GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
simplex-ai-inc
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
simplex-ai-inc
Model Tree
Qwen/Qwen3-4B-Thinking-2507
Input Modalities
Output Modalities
Supported Functionality
Qwen/Qwen3-4B-Thinking-2507Qwen3ForCausalLM (36 layers, hidden 2560, 32 heads, GQA 8 KV heads)bfloat16| Item | Value |
|---|---|
| Stage | SFT (cold-start before RL) |
| Base model | Qwen/Qwen3-4B-Thinking-2507 |
| Dataset | simplex-ai-inc/LiteResearcher-Data (~68.2k SFT trajectories) |
| Max sequence length | 64K (cutoff_len=65536) |
| Global batch size | 128 (per-device bs 2 × grad-accum 8 × 8 GPUs) |
| Epochs | 1 |
| Optimizer steps | 533 |
| Learning rate |
The SFT trajectories teach the model the ReAct think → search → visit → answer
loop and the strict <answer>...</answer> output contract used by the RL environment.
Because the base is the Thinking-2507 variant, the model preserves long
chain-of-thought behavior inside <think>...</think> blocks, which is what the
downstream RL curriculum builds on.
bash
# In the LiteResearcher training scripts (Training/ folder of the repo)export MODEL_PATH=$(hf download simplex-ai-inc/LiteResearcher-4B-SFT \ --local-dir ./literesearcher_sft)Then follow the Stage-1 / Stage-2 RL instructions in the LiteResearcher repository.
python
from transformers import AutoModelForCausalLM, AutoTokenizerimport torch model_id = "simplex-ai-inc/LiteResearcher-4B-SFT"tok = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map="auto")The model expects the same ReAct system prompt and tool schema used by
LiteResearcher (see Inference/ in the repo).
If you use this checkpoint in academic work, please cite the LiteResearcher project — see the GitHub README for the BibTeX entry.
Apache-2.0, inheriting from the Qwen3-4B-Thinking-2507 base model.
| 2.0e-5, cosine, 10% warmup |
| Final train loss | ≈ 0.447 (starting loss ≈ 1.19) |
# In the LiteResearcher training scripts (Training/ folder of the repo)export MODEL_PATH=$(hf download simplex-ai-inc/LiteResearcher-4B-SFT \ --local-dir ./literesearcher_sft)from transformers import AutoModelForCausalLM, AutoTokenizerimport torch model_id = "simplex-ai-inc/LiteResearcher-4B-SFT"tok = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map="auto")