ymcui Chinese-LLaMA-Alpaca-2 issues

ymcui / Chinese-LLaMA-Alpaca-2

中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models)

Apache License 2.0

7.11k stars 574 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Update run_clm_sft_with_peft.py

#578 dshwei opened 1 month ago
1
Update run_clm_sft_with_peft.py

#577 dshwei closed 1 month ago
1
在使用PeftModel 和已经存在的training_args.peft_path进行继续训练的的模型权重冻结的问题

#576 dshwei opened 1 month ago
1
lm_datasets = lm_datasets.train_test_split(test_size = data_args.validation_split_percentage)

#575 dshwei closed 1 month ago
3
llama.cpp更新后的wiki使用

#574 Jianliang-Shen closed 3 months ago
2
为什么llama的回答特别地乱

#573 327635328 closed 3 months ago
4
chinese-llama-2-13b-hf可否直接用bf16继续预训练？

#572 NLP-Learning closed 4 months ago
4
尝试ZeRO3报错：RuntimeError: shape '[-1, 0]' is invalid for input of size 4644864

#571 lyccyl1 closed 4 months ago
4
单机多卡训练，加载数据集时卡住，大概是卡在training_args.main_process_first(desc="dataset map tokenization and grouping")，请问如何解决，谢谢

#570 Wuhaotiantiantian closed 5 months ago
2
binascii.Error: Incorrect padding：How to solve it?

#569 Bleado closed 5 months ago
2
什么导致chinese-alpaca-2-7b推理存在大量重复生成情况呢

#568 fxb392 closed 6 months ago
6
请问reward模型怎么部署推理？

#567 slliao445 closed 6 months ago
3
训练数据和测试数据开源了么?

#566 chg0901 closed 5 months ago
6
模型预训练时的labels问题

#565 ybch14 closed 6 months ago
2
模型微调

#564 dongziyu1016 closed 6 months ago
2
HELP!!!!!!!!!!!!!!!!!!!!!!!

#562 xiaoToby closed 7 months ago
1
使用transformer命令行进行交互时推理报错

#561 Cbphcr closed 6 months ago
2
模型，做了屏蔽词管理么？

#560 RyanOvO closed 7 months ago
1
预训练数据以及微调数据会开源吗？

#559 Chen-Song closed 6 months ago
2
微调后的lora模块

#558 ymourenya closed 6 months ago
9
权重合并后重新加载训练时出现错误

#556 Shajiu closed 6 months ago
30
训练垂直领域大模型应该基于哪个版本？

#555 Zheng-Jay closed 7 months ago
3
通过openai_server_demo/openai_api_server_vllm.py 运行，输出出现自问自答

#554 Chaoran-F closed 7 months ago
2
ImportError: /usr/local/lib/python3.10/dist-packages/transformer_engine_extensions.cpython-310-x86_64-linux-gnu.so: undefined symbol:

#553 alf-wangzhi closed 7 months ago
2
多卡训练卡在加载模型

#552 ymourenya closed 7 months ago
7
无法从checkpoint恢复训练

#551 LuckyGlass closed 7 months ago
3
指令精调

#550 dongziyu1016 closed 7 months ago
4
指令精调

#549 dongziyu1016 closed 7 months ago
2
预训练完成后模型的使用

#548 ymourenya closed 7 months ago
4
6卡指令精调，报错oom

#547 afezeriaWrnbbmm closed 7 months ago
4
finetune之后的模型使用

#546 xiaoToby closed 7 months ago
3
'padding_value' (position 3) must be float, not NoneType

#545 liqinga closed 7 months ago
3
在精调的时候，如何让模型在指定的GPU上运行，而不是只在cuda:0上

#544 ZhenHengDong closed 7 months ago
4
词汇表扩充并且增量训练的具体流程和修改哪些部分？

#543 Shajiu closed 7 months ago
7
词汇表扩充后出现错误？

#542 Shajiu closed 8 months ago
1
How can I output generation scores(logits)?

#541 Sishxo closed 7 months ago
2
The model's performance is poor when using the merged tokenizer.

#540 adam-mhd94 closed 7 months ago
5
扩充词表后对新添加token初始化的方式

#538 YoLo-MUC closed 8 months ago
2
卡在加载数据集这一步

#537 dehaozhou closed 7 months ago
5
运行模型时output norm.weight' notfound如何解决

#534 dyqc closed 8 months ago
2
ceval的zero-shot测评，原生的llama-2-7b比本仓库的中文llama-2-7b效果要好

#533 xiaoxunlong closed 8 months ago
1
访问次数多了以后显存不释放

#532 jaysunxiao closed 7 months ago
6
请教一个问题。如何才能喂饱多个GPU

#531 leonunix closed 7 months ago
3
如何调整 Batch Size

#530 1099255210 closed 7 months ago
3
1.3B模型是如何训练的？

#529 makotov closed 8 months ago
6
Knowledge updation

#527 ForestR closed 9 months ago
1
运行时显存占用过大和没有获取json返回体

#525 xiaoToby closed 8 months ago
17
请问本仓库能否基于YaRN进行sft？

#524 Zheng-Jay closed 8 months ago
5
“基座模型”和“指令模型”该怎么使用？

#522 kgdxpr closed 9 months ago
1
model will broken when i start pretraining

#521 Abolfazl-kr closed 8 months ago
3