PEFT
Safetensors
Chinese
kev
queue-position
decision-model
lora
sft
permutation-consistency
chinese
Eval Results (legacy)
Instructions to use fzkun/kev-queue-v4-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use fzkun/kev-queue-v4-4b with PEFT:
from peft import PeftModel from transformers import AutoModel base_model = AutoModel.from_pretrained("Qwen/Qwen3.5-4B-Base") model = PeftModel.from_pretrained(base_model, "fzkun/kev-queue-v4-4b") - Notebooks
- Google Colab
- Kaggle
Download reports/completion-audit.json from fzkun/kev-queue-v4-4b: direct link, hf CLI and curl.
- Browser
- Download file 1.14 kB
-
https://huggingface.co/fzkun/kev-queue-v4-4b/resolve/main/reports/completion-audit.json
- Command line
-
hf download hf://fzkun/kev-queue-v4-4b/reports/completion-audit.json
-
curl -L -o completion-audit.json https://huggingface.co/fzkun/kev-queue-v4-4b/resolve/main/reports/completion-audit.json
1.14 kB
| { | |
| "passed": true, | |
| "panels": { | |
| "test": { | |
| "n": 600, | |
| "correct": 598, | |
| "families": { | |
| "return_visit": { | |
| "n": 300, | |
| "correct": 298, | |
| "accuracy": 0.9933333333333333 | |
| }, | |
| "blood_priority": { | |
| "n": 150, | |
| "correct": 150, | |
| "accuracy": 1.0 | |
| }, | |
| "community_priority": { | |
| "n": 150, | |
| "correct": 150, | |
| "accuracy": 1.0 | |
| } | |
| } | |
| }, | |
| "ood_test": { | |
| "n": 450, | |
| "correct": 449, | |
| "families": { | |
| "return_visit": { | |
| "n": 225, | |
| "correct": 224, | |
| "accuracy": 0.9955555555555555 | |
| }, | |
| "blood_priority": { | |
| "n": 112, | |
| "correct": 112, | |
| "accuracy": 1.0 | |
| }, | |
| "community_priority": { | |
| "n": 113, | |
| "correct": 113, | |
| "accuracy": 1.0 | |
| } | |
| } | |
| } | |
| }, | |
| "training_records": 7200, | |
| "optimizer_steps": 900, | |
| "fresh_eval_excludes_all_prior_patterns": true, | |
| "all_saved_data_hashes_verified": true, | |
| "go_labels_reconciled": 7050, | |
| "report_exists": true, | |
| "deployed": false | |
| } |