Downloads · 30 days
6
18% of all-time downloads
liuyihong/qwen3-vl-32b-proposer-sr-lora
qwen3-vl-32b-proposer-sr-lora is a image-text-to-text model from liuyihong. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
This repository contains the Proposer LoRA adapter used in the archived VEGA-SR supplementary SFT analysis. It is an adapter for Qwen/Qwen3-VL-32B-Instruct; the base-model weights are not included.
Downloads · 30 days
6
18% of all-time downloads
All-time downloads
34
Public
Repo size
548 MB
Likes
0
Public
Click a slice to open those files.
.safetensors537 MB · 97%
From the Hugging Face model README
This repository contains the Proposer LoRA adapter used in the archived
VEGA-SR supplementary SFT analysis. It is an adapter for
Qwen/Qwen3-VL-32B-Instruct; the base-model weights are not included.
The archived SFT comparison is descriptive. The intended matched SFT-side run was incomplete, so this artifact must not be interpreted as a checkpoint-only causal estimate of the effect of SFT.
The corpus contains 10,000 example records derived from 5,000 paired tasks: 5,000 proposal examples and 5,000 Critic-conditioned repair examples. A 2% example-level evaluation split produced 9,800 training records and 200 evaluation records. A task-grouped split manifest was not retained, so the partitions are not claimed to be task-disjoint.
q_proj, k_proj, v_proj, o_proj, gate_proj,
up_proj, and down_proj;The training artifact did not retain an explicit Hugging Face revision for the
base checkpoint (revision=null). The base model identifier is therefore
reported without guessing a training-time revision. The later inference audit
used a local Qwen3-VL-32B-Instruct snapshot whose cache metadata recorded
revision 0cfaf48183f594c314753d30a4c4974bc75f3ccb; this does not by itself
prove that the same snapshot was used at the start of SFT.
adamw_torch), betas (0.9, 0.999), epsilon 1e-8;5e-5;best_model_checkpoint and best_metric were not set.The archived framework versions were PEFT 0.17.1, Transformers 4.57.6, PyTorch 2.5.1+cu124, Datasets 4.0.0, and Tokenizers 0.22.2.
The loss curves and JSON metric exports are included. training_config.yaml
contains the human-readable training configuration. Optimizer state,
checkpoints, RNG state, and Python-pickle training arguments are intentionally
excluded from this public adapter package.
The code and experiment configuration are maintained at https://github.com/RUCAIBox/VEGA-SR. The exact paper release tag and archival DOI should be cited together with the versioned adapter tag.
The release manifest is SHA256SUMS. In particular, the original adapter
weight artifact had SHA-256:
0a8b2c55edd3c9900a94aa55a0170979c748fd11b6e5fa88531c4fe88f693dbb adapter_model.safetensors
The base model and this LoRA adapter are distributed under the Apache License 2.0. A copy of the license is included in this model repository. Third-party software and data retain their respective upstream terms.