ffmpeg-nl2cmd-0.8B

Qwen3.5 with a two-layer MLP-Mixer decision head. Supports text, images and videos, and returns Choice, Noul and Score decisions. Multiple questions can share one state encoding with execution="sharedstate". Trained on millions of samples. Install Python 3.10+, PyTorch, Transformers 5.4.0, torchvision, Pillow and av. Flash Attention 2 is optional with a compatible CUDA build. The model contains its tokenizer, processor and custom inference code; a separate base-model download is unnecessary. Use attnimplementation="flashattention2" for Flash Attention, or execution="question" for independent questions. Video defaults to 16 frames. Image/video request examples and training instructions are…

Model · Image and text to text

Qwen3.5-0.8B

Qwen

Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance. Qwen3.5 represents a significant leap forward, integrating breakthroughs in multimodal learning, architectural efficiency, reinforcement learning scale, and global accessibility to empower developers and enterprises with unprecedented capability and efficiency. For more details, please refer to our blog post Qwen3.5. WMT24++: a harder subset of WMT24 after difficulty labeling and rebalancing; we report the averaged scores on 55 languages using XCOMET-XXL. Empty cells (--) indicate scores not yet available or not applicable. Scores of Qwen3.5 models are reported…

Model · Image and text to text

povl-opd-scale05

Cheney Wong

On-policy distillation. The weight delta learned by the teacher was merged into the SFT base with an extra scale of 0.5, the best point of an alpha sweep (0.25 -> +0.32, 0.5 -> +0.44, 0.75 -> -0.29, 1.5 -> -3.01 with t = -12.42). Fine-tuned from CheneyWong/povl-sft-2d-merge, which is NOT the RL checkpoint -- the teacher delta was merged into the SFT base, which is why it neither clearly beats nor clearly follows round 2. Base = the unmodified base model. Public datasets only; the project's self-built benchmarks are excluded. (~0.22 here) measures how well the model reproduces empty cells and should be ignored -- a perturbation test shows a structurally perfect prediction that correctly…

Model · Image and text to text

povl-rl-gsapo-200

Cheney Wong

Reinforcement learning round 2, GSAPO, 200 steps. The delivered model of that round. Equal-weight TEDS 0.8473 / TEDS-Struct 0.9078 over 33,545 samples. Fine-tuned from CheneyWong/povl-rl-dapo-400, which is RL round 1 -- the stages form a single linear chain. Base = the unmodified base model. Public datasets only; the project's self-built benchmarks are excluded. (~0.22 here) measures how well the model reproduces empty cells and should be ignored -- a perturbation test shows a structurally perfect prediction that correctly reads the visible text scores 0.33 TEDS / 1.00 TEDS-S. Only the TEDS-S column is meaningful for that dataset. Rejected at the gate. The one substantive gap: every…

Model · Image and text to text

povl-rl-dapo-400

Cheney Wong

Reinforcement learning round 1, DAPO algorithm, 400 steps. Fine-tuned from CheneyWong/povl-dpo-2ep, which is its own immediate predecessor in the same run. Base = the unmodified base model. Public datasets only; the project's self-built benchmarks are excluded. (~0.22 here) measures how well the model reproduces empty cells and should be ignored -- a perturbation test shows a structurally perfect prediction that correctly reads the visible text scores 0.33 TEDS / 1.00 TEDS-S. Only the TEDS-S column is meaningful for that dataset. Only works with DAPO's dynamic sampling. The first attempt with GSAPO had 78% of groups contributing zero gradient (49.0% saturated, 16.5% identical rewards, 12.6%…

Model · Image and text to text

povl-dpo-2ep

Cheney Wong

Direct preference optimisation on top of the corrective SFT, 2 epochs over 8,383 preference pairs. Intended to move the model from 'roughly right structure' to 'exactly right structure'. Fine-tuned from CheneyWong/povl-sft-2d-merge, which is its own immediate predecessor in the same run. Base = the unmodified base model. Public datasets only; the project's self-built benchmarks are excluded. (~0.22 here) measures how well the model reproduces empty cells and should be ignored -- a perturbation test shows a structurally perfect prediction that correctly reads the visible text scores 0.33 TEDS / 1.00 TEDS-S. Only the TEDS-S column is meaningful for that dataset. The gain is within sampling…