Spaces:
Runtime error
Runtime error
File size: 2,738 Bytes
0c8c4f5 8272482 0c8c4f5 319b4d3 0c8c4f5 52102b1 06e5052 0d5d23d 0c8c4f5 0d5d23d d048f50 0d5d23d 52102b1 0c8c4f5 06e5052 bc29f4e 06e5052 0c8c4f5 bc29f4e 0c8c4f5 52102b1 0c8c4f5 319b4d3 0010001 8a97208 0010001 eb443cd 4789c94 c928ad3 | 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 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 | # import gradio as gr
# from transformers import AutoModelForCausalLM, AutoTokenizer
# from gpt4all import GPT4All
# model = GPT4All("wizardlm-13b-v1.1-superhot-8k.ggmlv3.q4_0.bin")
#----------------------------------------------------------------------------------------------------------------------------
from transformers import AutoModelForCausalLM, AutoTokenizer
# Path to the model directory (assuming it's in the same directory as your script)
model_directory = "./"
# Load the model and tokenizer
model = AutoModelForCausalLM.from_pretrained(model_directory, from_tf=True)
tokenizer = AutoTokenizer.from_pretrained(model_directory, trust_remote_code=True)
# Now you can generate text as before
# prompt = "What is a large language model?"
# input_ids = tokenizer.encode(prompt, return_tensors="pt")
# output = model.generate(input_ids, max_length=200, num_return_sequences=1)
# generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
# print(generated_text)
# ---------------------------------------------------------------------------------------------------------------------------------------------------------------------
# Ignore warnings
logging.set_verbosity(logging.CRITICAL)
# Run text generation pipeline with our next model
# prompt = "What is a large language model?"
# pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=200)
# result = pipe(f"<s>[INST] {prompt} [/INST]")
# print(result[0]['generated_text'])
#---------------------------------------------------------------------------------------------------------------------------------------------------------------------
# Ignore warnings
# logging.set_verbosity(logging.CRITICAL)
# Run text generation pipeline with our next model
# prompt = "What is a large language model?"
# pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=200)
# result = pipe(f"<s>[INST] {prompt} [/INST]")
# print(result[0]['generated_text'])
def generate_text(prompt):
# output = model.generate(input_text)
# pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=200)
# result = pipe(f"<s>[INST] {prompt} [/INST]")
# prompt = "What is a large language model?"
input_ids = tokenizer.encode(prompt, return_tensors="pt")
output = model.generate(input_ids, max_length=200, num_return_sequences=1)
result = tokenizer.decode(output[0], skip_special_tokens=True)
return result
text_generation_interface = gr.Interface(
fn=generate_text,
inputs=[
gr.inputs.Textbox(label="Input Text"),
],
outputs=gr.outputs.Textbox(label="Generated Text"),
title="GPT-4 Text Generation",
).launch()
# model_name = ""
|