Downloads · 30 days
0
just1nseo/qwen3-4b-if-rlvr-subset4k-n3-ci99-outer-ep5
qwen3-4b-if-rlvr-subset4k-n3-ci99-outer-ep5 is a text generation model from just1nseo. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
This public repository contains BF16 Hugging Face exports from one of two five-epoch Qwen3-4B thinking-model experiments:
Downloads · 30 days
0
Access
Public
Updated Aug 18, 2026
Repo size
40.2 GB
Likes
0
Public
Click a slice to open those files.
.safetensors40.2 GB · 100%
From the Hugging Face model README
This public repository contains BF16 Hugging Face exports from one of two five-epoch Qwen3-4B thinking-model experiments:
The pinned best-available data contains all three independent draws for 3,865 of 4,096 prompts, two draws for 63 prompts, and the verified run-1 draw for 168 prompts. No missing draw is imputed, duplicated, or fabricated. N=3 rows use a Student-t interval with df=2, N=2 rows use df=1, and N=1 rows retain the run-1 point anchor. Every row records its effective sample count and available draws in the derived cache provenance.
All draws use temperature 1.0, top-p 0.95, top-k 20, and presence penalty 0.0. The lower reward threshold is the lower endpoint for x-only per-token mean NLL; the upper threshold is the upper endpoint for x+c per-token mean NLL. Response IDs/token counts come from draw 1; NLL and PPL fields encode the selected endpoints.
Training otherwise matches the subset4k A3 strict baseline: Qwen3-4B with thinking enabled, 4,096 rows, batch 256, 16 steps/epoch, 5 epochs, LR 1e-6, 8 rollouts, 2,048 prompt tokens, 8,192 response tokens, hard-zero lower floor, and +0.1 reward inside the valid anchor interval. Checkpoints are exported at steps 16, 32, 48, 64, and 80.
Each checkpoint lives under <experiment>/global_step_<step>/. The
corresponding _manifests/ entry records file sizes, BF16 tensor validation,
and the verified Hub commit.
Pinned additional draws: