Instructions to use open-thoughts/OpenThinkerAgent-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use open-thoughts/OpenThinkerAgent-32B with Transformers:

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

pipe = pipeline("text-generation", model="open-thoughts/OpenThinkerAgent-32B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("open-thoughts/OpenThinkerAgent-32B")
model = AutoModelForCausalLM.from_pretrained("open-thoughts/OpenThinkerAgent-32B")
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 open-thoughts/OpenThinkerAgent-32B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "open-thoughts/OpenThinkerAgent-32B"
# 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/OpenThinkerAgent-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/open-thoughts/OpenThinkerAgent-32B

SGLang

How to use open-thoughts/OpenThinkerAgent-32B 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/OpenThinkerAgent-32B" \
    --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/OpenThinkerAgent-32B",
		"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/OpenThinkerAgent-32B" \
        --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/OpenThinkerAgent-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use open-thoughts/OpenThinkerAgent-32B with Docker Model Runner:
```
docker model run hf.co/open-thoughts/OpenThinkerAgent-32B
```

EtashGuha commited on about 21 hours ago

Commit

65d8a62

verified ·

1 Parent(s): 8bf17f1

Standardize card (v1-consistent)

Browse files

Files changed (1) hide show

README.md +39 -23

README.md CHANGED Viewed

@@ -5,6 +5,9 @@ datasets:
 - open-thoughts/OpenThoughts-Agent-SFT-100K
 library_name: transformers
 license: apache-2.0
 pipeline_tag: text-generation
 tags:
 - agents
@@ -12,35 +15,38 @@ tags:
 - code
 - software-engineering
 ---
 <p align="center">
 <a href="https://www.openthoughts.ai/blog/agent" style="margin-right: 24px;">Project</a> |
 <a href="https://github.com/open-thoughts/OpenThoughts-Agent" style="margin-right: 24px; margin-left: 24px;">Code</a> |
-<a href="https://huggingface.co/datasets/open-thoughts/OpenThoughts-Agent-SFT-100K" style="margin-left: 24px;">Training data</a> |
 <a href="https://huggingface.co/collections/open-thoughts/openthinker-agent" style="margin-left: 24px;">Collection</a>
 </p>
 # OpenThinkerAgent-32B
-**OpenThoughts-Agent** is an open effort to curate the best data for training agentic
-language models. **OpenThinkerAgent-32B** is the 32B model from the SFT scaling ladder, fine-tuned
-from [Qwen/Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B) on the **100,000-example**
-[OpenThoughts-Agent-SFT-100K](https://huggingface.co/datasets/open-thoughts/OpenThoughts-Agent-SFT-100K)
-dataset (Top-4 task sources, GLM-4.7-AWQ teacher in the terminus-2 harness, ≥5-turn filter).
-## Performance
-Evaluated in the **terminus-2** harness (pass@1, 3 stochastic re-runs):
-| Benchmark | Accuracy |
-| --- | --- |
-| SWE-Bench-Verified-100 | 55.7 |
-| OpenThoughts-TBLite | 41.3 |
-| Terminal-Bench 2.0 | 26.2 |
-### Full benchmark suite (OpenThinkerAgent-32B, best harness)
-| Benchmark | Acc |
 | --- | --- |
 | SWE-Bench-Verified | 54.0 |
 | Terminal-Bench 2.0 | 26.2 |
@@ -51,19 +57,29 @@ Evaluated in the **terminus-2** harness (pass@1, 3 stochastic re-runs):
 | FinanceAgent-Terminal | 44.0 |
 | **Average (7)** | **44.8** |
-This is the best open-data 32B model on the average of seven agentic benchmarks.
-## Links
-- 🌐 [Project](https://www.openthoughts.ai/blog/agent)
-- 💻 [Code](https://github.com/open-thoughts/OpenThoughts-Agent)
-- 🧠 [Training dataset](https://huggingface.co/datasets/open-thoughts/OpenThoughts-Agent-SFT-100K)
-- 📚 [Collection](https://huggingface.co/collections/open-thoughts/openthinker-agent)
-## Citation
 ```
 @misc{openthoughts-agent,
   author = {Team, OpenThoughts-Agent},
-  title = {OpenThoughts-Agent: Data Recipes for Agentic Models},
   howpublished = {https://www.openthoughts.ai/blog/agent},
   year = {2026}
 }

 - open-thoughts/OpenThoughts-Agent-SFT-100K
 library_name: transformers
 license: apache-2.0
+model-index:
+- name: OpenThinkerAgent-32B
+  results: []
 pipeline_tag: text-generation
 tags:
 - agents
 - code
 - software-engineering
 ---
+<p align="center">
+    <img src="https://huggingface.co/datasets/open-thoughts/OpenThoughts1-Agent-SFT/resolve/main/ota-logo.png" width="50%">
+</p>
 <p align="center">
 <a href="https://www.openthoughts.ai/blog/agent" style="margin-right: 24px;">Project</a> |
 <a href="https://github.com/open-thoughts/OpenThoughts-Agent" style="margin-right: 24px; margin-left: 24px;">Code</a> |
 <a href="https://huggingface.co/collections/open-thoughts/openthinker-agent" style="margin-left: 24px;">Collection</a>
 </p>
 # OpenThinkerAgent-32B
+**OpenThoughts-Agent** is an open-source effort to curate the best datasets for training agents. Our 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).
+[OpenThinkerAgent-32B](https://huggingface.co/open-thoughts/OpenThinkerAgent-32B) is post-trained from [Qwen/Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B) with full-parameter SFT on the **100,000-example** [OpenThoughts-Agent-SFT-100K](https://huggingface.co/datasets/open-thoughts/OpenThoughts-Agent-SFT-100K) dataset (Top-4 task sources, GLM-4.7-AWQ teacher in the terminus-2 harness, ≥5-turn trace filter). It is the flagship **OpenThinkerAgent-32B**, the strongest open-data 32B model on the average of seven agentic benchmarks.
+- **Homepage:** https://www.openthoughts.ai/blog/agent
+- **Repository:** https://github.com/open-thoughts/OpenThoughts-Agent
+# Performance
+Evaluated in the **terminus-2** harness (pass@1, mean over 3 stochastic re-runs):
+| Model | Harness | SWE-Bench-Verified-100 | OpenThoughts-TBLite | Terminal-Bench 2.0 |
+| --- | --- | --- | --- | --- |
+| [Qwen/Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B) | Terminus-2 | 26.7 | 13.7 | 7.5 |
+| **OpenThinkerAgent-32B** | Terminus-2 | 55.7 | 41.3 | 26.2 |
+Across the full seven-benchmark suite (best harness per benchmark), **OpenThinkerAgent-32B** is the strongest open-data model at the 32B scale:
+| Benchmark | Accuracy |
 | --- | --- |
 | SWE-Bench-Verified | 54.0 |
 | Terminal-Bench 2.0 | 26.2 |
 | FinanceAgent-Terminal | 44.0 |
 | **Average (7)** | **44.8** |
+# Data
+The model is trained on [OpenThoughts-Agent-SFT-100K](https://huggingface.co/datasets/open-thoughts/OpenThoughts-Agent-SFT-100K): (task, agent-trajectory) pairs from the Top-4 task sources (SWE-Smith, StackExchange-SuperUser, StackExchange-Tezos with synthetic augmentation, IssueTasks). Trajectories are generated by GLM-4.7-AWQ in the terminus-2 harness and filtered to traces with at least 5 model turns.
+### Training hyperparameters
+- learning_rate: 4e-05
+- lr_scheduler_type: cosine, warmup_ratio 0.1
+- global_batch_size: 96
+- num_epochs: 5
+- cutoff_len: 32768
+- precision: bf16, DeepSpeed ZeRO-3
+# Links
+- 🌐 [OpenThoughts-Agent project page](https://www.openthoughts.ai/blog/agent)
+- 💻 [OpenThoughts-Agent GitHub repository](https://github.com/open-thoughts/OpenThoughts-Agent)
+- 📚 [OpenThinker-Agent collection](https://huggingface.co/collections/open-thoughts/openthinker-agent)
+- 🧠 [Training dataset: OpenThoughts-Agent-SFT-100K](https://huggingface.co/datasets/open-thoughts/OpenThoughts-Agent-SFT-100K)
+# Citation
 ```
 @misc{openthoughts-agent,
   author = {Team, OpenThoughts-Agent},
+  title = {{OpenThoughts-Agent: Data Recipes for Agentic Models}},
   howpublished = {https://www.openthoughts.ai/blog/agent},
   year = {2026}
 }