Instructions to use SupraLabs/supra-title-FFT-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SupraLabs/supra-title-FFT-preview with Transformers:

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

pipe = pipeline("text-generation", model="SupraLabs/supra-title-FFT-preview")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("SupraLabs/supra-title-FFT-preview")
model = AutoModelForMultimodalLM.from_pretrained("SupraLabs/supra-title-FFT-preview")
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 SupraLabs/supra-title-FFT-preview with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/SupraLabs/supra-title-FFT-preview

SGLang

How to use SupraLabs/supra-title-FFT-preview 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 "SupraLabs/supra-title-FFT-preview" \
    --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": "SupraLabs/supra-title-FFT-preview",
		"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 "SupraLabs/supra-title-FFT-preview" \
        --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": "SupraLabs/supra-title-FFT-preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use SupraLabs/supra-title-FFT-preview with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for SupraLabs/supra-title-FFT-preview to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for SupraLabs/supra-title-FFT-preview to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SupraLabs/supra-title-FFT-preview to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="SupraLabs/supra-title-FFT-preview",
    max_seq_length=2048,
)

Docker Model Runner
How to use SupraLabs/supra-title-FFT-preview with Docker Model Runner:
```
docker model run hf.co/SupraLabs/supra-title-FFT-preview
```

SupraTitle (preview) Overview

Our first chat title model on the LFM2.5-350M-base model (SupraLabs/Supra-Title-350M-exp-GGUF) was trained on 12K samples on our first opensource chat title dataset (SupraLabs/chat-titles-12K) which had less training samples and didnt cover niche areas. SupraLabs/supra-title-FFT-preview is trained on 115k samples whereas 12k samples on our first model.

According to our naming conventions, this model is the last Chat Title model before the final model (...preview)

Downloads last month: -

Safetensors

Model size

0.4B params

Tensor type

BF16

Model tree for SupraLabs/supra-title-FFT-preview

Base model

LiquidAI/LFM2.5-350M-Base

Finetuned

(10)

this model

Dataset used to train SupraLabs/supra-title-FFT-preview

Collection including SupraLabs/supra-title-FFT-preview

Supra-Title

Collection

All Supra-Title models • 3 items • Updated about 22 hours ago • 5