Downloads · 30 days
42
64% of all-time downloads
bluesky7/TEMA-Qwen2.5-Omni-7B-GRPO
TEMA-Qwen2.5-Omni-7B-GRPO is a text-to-audio model from bluesky7. Use it for the text-to-audio task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
Downloads · 30 days
42
64% of all-time downloads
All-time downloads
66
Public
Parameters
8.9B
18 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors17.9 GB · 100%
From the Hugging Face model README
Final TEMA model: Qwen2.5-Omni-7B → temporal initialization → dialogue SFT → evidence GRPO. The model answers multi-turn, multi-audio questions with Route, Span, Reason, and Answer.
TEMA-Dialog and TEMA-Bench cover five task families and 18 subtasks. See the 18-subtask guide for definitions, example questions and answers, evidence requirements, and internal task labels.
253 dialogues / 1,239 questions, using model-generated history. Values are percentages.
| QA | QA+T | Span [email protected] | [email protected] |
|---|---|---|---|
| 69.81 | 58.76 | 58.65 | 44.39 |
Evaluation uses bluesky7/TEMA-Qwen2.5-Omni-7B-SFT + this repository's adapter/.
Evidence GRPO trains for 512 steps with G=4. The reward is 0.9 × H + 0.1 × D
for valid evidence and −0.1 otherwise. Training generation stops at </span>;
inference generates the full response.
The repository includes merged model weights and the training adapter.
Load merged weights with Qwen2_5OmniForConditionalGeneration.from_pretrained(...)
and the included processor; set return_audio=False for text responses.
To use adapter/, load it on bluesky7/TEMA-Qwen2.5-Omni-7B-SFT.