File size: 3,572 Bytes
2ec8e16 |
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 |
import os
import sys
import fire
import torch
from peft import PeftModel
from transformers import GenerationConfig, LlamaForCausalLM, LlamaTokenizer
from utils.prompter import Prompter
if torch.cuda.is_available():
device = "cuda"
else:
device = "cpu"
try:
if torch.backends.mps.is_available():
device = "mps"
except:
pass
def main(
load_8bit: bool = False,
base_model: str = "",
lora_weights: str = "DSMI/LLaMA-E/7b",
prompt_template: str = "",
):
print("lora_weights: " + str(lora_weights))
base_model = base_model or os.environ.get("BASE_MODEL", "")
prompter = Prompter(prompt_template)
tokenizer = LlamaTokenizer.from_pretrained(base_model)
if device == "cuda":
model = LlamaForCausalLM.from_pretrained(
base_model,
load_in_8bit=load_8bit,
torch_dtype=torch.float16,
device_map="auto",
)
model = PeftModel.from_pretrained(
model,
lora_weights,
torch_dtype=torch.float16,
)
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 = LlamaForCausalLM.from_pretrained(
base_model, device_map={"": device}, low_cpu_mem_usage=True
)
model = PeftModel.from_pretrained(
model,
lora_weights,
device_map={"": device},
)
model.config.pad_token_id = tokenizer.pad_token_id = 0 # unk
model.config.bos_token_id = 1
model.config.eos_token_id = 2
if not load_8bit:
model.half() # seems to fix bugs for some users.
model.eval()
if torch.__version__ >= "2" and sys.platform != "win32":
model = torch.compile(model)
def evaluate(
instruction,
input=None,
temperature=0.1,
top_p=0.75,
top_k=40,
num_beams=4,
max_new_tokens=128,
**kwargs,
):
prompt = prompter.generate_prompt(instruction, input)
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.no_grad():
generation_output = model.generate(
input_ids=input_ids,
generation_config=generation_config,
return_dict_in_generate=True,
output_scores=True,
max_new_tokens=max_new_tokens,
)
s = generation_output.sequences[0]
output = tokenizer.decode(s)
return prompter.get_response(output).split("</s>")[0]
print()
instruction = "Where can I buy the handmade jewellery?"
print("Instruction:", instruction)
print("Response:", evaluate(instruction))
print()
instruction = "Generate an ad for the following product."
input = "Emerald Teardrop Necklace.May Birthstone Pendant.Dainty Gift for Her.925 Sterling Silver.Spring Sale"
print("Instruction:", instruction)
print("Input:", input)
print("Response:", evaluate(instruction, input))
print()
if __name__ == "__main__":
fire.Fire(main) |