Spaces:
Runtime error
Runtime error
File size: 1,649 Bytes
a1084bc 3ce52c0 90f74fc a1084bc 3ce52c0 a1084bc 90f74fc |
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
from transformers import LlamaTokenizer, LlamaForCausalLM, GenerationConfig
tokenizer = LlamaTokenizer.from_pretrained("decapoda-research/llama-13b-hf")
model = LlamaForCausalLM.from_pretrained(
"decapoda-research/llama-13b-hf",
load_in_8bit=True,
torch_dtype=torch.float16,
device_map="auto",
)
model = PeftModel.from_pretrained(
model, "baruga/alpaca-lora-13b",
torch_dtype=torch.float16
)
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. Answer step by step.
### Instruction:
{instruction}
### Input:
{input}
### Response:"""
else:
return f"""Below is an instruction that describes a task. Write a response that appropriately completes the request. Answer step by step.
### Instruction:
{instruction}
### Response:"""
generation_config = GenerationConfig(
temperature=0.1,
top_p=0.75,
num_beams=4,
)
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())
|