Downloads · 30 days
0
rlcr-readout-qwen3.5-4b-math-rlcr
qcz/rlcr-readout-qwen3.5-4b-math-rlcr
rlcr-readout-qwen3.5-4b-math-rlcr is a reinforcement learning model from qcz. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
Research checkpoints for the RLCR readout project. Each iter subfolder is a complete Hugging Face checkpoint at the indicated completed rollout count. RLVR and RLCR use the same answer-and-confidence prompt and CISPO…
Access
Public
Updated Sep 5, 2026
Repo size
43 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors46.6 GB · 100%
At a glance
- Task
- Reinforcement Learning
- Library
- transformers
- Access
- Public
- Created
- Sep 5, 2026
- Updated
- Sep 5, 2026
- SHA
- 17a8f573
Model card
From the Hugging Face model README
qwen3.5-4b_math_rlcr
Research checkpoints for the RLCR readout project. Each iter_* subfolder is a complete
Hugging Face checkpoint at the indicated completed rollout count. RLVR and RLCR use the
same answer-and-confidence prompt and CISPO optimization. These are experimental weights;
mechanistic conclusions require the project's corrected evaluations and controls.
Each folder includes validation.json with CPU tensor checks and SHA-256 file hashes.
For Qwen3.5, visual and disabled MTP tensors remain those of the original model; only the
autoregressive text policy was trained, without speculative decoding or MTP training.
Load a checkpoint with subfolder="iter_100" and its own tokenizer/chat template.
The subfolder preserves the original model's license, notices and README for attribution;
this root card describes the research post-training applied to those weights.
- Task
- Reinforcement Learning
- Library
- transformers
- Created
- Sep 5, 2026
- Updated
- Sep 5, 2026