Instructions to use PokeeAI/pokee_research_7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PokeeAI/pokee_research_7b with Transformers:

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

pipe = pipeline("text-generation", model="PokeeAI/pokee_research_7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PokeeAI/pokee_research_7b")
model = AutoModelForCausalLM.from_pretrained("PokeeAI/pokee_research_7b")
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

vLLM

How to use PokeeAI/pokee_research_7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PokeeAI/pokee_research_7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PokeeAI/pokee_research_7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PokeeAI/pokee_research_7b

SGLang

How to use PokeeAI/pokee_research_7b 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 "PokeeAI/pokee_research_7b" \
    --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": "PokeeAI/pokee_research_7b",
		"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 "PokeeAI/pokee_research_7b" \
        --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": "PokeeAI/pokee_research_7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PokeeAI/pokee_research_7b with Docker Model Runner:
```
docker model run hf.co/PokeeAI/pokee_research_7b
```

Add pipeline tag, library name, and improve project page link

by nielsr HF Staff - opened Oct 22, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-7

Files changed (1) hide show

README.md +9 -7

README.md CHANGED Viewed

@@ -1,17 +1,19 @@
 ---
-license: apache-2.0
 language:
 - en
 tags:
 - agent
 - deepresearch
 - llm
 - rl
 - reinforcementlearning
-datasets:
-- miromind-ai/MiroRL-GenQA
-base_model:
-- Qwen/Qwen2.5-7B-Instruct
 ---
 # Model Card for PokeeResearch
@@ -33,7 +35,7 @@ The model integrates **Reinforcement Learning from AI Feedback (RLAIF)** with a
 - **Repository:** [https://github.com/Pokee-AI/PokeeResearchOSS](https://github.com/Pokee-AI/PokeeResearchOSS)
 - **Paper:** [*PokeeResearch: Effective Deep Research via Reinforcement Learning from AI Feedback and Robust Reasoning Scaffold*](https://arxiv.org/pdf/2510.15862), Pokee AI, October 2025
-- **API Access:** [https://pokee.ai/deepresearch-preview](https://pokee.ai/deepresearch-preview)
 ---
@@ -203,4 +205,4 @@ For inquiries, contact: hello@pokee.ai
 **Yi Wan**, **Jiuqi Wang**, Liam Li, Jinsong Liu, Ruihao Zhu, and Zheqing Zhu — Pokee AI Research Team
 ## Model Card Contact
-Pokee AI Team — hello@pokee.ai

 ---
+base_model:
+- Qwen/Qwen2.5-7B-Instruct
+datasets:
+- miromind-ai/MiroRL-GenQA
 language:
 - en
+license: apache-2.0
 tags:
 - agent
 - deepresearch
 - llm
 - rl
 - reinforcementlearning
+pipeline_tag: text-generation
+library_name: transformers
 ---
 # Model Card for PokeeResearch
 - **Repository:** [https://github.com/Pokee-AI/PokeeResearchOSS](https://github.com/Pokee-AI/PokeeResearchOSS)
 - **Paper:** [*PokeeResearch: Effective Deep Research via Reinforcement Learning from AI Feedback and Robust Reasoning Scaffold*](https://arxiv.org/pdf/2510.15862), Pokee AI, October 2025
+- **Project Page:** [https://pokee.ai/deepresearch-preview](https://pokee.ai/deepresearch-preview)
 ---
 **Yi Wan**, **Jiuqi Wang**, Liam Li, Jinsong Liu, Ruihao Zhu, and Zheqing Zhu — Pokee AI Research Team
 ## Model Card Contact
+Pokee AI Team — hello@pokee.ai