Downloads · 30 days
31
4% of all-time downloads
Pythia410m-Instruct-SFT
SummerSigh/Pythia410m-Instruct-SFT
Pythia410m-Instruct-SFT is a text generation model from SummerSigh. Use it when you need the model to write or continue text. It is set up for transformers.
All-time downloads
825
Public
Parameters
506M
5.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.7 GB · 50%
Parameter types
How the weights are stored.
F32405M · 80%
Try a prompt
Model card
From the Hugging Face model README
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)
- Task
- Text Generation
- Library
- transformers
- Type
- gpt_neox
- Created
- Mar 4, 2023
- Updated
- Mar 19, 2023