MOSS issues

训练代码中的eos_token_id设置疑问

老师还，感谢开源工作！有个问题， finetune_moss.py文件中第178行将tokenizer.eos_token_id重新设置的目的是什么，我没看懂后面的解释 ![image](https://user-images.githubusercontent.com/38311101/234801857-4ebc8eb4-34ee-46b3-b3fd-fa6c634299b8.png)

xdnjust

[moss-moon-003-sft-plugin-int4] 跑示例中的插件模型代码报错

9

示例代码 ``` >>> from transformers import AutoTokenizer, AutoModelForCausalLM, StoppingCriteriaList >>> from utils import StopWordsCriteria >>> tokenizer = AutoTokenizer.from_pretrained("fnlp/moss-moon-003-sft-plugin-int4", trust_remote_code=True) >>> stopping_criteria_list = StoppingCriteriaList([StopWordsCriteria(tokenizer.encode("", add_special_tokens=False))]) >>> model = AutoModelForCausalLM.from_pretrained("fnlp/moss-moon-003-sft-plugin-int4", trust_remote_code=True).half().cuda() >>>...

xf4fresh

出现问题 Setting `pad_token_id` to `eos_token_id`:106068 for open-end generation.

2

========实例配置======== 核数：16 内存：127 GB 磁盘：49% 9.7G/20G 显卡：NVIDIA A100-SXM4-80GB, 1 输出内容： The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please...

lin-cop

微调运行run.sh报错

12

按照步骤复制之后微调报错 ValueError: The port number of the rendezvous endpoint 'None:None' must be an integer between 0 and 65536. 请问是哪里出问题了吗？

Aris-z

NameError: name 'autotune' is not defined

5

按照官方的步骤和代码安装运行报错 ``` from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("../models/moss-moon-003-sft-int8", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("../models/moss-moon-003-sft-int8", trust_remote_code=True).half().cuda() meta_instruction = "You are an AI assistant whose name is MOSS.\n- MOSS is a conversational...

Lufffya

微调的finetune_moss.py之后可以支持plugin版本吗

4

dyc1998108

torch1.10.1，cuda11.3，推理时报错RuntimeError: CUDA error：no kernel image...是因为显存不够吗，3080显卡

1

python moss_cli_demo.py Fetching 17 files: 100%|██████████████████████████████████████████████████████████████████████████████████| 17/17 [00:00 0: RuntimeError: CUDA error: no kernel image is available for execution on the device CUDA kernel errors might be asynchronously reported at...

Ben2522662

本地化部署报错'NoneType' object has no attribute 'message_types_by_name'

root@wyhFire:/mnt/f/MOSS# python3 moss_cli_demo.py 2023-04-27 11:04:26.361098: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA...

wyhFire