Instructions to use simplex-ai-inc/LiteResearcher-4B-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use simplex-ai-inc/LiteResearcher-4B-SFT with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="simplex-ai-inc/LiteResearcher-4B-SFT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("simplex-ai-inc/LiteResearcher-4B-SFT")
model = AutoModelForMultimodalLM.from_pretrained("simplex-ai-inc/LiteResearcher-4B-SFT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use simplex-ai-inc/LiteResearcher-4B-SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "simplex-ai-inc/LiteResearcher-4B-SFT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "simplex-ai-inc/LiteResearcher-4B-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/simplex-ai-inc/LiteResearcher-4B-SFT

SGLang

How to use simplex-ai-inc/LiteResearcher-4B-SFT with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "simplex-ai-inc/LiteResearcher-4B-SFT" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "simplex-ai-inc/LiteResearcher-4B-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "simplex-ai-inc/LiteResearcher-4B-SFT" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "simplex-ai-inc/LiteResearcher-4B-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use simplex-ai-inc/LiteResearcher-4B-SFT with Docker Model Runner:
```
docker model run hf.co/simplex-ai-inc/LiteResearcher-4B-SFT
```

LiteResearcher-4B-SFT

This is the SFT cold-start checkpoint for LiteResearcher — a scalable agentic RL training framework for deep-research agents.

It is the initial policy used to launch the two-stage curriculum RL training that produces the final simplex-ai-inc/LiteResearcher-4B model.

If you are looking for the final RL model, please use simplex-ai-inc/LiteResearcher-4B. If you want to reproduce the RL training from scratch, this is the checkpoint you need.

Model details

Base model: Qwen/Qwen3-4B-Thinking-2507
Architecture: Qwen3ForCausalLM (36 layers, hidden 2560, 32 heads, GQA 8 KV heads)
Max position embeddings: 262,144 (RoPE θ = 5,000,000)
Precision: bfloat16
Total params: ~4B
Training framework: LLaMA-Factory

Training recipe

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	2.0e-5, cosine, 10% warmup
Final train loss	≈ 0.447 (starting loss ≈ 1.19)

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.

How to use

As the initial policy for RL (recommended use)

# 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.

Stand-alone inference

from transformers import AutoModelForCausalLM, AutoTokenizer
import 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).

Citation

If you use this checkpoint in academic work, please cite the LiteResearcher project — see the GitHub README for the BibTeX entry.

License

Apache-2.0, inheriting from the Qwen3-4B-Thinking-2507 base model.

Downloads last month: 1

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for simplex-ai-inc/LiteResearcher-4B-SFT

Base model

Qwen/Qwen3-4B-Thinking-2507

Finetuned

(237)

this model

simplex-ai-inc
/

LiteResearcher-4B-SFT