Downloads · 30 days
23
8% of all-time downloads
ShakespeareGPT
GeneralRincewind/ShakespeareGPT
ShakespeareGPT is a text generation model from GeneralRincewind. Use it when you need the model to write or continue text. It is set up for transformers.
https://colab.research.google.com/drive/1Dlm8FA9JjjcqJIkfCagaIQWex8Ho5IKIscrollTo=e8xIjRNsl3Bb
All-time downloads
276
Public
Repo size
13.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin13.5 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- llama
- Access
- Public
- Created
- Aug 13, 2023
- Updated
- Aug 13, 2023
- SHA
- 8707572c
Try a prompt
Model card
From the Hugging Face model README
https://colab.research.google.com/drive/1Dlm8FA9JjjcqJIkfCagaIQWex8Ho5IKI#scrollTo=e8xIjRNsl3Bb
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("GeneralRincewind/ShakespeareGPT")
model = AutoModelForCausalLM.from_pretrained("GeneralRincewind/ShakespeareGPT")
#### Generate text
from transformers import TextStreamer
tokenized_text = tokenizer("", return_tensors="pt", truncation=True)
input_ids = tokenized_text.input_ids
streamer = TextStreamer(tokenizer)
model.eval()
full_completion = model.generate(inputs=tokenized_text["input_ids"].to("cuda"),
attention_mask=tokenized_text["attention_mask"].to("cuda"),
temperature=0.9,
top_k=80,
top_p=0.65,
do_sample=True,
streamer=streamer,
num_beams=1,
max_new_tokens=500,
eos_token_id=tokenizer.eos_token_id,
pad_token_id=tokenizer.pad_token_id,
repetition_penalty=1)
decoded_text = tokenizer.decode(full_completion[0])
print(decoded_text)
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- Created
- Aug 13, 2023
- Updated
- Aug 13, 2023