4": 0.006294842546801113 | |
| }, | |
| "sarcasm_en": { | |
| "n": 32, | |
| "agreement_percent": 93.75, | |
| "bf16_accuracy_percent": 68.75, | |
| "fp4_accuracy_percent": 68.75, | |
| "mean_KL_bf16_to_fp4": 0.00877219076521019 | |
| }, | |
| "guard/science": { | |
| "n": 32, | |
| "agreement_percent": 100.0, | |
| "bf16_accuracy_percent": 90.625, | |
| "fp4_accuracy_percent": 90.625, | |
| "mean_KL_bf16_to_fp4": 0.027624650743396446 | |
| } | |
| } | |
| } | |