File size: 915 Bytes
d8c99c6 052012f cc07ecd 3dbb79e 65b75e6 6aa7c2f 65e2225 052012f 65e2225 052012f 65e2225 cc07ecd 65e2225 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 |
import gradio as gr
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("NousResearch/Llama-2-7b-chat-hf") #meta-llama/Llama-2-7b-hf
model = AutoModelForCausalLM.from_pretrained("NousResearch/Llama-2-7b-chat-hf")
def eval_text(text):
# Encode the input text
input_ids = tokenizer.encode(text, return_tensors="pt")
# Generate text
out = model.generate(
input_ids,
min_length=100,
max_length=100,
eos_token_id=5,
pad_token_id=1,
top_k=10,
top_p=0.0,
no_repeat_ngram_size=5
)
# Decode the generated output
generated_text = list(map(tokenizer.decode, out))[0]
print(generated_text)
return(f"Result: {generation[0]['generated_text']}")
demo = gr.Interface(fn=eval_text, inputs="text", outputs="text", title="Llama2")
demo.launch(share=True) |