https://huggingface.co/Bruno/Harpia-7b-guanacoLora/blob/main/har.png
Harpia
Adapter Description
This adapter was created with the PEFT library and allowed the base model Falcon-7b to be fine-tuned on the timdettmers/openassistant-guanaco by using the method QLoRA.
Model description
Intended uses & limitations
TBA
Training and evaluation data
TBA
Training results
How to use
import torch
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, AutoTokenizer, GenerationConfig
peft_model_id = "Bruno/Harpia-7b-guanacoLora"
config = PeftConfig.from_pretrained(peft_model_id)
bnb_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype=torch.float16,
)
tokenizer = AutoTokenizer.from_pretrained(peft_model_id)
model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path,
return_dict=True,
quantization_config=bnb_config,
trust_remote_code=True,
device_map={"":0})
prompt_input = ""
prompt_no_input = ""
def create_prompt(instruction, input=None):
if input:
return prompt_input.format(instruction=instruction, input=input)
else:
return prompt_no_input.format(instruction=instruction)
def generate(
instruction,
input=None,
max_new_tokens=128,
temperature=0.1,
top_p=0.75,
top_k=40,
num_beams=4,
**kwargs,
):
prompt = create_prompt(instruction, input)
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
)
s = generation_output.sequences[0]
output = tokenizer.decode(s)
return output.split("### Respuesta:")[1]
instruction = "Me conte algumas curiosidades sobre o Brasil"
print("Instruções:", instruction)
print("Resposta:", generate(instruction))
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 1
Inference API (serverless) does not yet support adapter-transformers models for this pipeline type.