GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
ngqtrung
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
ngqtrung
Model Tree
Qwen/Qwen3-VL-8B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Offline full-set eval (VideoMME-v1 2700 + PerceptionComp 1108 + Video-Holmes 1837 = 5645 rows), scored with the repo's vero compute_score. mean = macro-mean of the 3 bench accuracies.
Keeper = global_step_180 (peak):
| metric | mean | videomme | holmes | perceptioncomp | format |
|---|---|---|---|---|---|
| SFT-770 RL @180 (keeper) | 0.4845 | 0.6574 | 0.4513 | 0.3448 | 0.983 |
| cold-base RL keeper @80 (sibling) | 0.4918 | 0.6581 | 0.4741 | 0.3430 | — |
| stock Qwen3-VL-8B ckpt-0 (zero-shot) | 0.4444 | 0.6426 | 0.4143 | 0.2762 | — |
Trajectory (mean): flat plateau ~0.481 (±0.01) over steps 60–160, peak 0.4845 @180, then edged down (0.467 @200, 0.471 @220). Format compliance saturated ~0.97–0.98 throughout. The high reward did not convert to held-out accuracy — visible only because of the offline full-set eval.
Qwen/Qwen3-VL-8B-Instruct, warm-started from the OMR SFT checkpoint qwen3vl8b_ommr_sft_3node/checkpoint-770-hf. (SFT-770 = the stock 8B SFT'd on OpenMMReasoner reasoning data with lmms-engine — a math/visual-reasoning SFT, not a video model — used here to seed video RL.)ngquangtrung57/verl@videorl-mods. Fully-async GRPO: FSDP2 trainer + vLLM rollouter.score = 0.8·accuracy + 0.2·format (FORMAT_WEIGHT=0.2, FORMAT_MIN_THINK_CHARS=100). No KL penalty.Project verl_fully_async (entity quangtrung5705-nanyang-technological-university-singapore). Train metrics only — video val is offline, not on W&B:
https://wandb.ai/quangtrung5705-nanyang-technological-university-singapore/verl_fully_async/runs/s59ethn1
Research checkpoint — the SFT-warmstart arm of an 8B video study whose headline finding is a 7-way dead-heat at ~0.485 full-set val. This run shows SFT warm-start gives faster early convergence but no durable val edge over cold-start (which actually peaks slightly higher at 0.4918). Multiple-choice video QA, <think>…</think> then-answer format. No safety/RLHF alignment beyond the base.
python
from transformers import AutoModelForImageTextToText, AutoProcessor model_id = "ngqtrung/video-8b-grpo-sft770"model = AutoModelForImageTextToText.from_pretrained(model_id, dtype="auto", device_map="auto")processor = AutoProcessor.from_pretrained(model_id) messages = [{ "role": "user", "content": [ {"type": "video", "video": "clip.mp4"}, {"type": "text", "text": "Answer the multiple-choice question. Reason inside <think>...</think>, then give the final letter."}, ],}]inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt").to(model.device)out = model.generate(**inputs, max_new_tokens=1024)print(processor.batch_decode(out[:, inputs["input_ids"].shape[1]:], skip_special_tokens=True)[0])ngquangtrung57/verl@videorl-mods; fully-async GRPO (FSDP2 + vLLM).docs/experiments_summary_8b.md).ppo_mini_batch_size=16 × require_batches=4 × rollout.n=8 = 512 trajectories/step.GROUP_VIDEO_TRAIN_MC_24F100K (5 video-MC parquets, 24 frames / 100k pixels).1e-6, warmup 25 steps; total_epochs=2; clip_ratio 0.2 / 0.3 (clip_c=10.0); max_prompt_length=17408, max_response_length=16384; enforce_eager=true; gpu_memory_utilization=0.75; staleness 0.4.test_freq=10000); video val is offline full-set eval on a dedicated 8×H100 node (vLLM TP1), every 20 fit-steps.