Some problems in the demonstration example

[T-Atlas]

When I try :

Instruction: Tell me about the president of Mexico in 2019.

I get

Response: The president of Mexico in 2019 was Andrés Manuel López Obrador, who took office on December 1st, 2018. He is a member of the National Regeneration Movement (MORENA) political party and is the first left-wing president of Mexico since 1946. He is known for his anti-corruption and anti-neolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioliolioli

Instead of

The president of Mexico in 2019 was Andrés Manuel López Obrador, who took office on December 1, 2018. He is a member of the National Regeneration Movement (MORENA) political party and is the first left-wing president of Mexico since 1946. He is known for his anti-corruption and anti-neoliberal policies, as well as his commitment to improving the living conditions of the Mexican people.

---

I just add device_map={'': 0} follow the https://github.com/tloen/alpaca-lora/issues/14#issuecomment-1471263165

[tloen]

I couldn't reproduce this on my end, but after sleeping on it I think it might have to do with Huggingface Accelerate. Will investigate today.

What hardware are you running, and do you have Accelerate installed?

[younesbelkada]

If you are using a V100 this might be of interest: https://github.com/huggingface/transformers/pull/21955#issuecomment-1458250372 tweaking the llm_int8_threshold should maybe help Also make sure you are using one of the latest bitsandbytes version (at least 0.37.0)

[T-Atlas]

I couldn't reproduce this on my end, but after sleeping on it I think it might have to do with Huggingface Accelerate. Will investigate today.

What hardware are you running, and do you have Accelerate installed?

I using a V100 and install latest Accelerate

[T-Atlas]

If you are using a V100 this might be of interest: huggingface/transformers#21955 (comment) tweaking the llm_int8_threshold should maybe help Also make sure you are using one of the latest bitsandbytes version (at least 0.37.0)

I will try it

[T-Atlas]

Unfortunately, I have forgotten the parameter setting when my problem occurred. Because I tried to take some alternatives, such as modifying num_ Beams. I'm sure your solution works because it's similar to mine. Previously, I also observed that some answers could not be generated to return null questions, which I hope will be resolved and I will keep testing.

import os
os.environ["CUDA_VISIBLE_DEVICES"] = "0"
import torch
from peft import PeftModel
from transformers import LLaMATokenizer, LLaMAForCausalLM, GenerationConfig,BitsAndBytesConfig

tokenizer = LLaMATokenizer.from_pretrained("decapoda-research/llama-7b-hf",cache_dir="./cache/")

model = LLaMAForCausalLM.from_pretrained(
    "decapoda-research/llama-7b-hf",
    load_in_8bit=True,
    quantization_config = BitsAndBytesConfig(load_in_8bit=True, llm_int8_threshold=5.0),
    torch_dtype=torch.float16,
    device_map={'': 0},cache_dir="./cache/"
)
model = PeftModel.from_pretrained(
    model, "tloen/alpaca-lora-7b", torch_dtype=torch.float16,cache_dir="./cache/",device_map={'': 0}
)


def evaluate(instruction, input=None, **kwargs):
    prompt = generate_prompt(instruction, input)
    inputs = tokenizer(prompt, return_tensors="pt")
    input_ids = inputs["input_ids"].cuda()
    generation_config = GenerationConfig(
        temperature=0.7,
        top_p=1.0,
        num_beams=5,
        **kwargs,
    )
    generation_output = model.generate(
        input_ids=input_ids,
        generation_config=generation_config,
        return_dict_in_generate=True,
        output_scores=True,
        max_new_tokens=1024,
    )
    s = generation_output.sequences[0]
    output = tokenizer.decode(s)
    return output.split("### Response:")[1].strip()


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()

[Aekansh-Ak]

In your code-:

def evaluate(instruction, input=None, **kwargs): prompt = generate_prompt(instruction, input) inputs = tokenizer(prompt, return_tensors="pt") input_ids = inputs["input_ids"].cuda() generation_config = GenerationConfig( temperature=0.7, top_p=1.0, num_beams=5, **kwargs, ) generation_output = model.generate( input_ids=input_ids, generation_config=generation_config, return_dict_in_generate=True, output_scores=True, max_new_tokens=1024, ) s = generation_output.sequences[0] output = tokenizer.decode(s) return output.split("### Response:")[1].strip()

1. What is function generate_prompt?
2. Input is "None" so, this shouldn't inputs["input_ids"] return error.