GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
meirdick
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
meirdick
Model Tree
Qwen/Qwen3-4B-Instruct-2507
Input Modalities
Output Modalities
Supported Functionality
LoRA expert for the business_econ target of the route-then-admit pool, trained on meirdick/router-experts-data data/experts/business_econ.jsonl.
Qwen/Qwen3-4B-Instruct-2507| field | value |
|---|---|
| target | business_econ |
| items | 1500 |
| recipes | direct,cot_short |
| kinds | {'mc': 1500} |
| mc_padded | 542 |
| examples | 3000 |
| encoded | 3000 |
| dropped_too_long | 0 |
| train_rows | 2850 |
| val_rows | 150 |
| train_batches | 53 |
| train_tokens | 420999 |
| supervised_tokens | 65056 |
| steps | 106 |
| train_loss | 1.0173314556760609 |
| val_loss_before | 4.347536211155416 |
| val_loss | 0.9388195680416275 |
| seconds | 147.98 |
| trainable_params | 11796480 |