GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
SeongryongJung
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
SeongryongJung
Model Tree
Qwen/Qwen3-4B
Input Modalities
Output Modalities
Supported Functionality
The reported headline score is the best validation mean@16 observed during training.
It is not necessarily the score of the uploaded last checkpoint.
| Dataset | Method | Model | Uploaded checkpoint | Best val mean@16 | Best step | Final val mean@16 |
|---|---|---|---|---|---|---|
| chemistry | SRPO | Qwen3-4B | global_step_100 | 78.99% | 70 | 76.99% |
Raw result files:
results/validation_mean16.csvresults/training_scores.csvartifacts/config.yamlartifacts/wandb-summary.jsonQwen/Qwen3-4BchemistrySRPO0.05global_step_100val-aux/*/mean@16n=16python
from transformers import AutoModelForCausalLM, AutoTokenizer repo_id = "SeongryongJung/qwen3-4b-chemistry-srpo-ema005"tokenizer = AutoTokenizer.from_pretrained(repo_id, trust_remote_code=True)model = AutoModelForCausalLM.from_pretrained( repo_id, torch_dtype="auto", device_map="auto", trust_remote_code=True,)Most best-validation intermediate checkpoints were not retained as full actor checkpoints because training kept only the latest actor checkpoint. Therefore, this repository publishes the last checkpoint and records the best validation score separately.
from transformers import AutoModelForCausalLM, AutoTokenizer repo_id = "SeongryongJung/qwen3-4b-chemistry-srpo-ema005"tokenizer = AutoTokenizer.from_pretrained(repo_id, trust_remote_code=True)model = AutoModelForCausalLM.from_pretrained( repo_id, torch_dtype="auto", device_map="auto", trust_remote_code=True,)