Instructions to use SurjoLabs/Surjo-50m-SFT-Only with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SurjoLabs/Surjo-50m-SFT-Only with Transformers:

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

pipe = pipeline("text-generation", model="SurjoLabs/Surjo-50m-SFT-Only", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("SurjoLabs/Surjo-50m-SFT-Only", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SurjoLabs/Surjo-50m-SFT-Only with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SurjoLabs/Surjo-50m-SFT-Only"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SurjoLabs/Surjo-50m-SFT-Only",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SurjoLabs/Surjo-50m-SFT-Only

SGLang

How to use SurjoLabs/Surjo-50m-SFT-Only 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 "SurjoLabs/Surjo-50m-SFT-Only" \
    --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": "SurjoLabs/Surjo-50m-SFT-Only",
		"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 "SurjoLabs/Surjo-50m-SFT-Only" \
        --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": "SurjoLabs/Surjo-50m-SFT-Only",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SurjoLabs/Surjo-50m-SFT-Only with Docker Model Runner:
```
docker model run hf.co/SurjoLabs/Surjo-50m-SFT-Only
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Model Card for Surjo-50m-Instruct

This model is a fine-tuned version of SurjoLabs/Surjo-50m. It has been trained using TRL.

Quick start

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="SurjoLabs/Surjo-50m-Instruct", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

This model was trained with SFT.

Framework versions

TRL: 1.12.0
Transformers: 5.16.1
Pytorch: 2.13.0+cu130
Datasets: 5.0.1
Tokenizers: 0.23.2

Citations

Cite TRL as:

@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}
}

Downloads last month: 77

Safetensors

Model size

53.8M params

Tensor type

F32

BF16

Model tree for SurjoLabs/Surjo-50m-SFT-Only

Base model

SurjoLabs/Surjo-50m

Finetuned

(1)

this model