GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
SriGoli0123
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
SriGoli0123
Model Tree
Qwen/Qwen3-4B-Base
Input Modalities
Output Modalities
Supported Functionality
The root model-*.safetensors files contain the merged actor weights from training step 204 of 204. They load directly with Transformers:
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "SriGoli0123/Qwen3-4B-Base-MSJ-GRPO-DAPO17K"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map="auto",)The merged export contains 4,022,468,096 bfloat16 parameters across 398 tensors. The final deterministic DAPO Math validation accuracy was 0.325 on 1,000 examples at step 204 (best during training: 0.348 at step 200).
Qwen/Qwen3-4B-Base906bfd4b4dc7f14ee4320094d8b41684abff8539a100/ioher-mistake-judge, commit d169b69)data.train_batch_size): 64 promptsrollout.n): 8actor.ppo_mini_batch_size): 16 prompts (4 optimizer steps per training step)actor.ppo_micro_batch_size_per_gpu): 4rollout.log_prob_micro_batch_size_per_gpu): 4actor.use_dynamic_bsz, rollout.log_prob_use_dynamic_bsz): enabledactor.ppo_max_token_len_per_gpu, rollout.log_prob_max_token_len_per_gpu): 24,576actor.ppo_epochs): 1data.max_prompt_length): 2,048 tokensdata.max_response_length): 4,096 tokensalgorithm.ioh.judge_max_prompt_tokens): 8,192algorithm.ioh.judge_max_new_tokens): 512algorithm.ioh.max_extra_prompt_tokens): 256GRPO loss + 0.01 * SFT loss<mistakes>...</mistakes> block1e-6[0.9, 0.999]torch.compile: disabled-1)This is a research checkpoint. Validation accuracy plateaued around 0.31-0.33 after roughly step 70; differences of about ±1.5 points are within noise on the 1,000-example validation set. Evaluate the model on the intended benchmark and decoding configuration before downstream use.
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "SriGoli0123/Qwen3-4B-Base-MSJ-GRPO-DAPO17K"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map="auto",)