Downloads · 30 days
0
CoVT-Phase2-3expert-Full
Steven668866/CoVT-Phase2-3expert-Full
CoVT-Phase2-3expert-Full 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.
Status (2026-06-29): This repo previously hosted the 3-expert CoVT Phase2 LoRA from our non-strict reproduction run. The non-strict weights were trained with a real bug — model.globalsteps was not restored on resume,…
Access
Public
Updated Jun 29, 2026
Repo size
82.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.6 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jun 28, 2026
- Updated
- Jun 29, 2026
- SHA
- bc23af3e
Model card
From the Hugging Face model README
CoVT-Phase2-3expert-Full (post-cleanup)
Status (2026-06-29): This repo previously hosted the 3-expert CoVT Phase2 LoRA from our non-strict reproduction run. The non-strict weights were trained with a real bug —
model.global_stepswas not restored on resume, leaving anchor losses ON for ~1000 extra opt-steps — and are not paper-faithful. They have been removed.
What this repo contains now
| Path | Description |
|---|---|
stage1_merged/ | Phase1 LoRA merged into Qwen2.5-VL-7B base. Clean artifact built from the (clean) Stage1 6K-step LoRA. Safe to use as the starting point for any Phase2 reproduction. |
scripts/ | Training / merge / eval scripts used in the reproduction run. |
training_src/ | CoVT modelling and trainer source (Qwen2.5-VL fork). |
runs/ | Tensorboard event files for the original non-strict run. Loss curves remain useful for diagnostics even though the final weights were buggy. |
phase2.log, sft_phase2.log | Stdout/stderr from the original Phase2 run. |
What was deleted (2026-06-29)
The entire archive_nonstrict/ subtree (42 files, ~25 GB) was deleted in commit 974103e:
archive_nonstrict/adapter_*— final non-strict adapter (buggy)archive_nonstrict/non_lora_state_dict.bin,trainer_state.json,config.json— final non-strict state (buggy)archive_nonstrict/checkpoint-9000/andarchive_nonstrict/checkpoint-10000/— intermediate non-strict checkpoints (buggy)
Reason: the bug above means anchor losses were active far past their intended schedule. The weights drift from the paper-described training recipe and should not be used or compared against the paper's numbers.
Where to get paper-faithful 3-expert Phase2 weights
Use Steven668866/CoVT-Phase2-3expert-Strict — trained after the global_steps fix.
Companion repos
- Steven668866/CoVT-3expert-Stage1-LoRA — Phase1 6K-step LoRA adapter (clean; consumed by
stage1_merged/above). - Steven668866/CoVT-Phase2-3expert-Strict — Canonical strict 3-expert Phase2 artifacts.
Caveat
This is a 3-expert variant. The CoVT paper's main configuration uses 4 experts. Numbers from these weights should not be compared 1-to-1 with the paper's headline table.
- License
- apache-2.0
- Languages
- en
- Created
- Jun 28, 2026
- Updated
- Jun 29, 2026