🐃🇹🇭 Buffala-LoRa-TH

Buffala-LoRA是一个使用7个参数的LLaMA模型，经过微调以遵循指令。它是在斯坦福大学的Alpaca（TH Translated），Wisesignt，WikiTH，Pantip和IAppQ&A数据集上进行训练的，并利用了Huggingface LLaMA实现。有关更多信息，请访问 the project's website

问题和下一步计划？

• 该模型仍然缺乏大量的世界知识，因此有必要在更大的泰国数据集上进行微调 > 下一个版本：CCNet，OSCAR，thWiki
• 目前还没有翻译提示。我们计划很快在SCB泰英数据集上对模型进行微调。
• 该模型与LangChain Search agent（Serpapi）配合使用效果良好，作为世界知识的临时解决方案 > Spaces与搜索链演示计划
• 缺乏聊天功能，等待LangChain实现。
• Colab演示。
• 用于数据集和训练笔记的Github。

如何使用

import torch
from peft import PeftModel
from transformers import GenerationConfig, LlamaForCausalLM, LlamaTokenizer


device = "cuda"

tokenizer = LlamaTokenizer.from_pretrained("decapoda-research/llama-7b-hf")
model = LlamaForCausalLM.from_pretrained(
    "decapoda-research/llama-7b-hf",
    load_in_8bit=True,
    torch_dtype=torch.float16,
    device_map="auto",
)
model = PeftModel.from_pretrained(
    model,
    "Thaweewat/thai-buffala-lora-7b-v0-1",
    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.
### Instruction:
{instruction}
### Input:
{input + get_list_and_snippet(instruction)}
### Response:"""
    else:
        return f"""Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{instruction}
### Input:
{get_list_and_snippet(instruction)}
### Response:"""

if not LOAD_8BIT:
    model.half()  

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 = 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 output.split("### Response:")[1].strip()

evaluate(instruction = "จงแก้สมการต่อไปนี้ X เท่ากับเท่าไหร่", input="X+Y=15 and Y=7")
""" X = 8 """