Instructions to use SummerSigh/Pythia410m-Instruct-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SummerSigh/Pythia410m-Instruct-SFT with Transformers:

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

pipe = pipeline("text-generation", model="SummerSigh/Pythia410m-Instruct-SFT")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SummerSigh/Pythia410m-Instruct-SFT")
model = AutoModelForCausalLM.from_pretrained("SummerSigh/Pythia410m-Instruct-SFT")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use SummerSigh/Pythia410m-Instruct-SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SummerSigh/Pythia410m-Instruct-SFT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SummerSigh/Pythia410m-Instruct-SFT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SummerSigh/Pythia410m-Instruct-SFT

SGLang

How to use SummerSigh/Pythia410m-Instruct-SFT 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 "SummerSigh/Pythia410m-Instruct-SFT" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SummerSigh/Pythia410m-Instruct-SFT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "SummerSigh/Pythia410m-Instruct-SFT" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SummerSigh/Pythia410m-Instruct-SFT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use SummerSigh/Pythia410m-Instruct-SFT with Docker Model Runner:
```
docker model run hf.co/SummerSigh/Pythia410m-Instruct-SFT
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Usage:

from transformers import pipeline
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SummerSigh/Pythia410m-Instruct-SFT")
generator = pipeline('text-generation', model = 'SummerSigh/Pythia410m-Instruct-SFT')

inpopo  = input("Text here: ")

text = generator("<user>" + inpopo  + "<user><kinrel>" ,  max_length = 200, do_sample=True, top_p = 0.7, temperature = 0.5, repetition_penalty  = 1.2, pad_token_id=tokenizer.eos_token_id)
generated_text = text[0]["generated_text"]
parts = generated_text.split("<kinrel>")
cropped_text = "<kinrel>".join(parts[:2]) + "<kinrel>"
print(cropped_text)

Downloads last month: 7

Safetensors

Model size

0.5B params

Tensor type

F32

Model tree for SummerSigh/Pythia410m-Instruct-SFT

Quantizations

2 models