Spaces:
Runtime error
Runtime error
File size: 1,849 Bytes
cba212b |
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 |
import torch
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, AutoTokenizer, GenerationConfig
peft_model_id = "mrm8488/falcon-7b-ft-codeAlpaca_20k-v2" # adapter
config = PeftConfig.from_pretrained(peft_model_id)
model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path, return_dict=True, load_in_8bit=True, device_map={"":0}, trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(peft_model_id)
model = PeftModel.from_pretrained(model, peft_model_id)
model.eval()
def generate(
instruction,
max_new_tokens=128,
temperature=0.1,
top_p=0.75,
top_k=40,
num_beams=4,
**kwargs
):
prompt = instruction + "\n### Solution:\n"
print(prompt)
inputs = tokenizer(prompt, return_tensors="pt")
input_ids = inputs["input_ids"].to("cuda")
attention_mask = inputs["attention_mask"].to("cuda")
generation_config = GenerationConfig(
temperature=temperature,
top_p=top_p,
top_k=top_k,
num_beams=num_beams,
**kwargs,
)
with torch.no_grad():
generation_output = model.generate(
input_ids=input_ids,
attention_mask=attention_mask,
generation_config=generation_config,
return_dict_in_generate=True,
output_scores=True,
max_new_tokens=max_new_tokens,
early_stopping=True
)
s = generation_output.sequences[0]
output = tokenizer.decode(s)
return output.split("### Solution:")[1].lstrip("\n")
import gradio as gr
def my_function(input):
# Perform your task or computation using the input
# Return the output/result
return output
iface = gr.Interface(fn=my_function, inputs="text", outputs="text")
iface.launch()
|