GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
RobinY99
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
RobinY99
Model Tree
Input Modalities
Output Modalities
Supported Functionality
The released checkpoint was validated after each epoch with an 8-shard setup on a held-out KONIQ split.
| Epoch | Valid samples | SRCC | PLCC | Shards |
|---|---|---|---|---|
| 1 | 200 | 0.8840 | 0.8894 | 8 |
| 2 | 200 | 0.9213 | 0.9302 | 8 |
| 3 | 200 | 0.9318 | 0.9392 | 8 |
| 4 | 200 | 0.9274 | 0.9340 | 8 |
| 5 | 200 | 0.9271 | 0.9409 | 8 |
| 6 | 200 | 0.9249 | 0.9406 | 8 |
| 7 | 200 | 0.9205 | 0.9408 | 8 |
| 8 | 200 | 0.9288 | 0.9465 | 8 |
| 9 | 200 | 0.9307 | 0.9450 | 8 |
| 10 | 200 | 0.9251 | 0.9421 | 8 |
Best SRCC was reached at epoch 3. The final released checkpoint corresponds to epoch 10. Sanitized training metadata is available in training_guidance/.
Load the model with a standard Transformers vision-language workflow. Provide one image and ask for an overall perceptual quality score in the 1 to 5 range. For easiest downstream parsing, request the final numeric score inside <answer>...</answer>.
Recommended prompt:
Assess the overall perceptual quality of this image. Briefly explain your assessment, then output a final quality score as a float between 1 and 5, rounded to two decimal places, inside
<answer>...</answer>.
A typical response contains a short assessment followed by a final score:
text
The image has generally clear structure and acceptable perceptual quality, with some visible degradation in fine detail.<answer>3.74</answer>
Citation information will be added with the accompanying paper release.