Instructions to use SummerSigh/Pythia410m-V1-Instruct-SystemPromptTuning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SummerSigh/Pythia410m-V1-Instruct-SystemPromptTuning with Transformers:

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

pipe = pipeline("text-generation", model="SummerSigh/Pythia410m-V1-Instruct-SystemPromptTuning")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SummerSigh/Pythia410m-V1-Instruct-SystemPromptTuning")
model = AutoModelForCausalLM.from_pretrained("SummerSigh/Pythia410m-V1-Instruct-SystemPromptTuning")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use SummerSigh/Pythia410m-V1-Instruct-SystemPromptTuning with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SummerSigh/Pythia410m-V1-Instruct-SystemPromptTuning"
# 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-V1-Instruct-SystemPromptTuning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SummerSigh/Pythia410m-V1-Instruct-SystemPromptTuning

SGLang

How to use SummerSigh/Pythia410m-V1-Instruct-SystemPromptTuning 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-V1-Instruct-SystemPromptTuning" \
    --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-V1-Instruct-SystemPromptTuning",
		"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-V1-Instruct-SystemPromptTuning" \
        --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-V1-Instruct-SystemPromptTuning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use SummerSigh/Pythia410m-V1-Instruct-SystemPromptTuning with Docker Model Runner:
```
docker model run hf.co/SummerSigh/Pythia410m-V1-Instruct-SystemPromptTuning
```

Model info

This is Pythia410m-V1-Instruct finetuned on No Robots. This is so it follows system prompts better.

from transformers import pipeline

pipe = pipeline("text-generation", model="SummerSigh/Pythia410m-V1-Instruct-SystemPromptTuning")

out= pipe("<|im_start|>system\nYou are a good assistant designed to answer all prompts the user asks.<|im_end|><|im_start|>user\nWhat's the meaning of life?<|im_end|><|im_start|>assistant\n",max_length  = 500,repetition_penalty = 1.2, temperature  = 0.5, do_sample = True)

print(out[0]["generated_text"])

Downloads last month: 6

Safetensors

Model size

0.4B params

Tensor type

F32

SummerSigh
/

Pythia410m-V1-Instruct-SystemPromptTuning

Model info

Dataset used to train SummerSigh/Pythia410m-V1-Instruct-SystemPromptTuning