Downloads · 30 days
33
100% of all-time downloads
Qwen3-4B-Stratos-R1-SFT
RationalPursuit/Qwen3-4B-Stratos-R1-SFT
Qwen3-4B-Stratos-R1-SFT is a text generation model from RationalPursuit. Use it when you need the model to write or continue text. It is set up for peft.
Experimental research artifact. Base: Qwen/Qwen3-4B-Instruct-2507. SFT on bespokelabs/Bespoke-Stratos-17k DeepSeek-R1 traces (14,815 paired rows). Named -SFT, not -Distill — we SFT'd on teacher traces; we did not run…
All-time downloads
33
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
- Task
- Text Generation
- Library
- peft
- Model type
- qwen3
- Access
- Public
- Created
- Aug 4, 2026
- Updated
- Oct 12, 2026
- SHA
- e59e3d7b
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
Model Card
Experimental research artifact. Base: Qwen/Qwen3-4B-Instruct-2507.
SFT on bespokelabs/Bespoke-Stratos-17k DeepSeek-R1 traces (14,815 paired rows). Named -SFT, not -Distill — we SFT'd on teacher traces; we did not run the distillation ourselves.
Eval (Stratos held-out, 508 prompts): non-termination 109/508 = 0.215; has_think_block 399/508.
The collection shares a base and recorded LoRA settings. This student retained 14,815 training questions; sampled Qwen retained 14,772 and gpt-oss retained 14,768. Teacher generation and curation conditions also differ, so comparisons do not isolate teacher identity as the sole cause of behavior differences. See the source records.
Out-of-Scope Use
Research artifact only — not intended for production use.
Framework versions
- PEFT 0.20.0
- Task
- Text Generation
- Library
- peft
- Type
- qwen3
- Created
- Aug 4, 2026
- Updated
- Oct 12, 2026