Downloads · 30 days
20
16% of all-time downloads
Qwen3.5-35B-A3B-DAPO-RLVR-teacher
cm00cm/Qwen3.5-35B-A3B-DAPO-RLVR-teacher
Qwen3.5-35B-A3B-DAPO-RLVR-teacher is a reinforcement learning model from cm00cm. Use it for the reinforcement 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.
RLVR (GRPO) fine-tune of Qwen3.5-35B-A3B on DAPO-math-17k, trained with miles on a single 8×H200 node. This is the Phase-1 teacher for an on-policy self-distillation pipeline (see miles example examples/onpolicydistil…
All-time downloads
123
Public
Parameters
35.5B
71 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors71 GB · 100%
At a glance
- Task
- Reinforcement Learning
- License
- apache-2.0
- Model type
- qwen3_5_moe
- Access
- Public
- Created
- Jun 28, 2026
- Updated
- Jun 28, 2026
- SHA
- acf75b5b
Base models
Model card
From the Hugging Face model README
Qwen3.5-35B-A3B — DAPO RLVR Teacher (Phase 1)
RLVR (GRPO) fine-tune of Qwen3.5-35B-A3B on DAPO-math-17k, trained with
miles on a single 8×H200 node. This is the
Phase-1 teacher for an on-policy self-distillation pipeline
(see miles example examples/on_policy_distillation/qwen3_5_35b_selfdistill).
What changed vs the base
Held-out DAPO-math (512 disjoint problems, eval @ 24k cap, temperature 0.6):
| accuracy | mean response length | |
|---|---|---|
| base | 0.828 | 14,070 |
| this checkpoint | 0.887 | 6,248 |
The RLVR step (lr 1e-5, GRPO + format-agnostic boxed/Answer correctness reward, 24k rollout cap) makes the model both more accurate and ~2× more concise.
Details
- Parallelism: TP2 / PP1 / CP2 / EP8 / ETP1 (single node, world=8),
--colocate, optimizer CPU offload. - Reward: format-agnostic correctness (accepts
\boxed{}orAnswer:). - Weights only (optimizer state stripped). Standard
transformersload.
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("cm00cm/Qwen3.5-35B-A3B-DAPO-RLVR-teacher")
model = AutoModelForCausalLM.from_pretrained(
"cm00cm/Qwen3.5-35B-A3B-DAPO-RLVR-teacher", torch_dtype="bfloat16", device_map="auto")
- Task
- Reinforcement Learning
- Type
- qwen3_5_moe
- License
- apache-2.0
- Created
- Jun 28, 2026
- Updated
- Jun 28, 2026