Instructions to use open-thoughts/OpenThinkerAgent-8B-ColdStartSFTForRL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use open-thoughts/OpenThinkerAgent-8B-ColdStartSFTForRL with Transformers:

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

pipe = pipeline("text-generation", model="open-thoughts/OpenThinkerAgent-8B-ColdStartSFTForRL")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("open-thoughts/OpenThinkerAgent-8B-ColdStartSFTForRL")
model = AutoModelForMultimodalLM.from_pretrained("open-thoughts/OpenThinkerAgent-8B-ColdStartSFTForRL")
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-8B-ColdStartSFTForRL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "open-thoughts/OpenThinkerAgent-8B-ColdStartSFTForRL"
# 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-8B-ColdStartSFTForRL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/open-thoughts/OpenThinkerAgent-8B-ColdStartSFTForRL

SGLang

How to use open-thoughts/OpenThinkerAgent-8B-ColdStartSFTForRL 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-8B-ColdStartSFTForRL" \
    --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-8B-ColdStartSFTForRL",
		"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-8B-ColdStartSFTForRL" \
        --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-8B-ColdStartSFTForRL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use open-thoughts/OpenThinkerAgent-8B-ColdStartSFTForRL with Docker Model Runner:
```
docker model run hf.co/open-thoughts/OpenThinkerAgent-8B-ColdStartSFTForRL
```

OpenThinkerAgent-8B-ColdStartSFTForRL / README.md

penfever

Add model/dataset card

a779325 verified 7 days ago

preview code

raw

history blame contribute delete

5.97 kB

	---
	base_model:
	- Qwen/Qwen3-8B
	datasets:
	- open-thoughts/OpenThoughts-Agent-SFT-ColdStartForRL-10K
	library_name: transformers
	license: apache-2.0
	model-index:
	- name: OpenThinkerAgent-8B-ColdStartSFTForRL
	results: []
	pipeline_tag: text-generation
	tags:
	- agents
	- terminal
	- code
	- software-engineering
	- sft
	- cold-start
	---
	<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-8B-ColdStartSFTForRL

	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-8B-ColdStartSFTForRL](https://huggingface.co/open-thoughts/OpenThinkerAgent-8B-ColdStartSFTForRL) is the cold-start, pre-RL base of the OpenThoughts-Agent 8B SFT→RL recipe. It is post-trained from [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) with full-parameter SFT on the cold-start [OpenThoughts-Agent-SFT-ColdStartForRL-10K](https://huggingface.co/datasets/open-thoughts/OpenThoughts-Agent-SFT-ColdStartForRL-10K) dataset. Its purpose is to give the model the agentic interaction format and tool-use behaviour needed to make subsequent reinforcement learning stable; it is then RL-trained to produce [OpenThinkerAgent-8B-RL](https://huggingface.co/open-thoughts/OpenThinkerAgent-8B-RL).

	> Architecture note. Although the upstream artifact carries a `GLM-4.7` label (which refers to the teacher that generated the SFT trajectories, not the student), this model is a Qwen3-8B. Its `config.json` reports `model_type: qwen3`, `architectures: ["Qwen3ForCausalLM"]`, 36 layers, hidden size 4096, 32 attention heads / 8 KV heads, and a 40,960-token context — i.e. standard Qwen3-8B.

	- Homepage: https://www.openthoughts.ai/blog/agent
	- Repository: https://github.com/open-thoughts/OpenThoughts-Agent

	# Model details

	- Base model: [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B)
	- Architecture: Qwen3 (`Qwen3ForCausalLM`), 36 layers, hidden size 4096, 32 attention heads, 8 KV heads, RoPE θ = 1e6
	- Context length: 40,960 tokens (max position embeddings)
	- Vocabulary: 151,936 tokens
	- Precision: bf16
	- Role in pipeline: cold-start SFT checkpoint (pre-RL base)

	# Position in the SFT → RL recipe

	1. [OpenThoughts-Agent-SFT-ColdStartForRL-10K](https://huggingface.co/datasets/open-thoughts/OpenThoughts-Agent-SFT-ColdStartForRL-10K) — cold-start SFT trajectories.
	2. [OpenThinkerAgent-8B-ColdStartSFTForRL](https://huggingface.co/open-thoughts/OpenThinkerAgent-8B-ColdStartSFTForRL) — this model (Qwen3-8B after cold-start SFT, the pre-RL base).
	3. [OpenThoughts-Agent-RL-5K](https://huggingface.co/datasets/open-thoughts/OpenThoughts-Agent-RL-5K) — on-policy RL tasks.
	4. [OpenThinkerAgent-8B-RL](https://huggingface.co/open-thoughts/OpenThinkerAgent-8B-RL) — the final RL'd checkpoint (step 45).

	# Training data

	Trained on [OpenThoughts-Agent-SFT-ColdStartForRL-10K](https://huggingface.co/datasets/open-thoughts/OpenThoughts-Agent-SFT-ColdStartForRL-10K) (9,437 (task, trajectory) pairs): SWE-Smith sandboxed coding tasks with tests, solved by a teacher model in the terminus-2 harness inside Daytona sandboxes, oracle-verified (120s verifier timeout).

	# Training procedure

	Full-parameter SFT (LLaMA-Factory). Hyperparameters as recorded by the trainer:

	- learning_rate: 4e-05
	- lr_scheduler_type: cosine, warmup_ratio 0.1
	- train_batch_size: 1 per device × 8 devices × gradient_accumulation_steps 2 → total_train_batch_size 16
	- optimizer: AdamW (fused), betas (0.9, 0.98), eps 1e-08
	- num_epochs: 7
	- seed: 42
	- precision: bf16
	- final train loss: ≈ 0.303 (4,130 global steps)

	### Framework versions
	- Transformers 4.57.6
	- PyTorch 2.9.0+cu128
	- Datasets 4.4.1
	- Tokenizers 0.22.2

	# Intended uses & limitations

	This checkpoint is intended as the starting point for agentic RL, not as a final deployable agent. It has learned the agentic format and tool-use conventions of the terminus-2 harness from a relatively small cold-start set; its standalone agentic performance is expected to be below the RL-trained successor [OpenThinkerAgent-8B-RL](https://huggingface.co/open-thoughts/OpenThinkerAgent-8B-RL). As with the base Qwen3-8B, outputs may be incorrect or unsafe and should not be executed without review. No standalone agentic-benchmark numbers are published for this cold-start checkpoint.

	# 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-ColdStartForRL-10K](https://huggingface.co/datasets/open-thoughts/OpenThoughts-Agent-SFT-ColdStartForRL-10K)
	- 🧠 [RL tasks: OpenThoughts-Agent-RL-5K](https://huggingface.co/datasets/open-thoughts/OpenThoughts-Agent-RL-5K)
	- 🤖 [Final RL model: OpenThinkerAgent-8B-RL](https://huggingface.co/open-thoughts/OpenThinkerAgent-8B-RL)

	# 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}
	}
	```