Spaces:
Sleeping
Sleeping
File size: 3,898 Bytes
dbbfa01 d4238f5 dbbfa01 d4238f5 2188fec dbbfa01 2188fec dbbfa01 9e21612 dbbfa01 b48f19a ac2d9b2 dbbfa01 2188fec 27a71a3 2188fec dbbfa01 2188fec dbbfa01 bbd42cd dbbfa01 |
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 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 |
import torch
from peft import PeftModel
import transformers
import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
tokenizer = AutoTokenizer.from_pretrained("bigscience/bloom-1b1")
BASE_MODEL = "bigscience/bloom-1b1"
LORA_WEIGHTS = "naot97/bloom1b1-zalo-test"
if torch.cuda.is_available():
device = "cuda"
else:
device = "cpu"
try:
if torch.backends.mps.is_available():
device = "mps"
except:
pass
if device == "cuda":
model = AutoModelForCausalLM.from_pretrained(
BASE_MODEL,
load_in_8bit=False,
torch_dtype=torch.float16,
device_map="auto",
)
model = PeftModel.from_pretrained(
model, LORA_WEIGHTS, torch_dtype=torch.float16, force_download=True
)
elif device == "mps":
model = LlamaForCausalLM.from_pretrained(
BASE_MODEL,
device_map={"": device},
torch_dtype=torch.float16,
)
model = PeftModel.from_pretrained(
model,
LORA_WEIGHTS,
device_map={"": device},
torch_dtype=torch.float16,
)
else:
model = AutoModelForCausalLM.from_pretrained(
BASE_MODEL, device_map={"": device}, low_cpu_mem_usage=True
)
model = PeftModel.from_pretrained(
model,
LORA_WEIGHTS,
device_map={"": device},
)
# 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:"""
if device != "cpu":
model.half()
model.eval()
if torch.__version__ >= "2":
model = torch.compile(model)
def evaluate(
instruction,
**kwargs,
):
temperature=0.1,
top_p=0.75,
top_k=40,
num_beams=4,
max_new_tokens=128,
prompt = instruction
inputs = tokenizer(prompt, return_tensors="pt")
input_ids = inputs["input_ids"].to(device)
generation_config = GenerationConfig(
temperature=temperature,
top_p=top_p,
top_k=top_k,
num_beams=num_beams,
**kwargs,
)
with torch.cuda.amp.autocast():
output_tokens = model.generate(**inputs, generation_config=generation_config)
output = tokenizer.decode(output_tokens[0], skip_special_tokens=True)
return output[len(input_ids):]
g = gr.Interface(
fn=evaluate,
inputs= gr.components.Textbox(
lines=2, label="Instruction", placeholder="Tell me raw text."
),
outputs= gr.inputs.Textbox(
lines=5,
label="Output",
),
title="bloom 1b1",
description="",
)
g.queue(concurrency_count=1)
g.launch()
# Old testing code follows.
"""
if __name__ == "__main__":
# testing code for readme
for instruction in [
"Tell me about alpacas.",
"Tell me about the president of Mexico in 2019.",
"Tell me about the king of France in 2019.",
"List all Canadian provinces in alphabetical order.",
"Write a Python program that prints the first 10 Fibonacci numbers.",
"Write a program that prints the numbers from 1 to 100. But for multiples of three print 'Fizz' instead of the number and for the multiples of five print 'Buzz'. For numbers which are multiples of both three and five print 'FizzBuzz'.",
"Tell me five words that rhyme with 'shock'.",
"Translate the sentence 'I have no mouth but I must scream' into Spanish.",
"Count up from 1 to 500.",
]:
print("Instruction:", instruction)
print("Response:", evaluate(instruction))
print()
"""
|