Instructions to use codingmonster1234/Llama-3.1-Minitron-4B-Chess-Reasoning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use codingmonster1234/Llama-3.1-Minitron-4B-Chess-Reasoning with Transformers:

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

pipe = pipeline("text-generation", model="codingmonster1234/Llama-3.1-Minitron-4B-Chess-Reasoning")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("codingmonster1234/Llama-3.1-Minitron-4B-Chess-Reasoning")
model = AutoModelForMultimodalLM.from_pretrained("codingmonster1234/Llama-3.1-Minitron-4B-Chess-Reasoning")
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 codingmonster1234/Llama-3.1-Minitron-4B-Chess-Reasoning with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "codingmonster1234/Llama-3.1-Minitron-4B-Chess-Reasoning"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "codingmonster1234/Llama-3.1-Minitron-4B-Chess-Reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/codingmonster1234/Llama-3.1-Minitron-4B-Chess-Reasoning

SGLang

How to use codingmonster1234/Llama-3.1-Minitron-4B-Chess-Reasoning 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 "codingmonster1234/Llama-3.1-Minitron-4B-Chess-Reasoning" \
    --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": "codingmonster1234/Llama-3.1-Minitron-4B-Chess-Reasoning",
		"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 "codingmonster1234/Llama-3.1-Minitron-4B-Chess-Reasoning" \
        --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": "codingmonster1234/Llama-3.1-Minitron-4B-Chess-Reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use codingmonster1234/Llama-3.1-Minitron-4B-Chess-Reasoning with Docker Model Runner:
```
docker model run hf.co/codingmonster1234/Llama-3.1-Minitron-4B-Chess-Reasoning
```

Llama-3.1-Minitron-4B-Chess-Reasoning / README.md

codingmonster1234

Update README.md

363425a verified 2 days ago

preview code

raw

history blame contribute delete

1.78 kB

	---
	base_model: rasyosef/Llama-3.1-Minitron-4B-Chat
	library_name: transformers
	model_name: output-Llama-3.1-Minitron-4B-Chat
	tags:
	- generated_from_trainer
	- sft
	- trl
	- chess
	- reasoning
	licence: license
	license: mit
	datasets:
	- codingmonster1234/chess-reasoning-sft
	language:
	- en
	---

	# Model Card for output-Llama-3.1-Minitron-4B-Chat

	This model is a fine-tuned version of [rasyosef/Llama-3.1-Minitron-4B-Chat](https://huggingface.co/rasyosef/Llama-3.1-Minitron-4B-Chat).
	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="None", 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/easwar-chess-none/huggingface/runs/ulmc14g2)



	This model was trained with SFT.

	### Framework versions

	- TRL: 1.5.1
	- Transformers: 5.10.2
	- Pytorch: 2.12.0
	- Datasets: 5.0.0
	- Tokenizers: 0.22.2

	## Citations



	Cite TRL as:

	```bibtex
	@software{vonwerra2020trl,
	title = {{TRL: Transformers Reinforcement Learning}},
	author = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
	license = {Apache-2.0},
	url = {https://github.com/huggingface/trl},
	year = {2020}
	}
	```