VLR-CVC

CVC-Qwen3.5-35B-A3B

README

License: apache-2.0

Training

Instruct SFT: one pass over the LLaVA-OneVision-1.5-Instruct blend (197 sources), 2274 steps at sequence length 16384.
Decay anneal: 326 further steps over the same sources, reweighted towards document and OCR data, with the learning rate decayed to zero.
RL: one pass over ViRL39K, 57 steps, with the molt RL framework.
- Data: single-image rows that a trained 32B model does not always solve (PassRate < 1), deduplicated by image hash and question, with every row whose image matches a MathVista testmini image removed. 15,919 training prompts.
- Reward: 1 if the \boxed{} answer matches the reference (math-equivalence and multiple-choice matching), else 0.
- Algorithm: REINFORCE with a group-mean baseline (8 answers per prompt), PPO-style clipping (0.2 / 0.28), no KL penalty. Groups where all 8 answers score the same are dropped and refilled. Training-inference mismatch is handled with sequence-level importance-ratio masking, and MoE routing is replayed from inference.
- 128 prompts per step, up to 8192 new tokens, temperature 1.0, Adam with a constant learning rate of 1e-6, vision encoder frozen.
- 32 nodes of JUPITER (4x GH200 per node) for 4.9 hours.

Results

4 answers per question at temperature 1.0, up to 16384 new tokens, pass@1 averaged over the answers. "SFT" is the model after stage 2.

Table with columns: Benchmark, SFT, CVC-Qwen3.5-35B-A3B, Qwen3.5-35B-A3B
Benchmark	SFT	CVC-Qwen3.5-35B-A3B	Qwen3.5-35B-A3B
MathVista testmini (1000)	0.701	0.815	0.852
- multiple choice (540)	0.703	0.862	0.901
- free form (460)	0.698	0.760	0.795
MathVista median answer length (tokens)	633	566	1652

The RL stage targets visual math. GPQA Diamond (text-only science) is unchanged.

General multimodal benchmarks

lmms-eval + vLLM, thinking enabled, max_new_tokens=2048 (more than any of the three models uses, so no answer is cut short). mmbench_en_dev and hallusion_bench_image are excluded: their GPT-judge scoring needs internet access the compute nodes don't have. Bold marks the best per row.

Table with columns: Benchmark, SFT, CVC-Qwen3.5-35B-A3B, Qwen3.5-35B-A3B
Benchmark	SFT	CVC-Qwen3.5-35B-A3B	Qwen3.5-35B-A3B
mmmu_val (acc)	0.6811	0.6967	0.6267
mme (perception)	1754.0	1807.2	1560.8
mme (cognition)	772.5	775.4	751.8
ai2d (exact_match)	0.8562	0.8818

Although RL trained only on visual math, it improved most general benchmarks (textvqa +13.5, mmstar +3.0, chartqa +3.8) while generating 40% fewer answer tokens than the SFT model. Thinking matters for this model: with thinking turned off (enable_thinking=False), docvqa drops to 0.55 and textvqa to 0.52.

Notes

Uses the Qwen3.5 chat template, which renders <think> blocks on every assistant turn. Prompt for a final answer in \boxed{} to match the RL training format.
eos_token is <|im_end|>, and generation_config.json stops on both <|im_end|> (248046) and <|endoftext|> (248044).
With vLLM, set mamba_ssm_cache_dtype="float32" for the linear-attention state, as done in training and evaluation.

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

VLR-CVC

Model Tree

Base

VLR-CVC/CVC-Qwen3.5-35B-A3B-SFT

Fine-tuned

this model

Input Modalities

TextImageVideo

Output Modalities

Text

Supported Functionality