Instructions to use ggml-org-dev/tiny-kev-4b-for-testing with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use ggml-org-dev/tiny-kev-4b-for-testing with PEFT:
from peft import PeftModel from transformers import AutoModel base_model = AutoModel.from_pretrained("ggml-org-dev/tiny-Qwen3.5-4B-Base-for-testing") model = PeftModel.from_pretrained(base_model, "ggml-org-dev/tiny-kev-4b-for-testing") - Notebooks
- Google Colab
- Kaggle
Download training_config.json from ggml-org-dev/tiny-kev-4b-for-testing: direct link, hf CLI and curl.
- Browser
- Download file 1.87 kB
-
https://huggingface.co/ggml-org-dev/tiny-kev-4b-for-testing/resolve/main/training_config.json
- Command line
-
hf download hf://ggml-org-dev/tiny-kev-4b-for-testing/training_config.json
-
curl -L -o training_config.json https://huggingface.co/ggml-org-dev/tiny-kev-4b-for-testing/resolve/main/training_config.json
1.87 kB
| { | |
| "args": { | |
| "base": "ggml-org-dev/tiny-Qwen3.5-4B-Base-for-testing", | |
| "n_per_source": 1000, | |
| "epochs": 1, | |
| "lr": 2e-05, | |
| "head_lr": 0.0, | |
| "weight_decay": 0.01, | |
| "lora": 16, | |
| "accum": 4, | |
| "holdout": "", | |
| "perm_kl": 0.0, | |
| "perm_frac": 0.3, | |
| "ord_w": 0.0, | |
| "label_smoothing": 0.0, | |
| "brier_w": 0.0, | |
| "focal_gamma": 0.0, | |
| "suite": "/root/evals/v7/decision-v7", | |
| "train_sources": "", | |
| "device": "cuda", | |
| "batch": 2, | |
| "dtype": "bf16", | |
| "weights_dtype": "fp32", | |
| "checkpointing": 1, | |
| "option_isolation": 0, | |
| "special_embeddings": 0, | |
| "head_dim": 256, | |
| "lora_targets": "all", | |
| "lora_placement": "full", | |
| "base_revision": "8b286693e48ab9a31ef87a17f5ef980af233ccc3", | |
| "p_none": 0.1, | |
| "p_none_distract": 0.12, | |
| "p_distract": 0.15, | |
| "p_none_pair": 0.25, | |
| "synthetic_repeat": 1, | |
| "public_frac": 1.0, | |
| "anchor": "", | |
| "anchor_w": 0.0, | |
| "anchor_sources": "", | |
| "out": "/runs/r10-skills/00-trial-0/checkpoint", | |
| "data": "evals/round10/skills/train.jsonl", | |
| "max_state": 7552, | |
| "replay": 4000, | |
| "init_from": "jaredpalmer/kev-4b@957b91e762e883935830246eeb02381f9d2694b6", | |
| "seed": 1 | |
| }, | |
| "suite_sha256": "a8f50e481b7d90b97da049e0ff6a01cee2f1ed204aed61a8265af0edbb5514d2", | |
| "base_revision": "8b286693e48ab9a31ef87a17f5ef980af233ccc3", | |
| "init_source": { | |
| "init_from": "jaredpalmer/kev-4b@957b91e762e883935830246eeb02381f9d2694b6", | |
| "resolved": "/__modal/volumes/vo-kEMu8BkBAIrorAQI6V8f2D/hub/models--jaredpalmer--kev-4b/snapshots/957b91e762e883935830246eeb02381f9d2694b6", | |
| "adapter_sha256": "c2c99077b58cd4a604304b743b7db5391187ef1d58e575f90c554c744aa23d65", | |
| "head_sha256": "9a3051c3676f0be29d885935b6f50c287f7acf04e3cb29a6fed82ca3e5540b7e", | |
| "adapter_tensors": 496 | |
| }, | |
| "ordinal_objective": "ranked_probability_score", | |
| "holdout": [] | |
| } | |