issues
search
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
6.99k
stars
569
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
尝试ZeRO3报错：RuntimeError: shape '[-1, 0]' is invalid for input of size 4644864
#571
lyccyl1
opened
4 days ago
2
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
2 weeks ago
0
binascii.Error: Incorrect padding：How to solve it?
#569
Bleado
closed
1 week 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
1 month ago
6
请问reward模型怎么部署推理？
#567
slliao445
closed
1 month ago
3
训练数据和测试数据开源了么?
#566
chg0901
closed
3 weeks ago
6
模型预训练时的labels问题
#565
ybch14
closed
1 month ago
2
模型微调
#564
dongziyu1016
closed
1 month ago
2
HELP!!!!!!!!!!!!!!!!!!!!!!!
#562
xiaoToby
closed
2 months ago
1
使用transformer命令行进行交互时推理报错
#561
Cbphcr
closed
1 month ago
2
模型，做了屏蔽词管理么？
#560
RyanOvO
closed
2 months ago
1
预训练数据以及微调数据会开源吗？
#559
Chen-Song
closed
2 months ago
2
微调后的lora模块
#558
ymourenya
closed
2 months ago
9
权重合并后重新加载训练时出现错误
#556
Shajiu
closed
2 months ago
30
训练垂直领域大模型应该基于哪个版本？
#555
Zheng-Jay
closed
2 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
2 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
2 months ago
2
多卡训练卡在加载模型
#552
ymourenya
closed
2 months ago
7
无法从checkpoint恢复训练
#551
LuckyGlass
closed
2 months ago
3
指令精调
#550
dongziyu1016
closed
2 months ago
4
指令精调
#549
dongziyu1016
closed
2 months ago
2
预训练完成后模型的使用
#548
ymourenya
closed
2 months ago
4
6卡指令精调，报错oom
#547
afezeriaWrnbbmm
closed
2 months ago
4
finetune之后的模型使用
#546
xiaoToby
closed
2 months ago
3
'padding_value' (position 3) must be float, not NoneType
#545
liqinga
closed
2 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
2 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
3 months ago
7
词汇表扩充后出现错误？
#542
Shajiu
closed
3 months ago
1
How can I output generation scores(logits)?
#541
Sishxo
closed
3 months ago
2
The model's performance is poor when using the merged tokenizer.
#540
adam-mhd94
closed
2 months ago
5
扩充词表后对新添加token初始化的方式
#538
YoLo-MUC
closed
3 months ago
2
卡在加载数据集这一步
#537
dehaozhou
closed
3 months ago
5
运行模型时output norm.weight' notfound如何解决
#534
dyqc
closed
4 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
3 months ago
1
访问次数多了以后显存不释放
#532
godotg
closed
3 months ago
6
请教一个问题。如何才能喂饱多个GPU
#531
leonunix
closed
3 months ago
3
如何调整 Batch Size
#530
1099255210
closed
3 months ago
3
1.3B模型是如何训练的？
#529
makotov
closed
3 months ago
6
Knowledge updation
#527
ForestR
closed
4 months ago
1
运行时显存占用过大和没有获取json返回体
#525
xiaoToby
closed
3 months ago
17
请问本仓库能否基于YaRN进行sft？
#524
Zheng-Jay
closed
3 months ago
5
“基座模型”和“指令模型”该怎么使用？
#522
kgdxpr
closed
5 months ago
1
model will broken when i start pretraining
#521
Abolfazl-kr
closed
4 months ago
3
llama.cpp部署出现格式错误
#519
HelloEveryonehh
closed
5 months ago
3
load_in_8bit 推理耗时比fp16长
#516
haoxurt
closed
4 months ago
3
请教如何更换Tokenizer进行训练，Tokenizer大小不匹配问题
#514
wangzhengh
closed
4 months ago
6
llama.cpp: update GGUF models (with imatrix)
#510
ymcui
closed
5 months ago
0
报错import name 'insecure_hashlib' from 'huggingface_hub.utils'
#508
Go4miii
closed
5 months ago
0
关于强化学习
#506
wuhuanon
closed
4 months ago
3
YaRN support implementation
#505
iMountTai
closed
5 months ago
0
Next