Instructions to use open-thoughts/OpenThinker-Agent-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use open-thoughts/OpenThinker-Agent-v1 with Transformers:

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

pipe = pipeline("text-generation", model="open-thoughts/OpenThinker-Agent-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("open-thoughts/OpenThinker-Agent-v1")
model = AutoModelForCausalLM.from_pretrained("open-thoughts/OpenThinker-Agent-v1")
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
Local Apps Settings

vLLM

How to use open-thoughts/OpenThinker-Agent-v1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/open-thoughts/OpenThinker-Agent-v1

SGLang

How to use open-thoughts/OpenThinker-Agent-v1 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 "open-thoughts/OpenThinker-Agent-v1" \
    --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": "open-thoughts/OpenThinker-Agent-v1",
		"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 "open-thoughts/OpenThinker-Agent-v1" \
        --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": "open-thoughts/OpenThinker-Agent-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use open-thoughts/OpenThinker-Agent-v1 with Docker Model Runner:
```
docker model run hf.co/open-thoughts/OpenThinker-Agent-v1
```

Link model card to OpenThoughts-Agent paper

by nielsr HF Staff - opened 5 days ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-5

Files changed (1) hide show

README.md +8 -5

README.md CHANGED Viewed

@@ -6,15 +6,15 @@ datasets:
 - OpenThoughts-Agent-v1-RL
 library_name: transformers
 license: apache-2.0
-model-index:
-- name: OpenThinker-Agent-v1
-  results: []
 pipeline_tag: text-generation
 tags:
 - agents
 - terminal
 - code
 - software-engineering
 ---
 <p align="center">
@@ -22,7 +22,8 @@ tags:
 </p>
 <p align="center">
-<a href="https://www.openthoughts.ai/blog/agent" style="margin-right: 24px;">Project</a> |
 <a href="https://huggingface.co/datasets/open-thoughts/OpenThoughts-Agent-v1-SFT" style="margin-right: 24px; margin-left: 24px;">SFT dataset</a> |
 <a href="https://huggingface.co/datasets/open-thoughts/OpenThoughts-Agent-v1-RL" style="margin-right: 24px; margin-left: 24px;">RL dataset</a> |
 <a href="https://huggingface.co/open-thoughts/OpenThinker-Agent-v1-SFT" style="margin-right: 24px; margin-left: 24px;">SFT model</a> |
@@ -32,7 +33,7 @@ tags:
 # OpenThinker-Agent-v1
-**OpenThoughts-Agent** is an open-source effort to curate the best datasets for training agents. Our first release includes [datasets](https://huggingface.co/collections/open-thoughts/openthinker-agent), [models](https://huggingface.co/collections/open-thoughts/openthinker-agent) and our [research codebase](https://github.com/open-thoughts/OpenThoughts-Agent).
 [OpenThinker-Agent-v1](https://huggingface.co/open-thoughts/OpenThinker-Agent-v1) is a model trained for agentic tasks such as **Terminal-Bench 2.0** and **SWE-Bench**.
@@ -41,6 +42,7 @@ It is SFT-ed on the [OpenThoughts-Agent-v1-SFT](https://huggingface.co/datasets/
 This model is the final model after both SFT and RL. For the model after the SFT stage only, see [OpenThinker-Agent-v1-SFT](https://huggingface.co/open-thoughts/OpenThinker-Agent-v1-SFT).
 - **Homepage:** https://www.openthoughts.ai/blog/agent
 - **Repository:** https://github.com/open-thoughts/OpenThoughts-Agent
@@ -76,6 +78,7 @@ Optional difficulty filter: discard tasks that even a strong model (GPT-5 Codex)
 # Links
 - 🌐 [OpenThoughts-Agent project page](https://www.openthoughts.ai/blog/agent)
 - 💻 [OpenThoughts-Agent GitHub repository](https://github.com/open-thoughts/OpenThoughts-Agent)
 - 🧠 [OpenThoughts-Agent-v1-SFT dataset](https://huggingface.co/datasets/open-thoughts/OpenThoughts-Agent-v1-SFT)

 - OpenThoughts-Agent-v1-RL
 library_name: transformers
 license: apache-2.0
 pipeline_tag: text-generation
 tags:
 - agents
 - terminal
 - code
 - software-engineering
+model-index:
+- name: OpenThinker-Agent-v1
+  results: []
 ---
 <p align="center">
 </p>
 <p align="center">
+<a href="https://huggingface.co/papers/2606.24855" style="margin-right: 24px;">Paper</a> |
+<a href="https://www.openthoughts.ai/blog/agent" style="margin-right: 24px; margin-left: 24px;">Project</a> |
 <a href="https://huggingface.co/datasets/open-thoughts/OpenThoughts-Agent-v1-SFT" style="margin-right: 24px; margin-left: 24px;">SFT dataset</a> |
 <a href="https://huggingface.co/datasets/open-thoughts/OpenThoughts-Agent-v1-RL" style="margin-right: 24px; margin-left: 24px;">RL dataset</a> |
 <a href="https://huggingface.co/open-thoughts/OpenThinker-Agent-v1-SFT" style="margin-right: 24px; margin-left: 24px;">SFT model</a> |
 # OpenThinker-Agent-v1
+**OpenThoughts-Agent** is an open-source effort to curate the best datasets for training agents. Our first release includes [datasets](https://huggingface.co/collections/open-thoughts/openthinker-agent), [models](https://huggingface.co/collections/open-thoughts/openthinker-agent) and our [research codebase](https://github.com/open-thoughts/OpenThoughts-Agent). For more details, please see our paper: [OpenThoughts-Agent: Data Recipes for Agentic Models](https://huggingface.co/papers/2606.24855).
 [OpenThinker-Agent-v1](https://huggingface.co/open-thoughts/OpenThinker-Agent-v1) is a model trained for agentic tasks such as **Terminal-Bench 2.0** and **SWE-Bench**.
 This model is the final model after both SFT and RL. For the model after the SFT stage only, see [OpenThinker-Agent-v1-SFT](https://huggingface.co/open-thoughts/OpenThinker-Agent-v1-SFT).
+- **Paper:** https://huggingface.co/papers/2606.24855
 - **Homepage:** https://www.openthoughts.ai/blog/agent
 - **Repository:** https://github.com/open-thoughts/OpenThoughts-Agent
 # Links
+- 📄 [OpenThoughts-Agent Paper](https://huggingface.co/papers/2606.24855)
 - 🌐 [OpenThoughts-Agent project page](https://www.openthoughts.ai/blog/agent)
 - 💻 [OpenThoughts-Agent GitHub repository](https://github.com/open-thoughts/OpenThoughts-Agent)
 - 🧠 [OpenThoughts-Agent-v1-SFT dataset](https://huggingface.co/datasets/open-thoughts/OpenThoughts-Agent-v1-SFT)