Instructions to use yingfanbot/gsm-cot-llama3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yingfanbot/gsm-cot-llama3b with Transformers:

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

pipe = pipeline("text-generation", model="yingfanbot/gsm-cot-llama3b", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yingfanbot/gsm-cot-llama3b")
model = AutoModelForCausalLM.from_pretrained("yingfanbot/gsm-cot-llama3b", device_map="auto")
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 yingfanbot/gsm-cot-llama3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yingfanbot/gsm-cot-llama3b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yingfanbot/gsm-cot-llama3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yingfanbot/gsm-cot-llama3b

SGLang

How to use yingfanbot/gsm-cot-llama3b 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 "yingfanbot/gsm-cot-llama3b" \
    --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": "yingfanbot/gsm-cot-llama3b",
		"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 "yingfanbot/gsm-cot-llama3b" \
        --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": "yingfanbot/gsm-cot-llama3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use yingfanbot/gsm-cot-llama3b with Docker Model Runner:
```
docker model run hf.co/yingfanbot/gsm-cot-llama3b
```

GSM8K CoT fine-tune of Llama-3.2-3B-Instruct

Built with Llama. Supervised chain-of-thought fine-tune of meta-llama/Llama-3.2-3B-Instruct on GSM8K.

This model serves as the Stage-1 CoT baseline/initialization checkpoint for LOTUS (Looped Transformers with parallel supervision on latents), as described in the paper Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("yingfanbot/gsm-cot-llama3b")
tokenizer = AutoTokenizer.from_pretrained("yingfanbot/gsm-cot-llama3b")

Citation

@misc{fan2026bridginggaplatentexplicit,
      title={Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers}, 
      author={Ying Fan and Anej Svete and Kangwook Lee},
      year={2026},
      eprint={2606.31779},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2606.31779}, 
}

Downloads last month: 193

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for yingfanbot/gsm-cot-llama3b

Base model

meta-llama/Llama-3.2-3B-Instruct

Finetuned

(1761)

this model

Paper for yingfanbot/gsm-cot-llama3b

Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers

Paper • 2606.31779 • Published 21 days ago • 2

yingfanbot
/

gsm-cot-llama3b