Code Monkey home page Code Monkey logo

Comments (10)

SparkJiao avatar SparkJiao commented on September 4, 2024
  1. inputs里面不需要加Human:或者Assistant:前缀,直接提问即可
  2. 7B的模型 要么greedy search要么beam search 不要加温度系数也不要采样,如果你想要多样性的回答可以用beam search取top-3
  3. 从你的例子来看主要有两个问题,事实性问题和无法停止,目前这两个问题在LLaMA系列里都很常见,即使是英文模型,后续可以在13B模型上试试

from pandallm.

frog-game avatar frog-game commented on September 4, 2024

好的感谢up主回答~
我把温度系数和采样删除试试

from pandallm.

SparkJiao avatar SparkJiao commented on September 4, 2024

另外你这个去除输入部分的代码不太对 len(inputs) + len(line)把line算了两遍?

你直接把inputs从batch decode的结果里replace掉不行吗

outputs = [seq.replace(self.tokenizer.decode(input_ids[i], skip_special_tokens=True), "")
                                     for i, seq in enumerate(rets)]

from pandallm.

frog-game avatar frog-game commented on September 4, 2024

这个是因为返回把前面的的iput也加进去了,我临时做得切片输出 比如你输入来首李白的诗句,然后他就会把李白的诗句也在输出的最前面输出出来

from pandallm.

SparkJiao avatar SparkJiao commented on September 4, 2024

我知道啊 因为这是decoder-only 我的意思是你去掉输入时候的切片为什么用rets[len(inputs) + len(line):] 而不是 rets[len(inputs):]

from pandallm.

frog-game avatar frog-game commented on September 4, 2024

我知道啊 因为这是decoder-only 我的意思是你去掉输入时候的切片为什么用rets[len(inputs) + len(line):] 而不是 rets[len(inputs):]

我试试哈,懂up主的意思了~

from pandallm.

frog-game avatar frog-game commented on September 4, 2024

我知道啊 因为这是decoder-only 我的意思是你去掉输入时候的切片为什么用rets[len(inputs) + len(line):] 而不是 rets[len(inputs):]

因为 那个line 也带了~

from pandallm.

frog-game avatar frog-game commented on September 4, 2024

我知道啊 因为这是decoder-only 我的意思是你去掉输入时候的切片为什么用rets[len(inputs) + len(line):] 而不是 rets[len(inputs):]

就是 有两段不需要的长度字符输出,一个是inputs的内容,一个是line的内容

from pandallm.

SparkJiao avatar SparkJiao commented on September 4, 2024

Reopen this if need further help.

from pandallm.

frog-game avatar frog-game commented on September 4, 2024
import torch
import sys
from transformers import AutoTokenizer, AutoModelForCausalLM, LlamaForCausalLM
import os
from accelerate import infer_auto_device_map

model_path = "/root/vicuna-7b"
model = LlamaForCausalLM.from_pretrained(
    model_path, device_map='auto', low_cpu_mem_usage=True)
tokenizer = AutoTokenizer.from_pretrained(model_path)

print('Human:')
line = input().strip()

while line:
    batch = tokenizer(line, return_tensors="pt")
    print('\n\nAssistant:' + tokenizer.decode(model.generate(batch["input_ids"].cuda(
    ), do_sample=True, top_k=50, max_length=100, top_p=0.95, temperature=1.0)[0]))
    print("\n------------------------------------------------\nHuman:")
    line = input().strip()

image

还是不理想

from pandallm.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.