File size: 2,118 Bytes
c92771c |
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 |
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
model_id = "clibrain/Llama-2-7b-ft-instruct-es"
model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True).to("cuda")
tokenizer = AutoTokenizer.from_pretrained(model_id)
def create_instruction(instruction, input_data=None, context=None):
sections = {
"Instrucci贸n": instruction,
"Entrada": input_data,
"Contexto": context,
}
system_prompt = "A continuaci贸n hay una instrucci贸n que describe una tarea, junto con una entrada que proporciona m谩s contexto. Escriba una respuesta que complete adecuadamente la solicitud.\n\n"
prompt = system_prompt
for title, content in sections.items():
if content is not None:
prompt += f"### {title}:\n{content}\n\n"
prompt += "### Respuesta:\n"
return prompt
def generate(
instruction,
input=None,
context=None,
max_new_tokens=128,
temperature=0.1,
top_p=0.75,
top_k=40,
num_beams=4,
**kwargs
):
prompt = create_instruction(instruction, input, context)
print(prompt.replace("### Respuesta:\n", ""))
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("### Respuesta:")[1].lstrip("\n")
instruction = "Dame una lista de lugares a visitar en Espa帽a."
print(generate(instruction))
|