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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("simplex-ai-inc/LiteResearcher-4B")
model = AutoModelForCausalLM.from_pretrained("simplex-ai-inc/LiteResearcher-4B")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use simplex-ai-inc/LiteResearcher-4B 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"
# 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",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

How to use simplex-ai-inc/LiteResearcher-4B 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" \
    --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",
		"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" \
        --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",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

wanlilll commited on Apr 14

Commit

252ab07

verified ·

1 Parent(s): d75a775

Update links to simplex-ai-inc org

Browse files

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -19,7 +19,7 @@ library_name: transformers
 <p align="center">
   <a href="https://wanli-lee.github.io/LiteResearcher/">🌐 Project Page</a> •
-  <a href="https://github.com/Wanli-Lee/LiteResearcher">💻 Code</a> •
   <a href="#">📄 Paper (Coming Soon)</a>
 </p>
@@ -59,7 +59,7 @@ The model uses `<think>`, `<tool_call>`, and `<answer>` tags to structure its re
 ### With the Inference Framework
 ```bash
-git clone https://github.com/Wanli-Lee/LiteResearcher.git
 cd LiteResearcher
 pip install -r requirements.txt
@@ -69,12 +69,12 @@ cp .env.example .env
 # Start SGLang server
 python -m sglang.launch_server \
-    --model-path lev8-simplexai/LiteResearcher-4B \
     --port 6001 --tp 2
 # Run inference
 bash scripts/run_all.sh \
-    --model lev8-simplexai/LiteResearcher-4B \
     --dataset data/example.jsonl
 ```
@@ -83,7 +83,7 @@ bash scripts/run_all.sh \
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
-model_name = "lev8-simplexai/LiteResearcher-4B"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")

 <p align="center">
   <a href="https://wanli-lee.github.io/LiteResearcher/">🌐 Project Page</a> •
+  <a href="https://github.com/simplex-ai-inc/LiteResearcher">💻 Code</a> •
   <a href="#">📄 Paper (Coming Soon)</a>
 </p>
 ### With the Inference Framework
 ```bash
+git clone https://github.com/simplex-ai-inc/LiteResearcher.git
 cd LiteResearcher
 pip install -r requirements.txt
 # Start SGLang server
 python -m sglang.launch_server \
+    --model-path simplex-ai-inc/LiteResearcher-4B \
     --port 6001 --tp 2
 # Run inference
 bash scripts/run_all.sh \
+    --model simplex-ai-inc/LiteResearcher-4B \
     --dataset data/example.jsonl
 ```
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
+model_name = "simplex-ai-inc/LiteResearcher-4B"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")