Downloads · 30 days
5
25% of all-time downloads
eh-qwen3-4b-clean-sft-seed2-merged-16bit
professorsynapse/eh-qwen3-4b-clean-sft-seed2-merged-16bit
eh-qwen3-4b-clean-sft-seed2-merged-16bit is a machine learning model from professorsynapse. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Status: exploratory response-confidence track. The seed-2 merged 16-bit clean-schema-SFT base of the GRPO three-seed confirmatory block (experiments/grpo-three-seed-confirmatory, resolved 2026-08-07). Trained from uns…
All-time downloads
20
Public
Parameters
4B
8.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors8 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Aug 15, 2026
- Updated
- Aug 15, 2026
- SHA
- 331c3d55
Base models
Model card
From the Hugging Face model README
eh-qwen3-4b-clean-sft-seed2-merged-16bit
Status: exploratory response-confidence track. The seed-2 merged 16-bit
clean-schema-SFT base of the GRPO three-seed confirmatory block
(experiments/grpo-three-seed-confirmatory, resolved 2026-08-07). Trained
from unsloth/Qwen3-4B-bnb-4bit on the
professorsynapse/epistemic-humility-phase1
data at seed 2, then merged to 16-bit.
The adapter
professorsynapse/eh-qwen3-4b-clean-sft-grpo-v2-seed2-lora
loads on THIS base. Per-seed lineage is a registered rule of the block
(Amendment G §3, carried forward): each seed rebuilds its own complete
lineage from the foundation model; never mix this base with another seed's
adapters. Its own eval reads refusal recall 89.92% / answer-on-unknown
10.08% on the full 3,369-row SelfAware set under the response-confidence
contract.
Full record: experiments/grpo-three-seed-confirmatory/AMENDMENT.md and
NOTEBOOK.md in the source repository.
- Type
- qwen3
- License
- apache-2.0
- Created
- Aug 15, 2026
- Updated
- Aug 15, 2026