Instructions to use Shekswess/tiny-think-sft-math-stem-loss-dft-bf16-lr5e-5-e2-bs8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Shekswess/tiny-think-sft-math-stem-loss-dft-bf16-lr5e-5-e2-bs8 with Transformers:

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

pipe = pipeline("text-generation", model="Shekswess/tiny-think-sft-math-stem-loss-dft-bf16-lr5e-5-e2-bs8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Shekswess/tiny-think-sft-math-stem-loss-dft-bf16-lr5e-5-e2-bs8")
model = AutoModelForCausalLM.from_pretrained("Shekswess/tiny-think-sft-math-stem-loss-dft-bf16-lr5e-5-e2-bs8")
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

vLLM

How to use Shekswess/tiny-think-sft-math-stem-loss-dft-bf16-lr5e-5-e2-bs8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Shekswess/tiny-think-sft-math-stem-loss-dft-bf16-lr5e-5-e2-bs8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Shekswess/tiny-think-sft-math-stem-loss-dft-bf16-lr5e-5-e2-bs8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Shekswess/tiny-think-sft-math-stem-loss-dft-bf16-lr5e-5-e2-bs8

SGLang

How to use Shekswess/tiny-think-sft-math-stem-loss-dft-bf16-lr5e-5-e2-bs8 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 "Shekswess/tiny-think-sft-math-stem-loss-dft-bf16-lr5e-5-e2-bs8" \
    --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": "Shekswess/tiny-think-sft-math-stem-loss-dft-bf16-lr5e-5-e2-bs8",
		"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 "Shekswess/tiny-think-sft-math-stem-loss-dft-bf16-lr5e-5-e2-bs8" \
        --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": "Shekswess/tiny-think-sft-math-stem-loss-dft-bf16-lr5e-5-e2-bs8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Shekswess/tiny-think-sft-math-stem-loss-dft-bf16-lr5e-5-e2-bs8 with Docker Model Runner:
```
docker model run hf.co/Shekswess/tiny-think-sft-math-stem-loss-dft-bf16-lr5e-5-e2-bs8
```

Shekswess commited on Jan 28

Commit

112f784

verified ·

1 Parent(s): 2ff7539

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -34

README.md CHANGED Viewed

@@ -14,45 +14,14 @@ licence: license
 This model is a fine-tuned version of [facebook/MobileLLM-R1-140M-base](https://huggingface.co/facebook/MobileLLM-R1-140M-base).
 It has been trained using [TRL](https://github.com/huggingface/trl).
-## Quick start
-```python
-from transformers import pipeline
-question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="Shekswess/tiny-think-sft-math-stem-loss-dft-bf16-lr5e-5-e2-bs8", device="cuda")
-output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
-print(output["generated_text"])
-```
 ## Training procedure
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/bokicasheks-loka/tiny_think/runs/asfyk72n)
 This model was trained with SFT.
 ### Framework versions
 - TRL: 0.26.2
-- Transformers: 4.57.5
 - Pytorch: 2.9.0+cu128
-- Datasets: 4.5.0
-- Tokenizers: 0.22.2
-## Citations
-Cite TRL as:
-```bibtex
-@misc{vonwerra2022trl,
-	title        = {{TRL: Transformer Reinforcement Learning}},
-	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
-	year         = 2020,
-	journal      = {GitHub repository},
-	publisher    = {GitHub},
-	howpublished = {\url{https://github.com/huggingface/trl}}
-}
-```

 This model is a fine-tuned version of [facebook/MobileLLM-R1-140M-base](https://huggingface.co/facebook/MobileLLM-R1-140M-base).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Training procedure
 This model was trained with SFT.
 ### Framework versions
 - TRL: 0.26.2
+- Transformers: 4.57.3
 - Pytorch: 2.9.0+cu128
+- Datasets: 4.4.2
+- Tokenizers: 0.22.2