GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
happyhappy-jun
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
happyhappy-jun
Model Tree
Qwen/Qwen3-VL-4B-Instruct
Input Modalities
Output Modalities
Supported Functionality
hl in 20260911_mt80k_ft60k_a100_hlcheckpoint-6000 (6,000 optimizer updates)13433 on the lab AWS cluster gpu26, 4 × A100Qwen/Qwen3-VL-4B-Instruct at revision
ebb281ec70b05090aa6165b016eac8ec08e71b17833e241ad7de301be5a8f41cd2aebc336368500d828d3b7482c66a737166aed4The published files are copied byte-for-byte from that checkpoint. No weights,
tokenizer entries or configuration values were changed for this upload. See
publication_manifest.json for sizes and SHA-256 checksums.
| Item | Value |
|---|---|
| Data | uvd_mtft conversation dataset of the UVD-RACER campaign (--data_flatten True) |
| Steps | 6,000 (--num_train_epochs 15 --max_steps 6000) |
| Effective batch | 128 (16 per device × gradient accumulation 2 × 4 GPUs) |
| Learning rate | 6e-5, cosine schedule, warmup ratio 0.05 (5%) |
| Weight decay | 0; --max_grad_norm 1 |
| Optimizer | adamw_torch, bf16 |
The vision encoder is unchanged from the base model; only the language model was updated.
model.safetensors (single unsharded bf16 weight file), config.json,
generation_config.json, tokenizer.json, tokenizer_config.json,
chat_template.jinja, processor_config.json.
This repository is self-sufficient for inference — model, tokenizer and processor all load from it directly:
python
from transformers import AutoProcessor, AutoModelForImageTextToTextREPO = "happyhappy-jun/qwen3-vl-4b-uvd-racer-hl6k"processor = AutoProcessor.from_pretrained(REPO)model = AutoModelForImageTextToText.from_pretrained(REPO, dtype="auto", device_map="auto")
The run wrote two exports at step 6000: the checkpoint directory
checkpoint-6000 (which the run's own completion marker designates) and a final
save_model export at the run root. The six weight/config/tokenizer files here are
copied byte-for-byte from checkpoint-6000. That directory does not contain a
processor config, so processor_config.json is copied byte-for-byte from the
run-root save_model export — the same step of the same job — purely so that
AutoProcessor.from_pretrained works against this repository. It is a
Qwen3VLProcessor config holding the Qwen2VLImageProcessor settings
(patch size 16, merge size 2, temporal patch size 2, mean/std 0.5) and the video
processor settings (fps 2, frame sampling on); on this Transformers version that
single file replaces the base repo's separate preprocessor_config.json and
video_preprocessor_config.json. No preprocessing setting was modified relative
to the base model. Per-file sizes and SHA-256 values, each tagged with its origin,
are in publication_manifest.json.
vocab.json / merges.txt are not shipped and are not needed: tokenizer.json
is self-contained, so the fast tokenizer loads without them.
Not included, by design: DeepSpeed ZeRO optimizer shards (global_step*/),
optimizer/scheduler/RNG state, trainer_state.json, training_args.bin,
training logs and the training data. This is a model export for inference,
not a complete optimizer-state resume bundle.
python
from huggingface_hub import snapshot_downloadcheckpoint_dir = snapshot_download("happyhappy-jun/qwen3-vl-4b-uvd-racer-hl6k",# revision=<commit sha of the single publication commit>)
The whole payload is submitted in one atomic commit on a freshly created
repository, so that commit's sha is the only model revision here. It cannot be
written inside this file (the text would change the commit it names); the pinned
snapshot_download(..., revision=...) snippet is recorded in the publishing
lab's publication log alongside the per-file SHA-256 values.
Upload verification covers source checksum identity, Safetensors header and tensor-offset coverage, and Hub file integrity. It is not a new GPU inference or robot rollout evaluation, and no task-success, accuracy or safety-performance claim is made by this model card.
Inherits the base model's Apache-2.0 license. Attribution: Qwen team,
Alibaba Cloud — Qwen/Qwen3-VL-4B-Instruct. This repository is an independent
derivative fine-tune and is not endorsed by the Qwen team.
Outputs are generated language and are not guaranteed to be correct or safe. Validate in simulation and use appropriate robot safety controls before any physical deployment.
| Trainable | LLM only (--tune_mm_llm True); vision tower and the multimodal projector are frozen (--tune_mm_vision False --tune_mm_mlp False) |
| Vision budget | --min_pixels 50176 --max_pixels 115200 |
| Sequence length | --model_max_length 8192, gradient checkpointing on |
| Seed | 42 |
| Runtime | DeepSpeed ZeRO stage 2 |