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/mixed-functional-summary.json from fzkun/kev-queue-v4-4b: direct link, hf CLI and curl.
- Browser
- Download file 3.08 kB
-
https://huggingface.co/fzkun/kev-queue-v4-4b/resolve/main/reports/mixed-functional-summary.json
- Command line
-
hf download hf://fzkun/kev-queue-v4-4b/reports/mixed-functional-summary.json
-
curl -L -o mixed-functional-summary.json https://huggingface.co/fzkun/kev-queue-v4-4b/resolve/main/reports/mixed-functional-summary.json
3.08 kB
| { | |
| "checkpoint": "queue-v4", | |
| "groups": { | |
| "blood_priority": { | |
| "n": 25, | |
| "correct": 25 | |
| }, | |
| "community_priority": { | |
| "n": 25, | |
| "correct": 25 | |
| }, | |
| "return_visit": { | |
| "n": 30, | |
| "correct": 29 | |
| }, | |
| "workflow_untrained": { | |
| "n": 12, | |
| "correct": 8 | |
| } | |
| }, | |
| "n_original": 92, | |
| "n_inferences": 184, | |
| "reversal_consistent": 87, | |
| "errors": [ | |
| { | |
| "id": "return_visit-random-19", | |
| "expected": 15, | |
| "predicted": 16, | |
| "p": 0.8884735107421875 | |
| }, | |
| { | |
| "id": "return_visit-random-20/reverse", | |
| "expected": 24, | |
| "predicted": 25, | |
| "p": 0.9999998807907104 | |
| }, | |
| { | |
| "id": "workflow-07", | |
| "expected": 3, | |
| "predicted": 4, | |
| "p": 1.0 | |
| }, | |
| { | |
| "id": "workflow-07/reverse", | |
| "expected": 3, | |
| "predicted": 4, | |
| "p": 0.9999973773956299 | |
| }, | |
| { | |
| "id": "workflow-08", | |
| "expected": 7, | |
| "predicted": 10, | |
| "p": 0.9917375445365906 | |
| }, | |
| { | |
| "id": "workflow-10", | |
| "expected": 2, | |
| "predicted": 10, | |
| "p": 0.9999996423721313 | |
| }, | |
| { | |
| "id": "workflow-11", | |
| "expected": 5, | |
| "predicted": 10, | |
| "p": 0.9999972581863403 | |
| } | |
| ], | |
| "seconds": 32.374245405197144, | |
| "environment": { | |
| "packages": { | |
| "torch": "2.8.0+cu128", | |
| "transformers": "5.17.0", | |
| "peft": "0.21.0", | |
| "flash-linear-attention": "0.5.2", | |
| "triton": "3.4.0", | |
| "causal-conv1d": null, | |
| "mlx": null, | |
| "mlx-lm": null | |
| }, | |
| "device": "cuda", | |
| "gpu": "NVIDIA RTX A6000", | |
| "backend": "torch", | |
| "dtype": "bfloat16", | |
| "triton_f32_default": null, | |
| "attention": "sdpa", | |
| "deltanet": { | |
| "forward": "transformers.models.qwen3_5.modeling_qwen3_5.Qwen3_5GatedDeltaNet.forward", | |
| "causal_conv1d_fn": "transformers.models.qwen3_5.modeling_qwen3_5.causal_conv1d_fn", | |
| "torch_chunk_gated_delta_rule": "fla.ops.gated_delta_rule.chunk.chunk_gated_delta_rule" | |
| } | |
| }, | |
| "online_deployed": false, | |
| "detailed_groups": { | |
| "blood_priority": { | |
| "original": { | |
| "n": 25, | |
| "correct": 25 | |
| }, | |
| "reversed": { | |
| "n": 25, | |
| "correct": 25 | |
| } | |
| }, | |
| "community_priority": { | |
| "original": { | |
| "n": 25, | |
| "correct": 25 | |
| }, | |
| "reversed": { | |
| "n": 25, | |
| "correct": 25 | |
| } | |
| }, | |
| "return_visit": { | |
| "original": { | |
| "n": 30, | |
| "correct": 29 | |
| }, | |
| "reversed": { | |
| "n": 30, | |
| "correct": 29 | |
| } | |
| }, | |
| "workflow_untrained": { | |
| "original": { | |
| "n": 12, | |
| "correct": 8 | |
| }, | |
| "reversed": { | |
| "n": 12, | |
| "correct": 11 | |
| } | |
| } | |
| }, | |
| "workflow_operations": { | |
| "late_checkin": { | |
| "n": 6, | |
| "correct": 6 | |
| }, | |
| "manual_rewait": { | |
| "n": 6, | |
| "correct": 2 | |
| } | |
| }, | |
| "audit": { | |
| "all_requests_evaluated": true, | |
| "label_free_model_requests": true, | |
| "rule_oracle_cases": 80, | |
| "input_sha256": "47b3273c2ff39a63ed85b000628e64603b919851694a12048f28442cbd090c9d" | |
| } | |
| } |