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)
PythonApache-2.0
Issues
- 2
binascii.Error: Incorrect padding:How to solve it?
#569 opened by Bleado - 6
训练数据和测试数据开源了么?
#566 opened by chg0901 - 0
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 opened by Wuhaotiantiantian - 3
请问reward模型怎么部署推理?
#567 opened by slliao445 - 2
模型预训练时的labels问题
#565 opened by ybch14 - 2
模型微调
#564 opened by dongziyu1016 - 6
什么导致chinese-alpaca-2-7b推理存在大量重复生成情况 呢
#568 opened by fxb392 - 2
使用transformer命令行进行交互时推理报错
#561 opened by Cbphcr - 30
权重合并后重新加载训练时出现错误
#556 opened by Shajiu - 9
微调后的lora模块
#558 opened by ymourenya - 2
预训练数据以及微调数据会开源吗?
#559 opened by Chen-Song - 1
模型,做了屏蔽词管理么?
#560 opened by RyanOvO - 5
- 3
训练垂直领域大模型应该基于哪个版本?
#555 opened by Zheng-Jay - 7
多卡训练卡在加载模型
#552 opened by ymourenya - 1
HELP!!!!!!!!!!!!!!!!!!!!!!!
#562 opened by xiaoToby - 2
ImportError: /usr/local/lib/python3.10/dist-packages/transformer_engine_extensions.cpython-310-x86_64-linux-gnu.so: undefined symbol:
#553 opened by alf-wangzhi - 2
- 3
无法从checkpoint恢复训练
#551 opened by LuckyGlass - 4
指令精调
#550 opened by dongziyu1016 - 4
预训练完成后模型的使用
#548 opened by ymourenya - 2
指令精调
#549 opened by dongziyu1016 - 4
6卡指令精调,报错oom
#547 opened by afezeriaWrnbbmm - 3
finetune之后的模型使用
#546 opened by xiaoToby - 4
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 opened by ZhenHengDong - 3
- 7
词汇表扩充并且增量训练的具体流程和修改哪些部分?
#543 opened by Shajiu - 6
访问次数多了以后显存不释放
#532 opened by godotg - 3
请教一个问题。如何才能喂饱多个GPU
#531 opened by leonunix - 3
如何调整 Batch Size
#530 opened by 1099255210 - 5
卡在加载数据集这一步
#537 opened by dehaozhou - 2
How can I output generation scores(logits)?
#541 opened by Sishxo - 6
1.3B模型是如何训练的?
#529 opened by makotov - 17
运行时显存占用过大和没有获取json返回体
#525 opened by xiaoToby - 5
请问本仓库能否基于YaRN进行sft?
#524 opened by Zheng-Jay - 1
词汇表扩充后出现错误?
#542 opened by Shajiu - 1
- 2
扩充词表后对新添加token初始化的方式
#538 opened by YoLo-MUC - 3
model will broken when i start pretraining
#521 opened by Abolfazl-kr - 2
运行模型时output norm.weight' notfound如何解决
#534 opened by dyqc - 3
load_in_8bit 推理耗时比fp16长
#516 opened by haoxurt - 1
Knowledge updation
#527 opened by ForestR - 3
奖励模型如何进行推理
#503 opened by wuhuanon - 4
- 3
- 6
请教如何更换Tokenizer进行训练,Tokenizer大小不匹配问题
#514 opened by wangzhengh - 1
“基座模型”和“指令模型”该怎么使用?
#522 opened by kgdxpr - 3
llama.cpp部署出现格式错误
#519 opened by HelloEveryonehh - 2
使用flash attention会报错
#502 opened by Go4miii - 0