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 training_config.json from fzkun/kev-queue-v4-4b: direct link, hf CLI and curl.
- Browser
- Download file 1.83 kB
-
https://huggingface.co/fzkun/kev-queue-v4-4b/resolve/main/training_config.json
- Command line
-
hf download hf://fzkun/kev-queue-v4-4b/training_config.json
-
curl -L -o training_config.json https://huggingface.co/fzkun/kev-queue-v4-4b/resolve/main/training_config.json
1.83 kB
| { | |
| "args": { | |
| "base": "Qwen/Qwen3.5-4B-Base", | |
| "n_per_source": 1000, | |
| "epochs": 1, | |
| "lr": 1e-05, | |
| "head_lr": 0.0, | |
| "weight_decay": 0.01, | |
| "lora": 16, | |
| "accum": 8, | |
| "holdout": "", | |
| "perm_kl": 0.03, | |
| "perm_frac": 0.25, | |
| "ord_w": 0.0, | |
| "label_smoothing": 0.0, | |
| "brier_w": 0.0, | |
| "focal_gamma": 0.0, | |
| "suite": null, | |
| "train_sources": "", | |
| "device": "cuda", | |
| "batch": 1, | |
| "dtype": "bf16", | |
| "weights_dtype": "bf16", | |
| "checkpointing": 1, | |
| "option_isolation": 0, | |
| "special_embeddings": 0, | |
| "head_dim": 256, | |
| "lora_targets": "all", | |
| "base_revision": "1001bb4d826a52d1f399e183466143f4da7b741b", | |
| "p_none": 0.0, | |
| "p_none_distract": 0.0, | |
| "p_distract": 0.0, | |
| "p_none_pair": 0.0, | |
| "none_pair_max_state": null, | |
| "synthetic_repeat": 1, | |
| "public_frac": 1.0, | |
| "anchor": "", | |
| "anchor_w": 0.0, | |
| "anchor_sources": "", | |
| "out": "/results/stage1", | |
| "data": "/data/train.jsonl", | |
| "max_state": 1280, | |
| "replay": 0, | |
| "init_from": "/prior/queue-v3", | |
| "full_ft": 0, | |
| "row_budget": 0, | |
| "shared_prefix": 0, | |
| "length_sort": 0, | |
| "pass_tokens_max": 0, | |
| "max_steps": 0, | |
| "save_every_steps": 0, | |
| "save_every_minutes": 0, | |
| "resume": 0, | |
| "stop_after": 0, | |
| "snapshot_fractions": "", | |
| "snapshot_every_steps": 0, | |
| "snapshot_dir": "", | |
| "seed": 20261010 | |
| }, | |
| "suite_sha256": null, | |
| "base_revision": "1001bb4d826a52d1f399e183466143f4da7b741b", | |
| "init_source": { | |
| "init_from": "/prior/queue-v3", | |
| "resolved": "/prior/queue-v3", | |
| "weights_sha256": "a90f62fb7bfc53133b4617e934490d501ba45a50debde2ca05c10c84fa3ff1e0", | |
| "head_sha256": "35eb06b79e002864274064fb8d9b056a9dd0fcc712ae64c446255175559fda01", | |
| "tensors": 496 | |
| }, | |
| "ordinal_objective": "ranked_probability_score", | |
| "holdout": [] | |
| } | |