Instructions to use ByteDance/Ouro-1.4B-Thinking with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ByteDance/Ouro-1.4B-Thinking with Transformers:

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

pipe = pipeline("text-generation", model="ByteDance/Ouro-1.4B-Thinking", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("ByteDance/Ouro-1.4B-Thinking", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ByteDance/Ouro-1.4B-Thinking with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ByteDance/Ouro-1.4B-Thinking"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ByteDance/Ouro-1.4B-Thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ByteDance/Ouro-1.4B-Thinking

SGLang

How to use ByteDance/Ouro-1.4B-Thinking 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 "ByteDance/Ouro-1.4B-Thinking" \
    --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": "ByteDance/Ouro-1.4B-Thinking",
		"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 "ByteDance/Ouro-1.4B-Thinking" \
        --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": "ByteDance/Ouro-1.4B-Thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ByteDance/Ouro-1.4B-Thinking with Docker Model Runner:
```
docker model run hf.co/ByteDance/Ouro-1.4B-Thinking
```

Fix bos/eos token IDs + add enable_thinking to chat template

by KristianS7 - opened Feb 20

base: refs/heads/main

←

from: refs/pr/4

Discussion Files changed

-6

KristianS7

Feb 20

•

edited Feb 20

Summary

Fix token configuration and add enable_thinking support for the chat template.

Token ID fixes

The current bos_token and eos_token are both set to <|endoftext|> (id=0), which is incorrect for a ChatML-style model. This PR fixes them to match the actual chat format:

Field	Before	After
`bos_token`	`<\|endoftext\|>` (0)	`<\|im_start\|>` (1)
`eos_token`	`<\|endoftext\|>` (0)	`<\|im_end\|>` (2)
`bos_token_id`	0	1
`eos_token_id`	0	2

These are also set in config.json.

(Subsumes PRs #2, #3)

`enable_thinking` chat template support

The Ouro-Thinking model enters chain-of-thought reasoning mode when <think> is prepended to the assistant turn, but the current chat template does not support triggering this.

This PR adds enable_thinking parameter support (following the convention from Qwen3 and DeepSeek-R1), so that:

tokenizer.apply_chat_template(messages, add_generation_prompt=True, enable_thinking=True)
# produces: ...<|im_start|>assistant\n<think>\n

Backward compatible — default behavior is unchanged (no <think> unless explicitly requested).

This also enables proper integration with vLLM and lm-eval-harness, which pass enable_thinking=True to apply_chat_template().

Fix bos/eos token IDs + add enable_thinking to chat template8f196b8a

KristianS7

Feb 20

•

edited Feb 20

Thanks to @sirorezka for identifying the bos/eos/pad token ID issues in PRs #2, #3. This PR bundles those fixes together with the enable_thinking chat template change.

ridger

ByteDance org Feb 26

Thank you so much!

ridger changed pull request status to merged Feb 26

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment

Fix bos/eos token IDs + add enable_thinking to chat template

Summary

Token ID fixes

enable_thinking chat template support

`enable_thinking` chat template support