Downloads · 30 days
59
7% of all-time downloads
CoVT-Phase2-3expert-Strict
Steven668866/CoVT-Phase2-3expert-Strict
CoVT-Phase2-3expert-Strict is a machine learning model from Steven668866. Use it for the machine 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.
Canonical strict 3-expert Phase2 LoRA + merged weights for our CoVT reproduction. Trained after the model.globalsteps-on-resume bug was fixed, so the anchor-loss schedule matches the paper.
All-time downloads
897
Public
Repo size
82.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin50 GB · 50%
At a glance
- License
- apache-2.0
- Model type
- qwen2_5_vl
- Access
- Public
- Created
- Jun 28, 2026
- Updated
- Jun 29, 2026
- SHA
- 51e0b934
Model card
From the Hugging Face model README
CoVT-Phase2-3expert-Strict
Canonical strict 3-expert Phase2 LoRA + merged weights for our CoVT reproduction. Trained after the model.global_steps-on-resume bug was fixed, so the anchor-loss schedule matches the paper.
Contents
| Path | Description |
|---|---|
adapter_config.json, adapter_model.safetensors, non_lora_state_dict.bin | Final Phase2 LoRA adapter + non-LoRA state. |
checkpoint-9000/, checkpoint-10000/ | Intermediate Phase2 checkpoints (LoRA + DeepSpeed Zero-2 optimizer states). |
stage4_merged_strict/ | Final adapter merged into Qwen2.5-VL-7B base — ready for inference / eval. |
eval_stage4_strict/ | VLMEvalKit results on CV-Bench 2D / 3D. |
config.json, config_patched.py, trainer_patched.py, trainer_state.json | Final config and trainer state. |
runs/ | Tensorboard event files. |
*.log | Phase2 strict training / eval / continuation logs. |
Companion repos
- Steven668866/CoVT-3expert-Stage1-LoRA — Phase1 6K-step LoRA adapter (clean).
- Steven668866/CoVT-Phase2-3expert-Full — Historical repo from the non-strict run; buggy adapter weights have been removed (2026-06-29). Only the clean Phase1 merge + scripts + logs remain there.
Caveat
This is a 3-expert variant of CoVT. The paper's main configuration uses 4 experts, so absolute numbers are not directly comparable to the paper's headline table.
- Type
- qwen2_5_vl
- License
- apache-2.0
- Languages
- en
- Created
- Jun 28, 2026
- Updated
- Jun 29, 2026