Spaces:
Sleeping
Sleeping
File size: 2,326 Bytes
1c0e302 075341e 1c0e302 4671f72 1c0e302 4671f72 1c0e302 075341e 1c0e302 d799106 1c0e302 39687cb b12f8f0 1c0e302 |
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 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 |
import pathlib
import gradio as gr
import transformers
from transformers import AutoTokenizer
from transformers import AutoModelForCausalLM
from transformers import GenerationConfig
from typing import List, Dict, Union
from typing import Any, TypeVar
Pathable = Union[str, pathlib.Path]
def load_model(name: str) -> Any:
return AutoModelForCausalLM.from_pretrained(name)
def load_tokenizer(name: str) -> Any:
return AutoTokenizer.from_pretrained(name)
def create_generator():
return GenerationConfig(
temperature=1.0,
top_p=0.75,
num_beams=4,
)
def generate_prompt(instruction, input=None):
if input:
return f"""Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
### Instruction:
{instruction}
### Input:
{input}
### Response:"""
else:
return f"""Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{instruction}
### Response:"""
def evaluate(instruction, input=None):
prompt = generate_prompt(instruction, input)
inputs = tokenizer(prompt, return_tensors="pt")
input_ids = inputs["input_ids"].cuda()
generation_output = model.generate(
input_ids=input_ids,
generation_config=generation_config,
return_dict_in_generate=True,
output_scores=True,
max_new_tokens=256
)
for s in generation_output.sequences:
output = tokenizer.decode(s)
print("Response:", output.split("### Response:")[1].strip())
def inference(text):
output = evaluate(instruction = text, input = input)
return output
io = gr.Interface(
inference,
gr.Textbox(
lines = 3, max_lines = 10,
placeholder = "Add question here",
interactive = True,
show_label = False
),
# gr.Textbox(
# lines = 3,
# max_lines = 25,
# placeholder = "add context here",
# interactive = True,
# show_label = False
# ),
outputs =[
gr.Textbox(lines = 2, label = 'Pythia410m output', interactive = False)
],
cache_examples = False,
)
io.launch()
#gr.Interface.load("models/s3nh/pythia-410m-70k-steps-self-instruct-polish").launch()
|