File size: 1,574 Bytes
21c18e3 638c781 35c007b 8a681fd f264eed 4c39ff2 638c781 21c18e3 35c007b 21c18e3 638c781 f264eed 21c18e3 |
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 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 |
import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
from ctransformers import AutoConfig
import os
hf_token = os.environ.get('HF_TOKEN')
from huggingface_hub import login
login(token=hf_token)
config = AutoConfig.from_pretrained( "mistralai/Mistral-7B-Instruct-v0.1")
config.config.max_new_tokens = 2000
config.config.context_length = 4000 )
model = AutoModelForCausalLM.from_pretrained(
"mistralai/Mistral-7B-Instruct-v0.1",
token = hf_token,
torch_dtype=torch.bfloat16,
trust_remote_code=True,
device_map="auto",
config=config)
tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.1", token = hf_token)
def generate_text(input_text):
input_ids = tokenizer.encode(input_text, return_tensors="pt")
attention_mask = torch.ones(input_ids.shape)
output = model.generate(
input_ids,
attention_mask=attention_mask,
max_length=200,
do_sample=True,
top_k=10,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id,
)
output_text = tokenizer.decode(output[0], skip_special_tokens=True)
print(output_text)
# Remove Prompt Echo from Generated Text
cleaned_output_text = output_text.replace(input_text, "")
return cleaned_output_text
text_generation_interface = gr.Interface(
fn=generate_text,
inputs=[
gr.inputs.Textbox(label="Input Text"),
],
outputs=gr.inputs.Textbox(label="Generated Text")).launch() |