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
7.04k
stars
581
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Mac M2 pro在部署仿openai api的web demo卡死
#382
guankai
closed
9 months ago
5
在mac的M2pro上运行chinese-alpaca-2-13b-16k-hf报错
#381
guankai
closed
10 months ago
2
推理载入后出现以下错误,输入数个汉字后,出现该问题。
#380
q5756578
closed
9 months ago
4
使用模型进行摘要出现问题
#379
1042312930
closed
10 months ago
3
alpaca2-7b模型推理阶段报错:OSError: [Errno 9] Bad file descriptor
#378
promisecc
closed
9 months ago
2
请问是不能用LLaMA-2-chat版本执行Lora微调嘛?
#377
changyuying
closed
9 months ago
2
多机训练会报 CUDA error: an illegal memory access was encountered
#376
440981
closed
9 months ago
7
chinese-alpaca-2-13b-16k 长文本训练过程咨询
#375
zx4321
closed
9 months ago
2
部署chinese-alpaca-2-7b-hf提示“ If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True”
#374
minmie
closed
10 months ago
8
整个训练过程中'eval_loss'都是nan,但是training_loss正常,一直在下降
#370
litsh
closed
8 months ago
11
Update links for 1.3B models
#368
ymcui
closed
10 months ago
0
Add flash attention support for inference
#367
GoGoJoestar
closed
10 months ago
1
加载数据集时卡住,是什么原因
#365
clclclaiggg
closed
10 months ago
10
多次進行微調
#364
Naozumi520
closed
10 months ago
2
llama-7b模型参数有问题,下载时报错,微调时不拟合
#361
Fuyubai
closed
9 months ago
3
词表扩充后的模型合并
#360
lyq080700
closed
9 months ago
5
tokenizer training
#358
StephennFernandes
closed
10 months ago
2
为什么我用fastchat框架部署然后请求得到的回复,会有类似“### Instruction”,“### Response”的文本呢
#357
pen-ho
closed
10 months ago
2
请教一下Chinese-Alpaca-2继续训练lora的问题
#356
Agreewithu
closed
10 months ago
2
部署16k完整模型失败 chinese-alpaca-2-13b-16k-hf
#355
qianxifu
closed
10 months ago
3
Update README.md
#354
reterVision
closed
10 months ago
1
请问支持全参微调吗?
#353
CHAOJICHENG5
closed
10 months ago
2
合并 chinese-alpaca-2-lora-7b 模型后,存在推理无法正常显示的问题
#352
tanghui315
closed
10 months ago
8
对Chinese-Alpaca-2(7B)进行指令精调后,合并模型并量化运行,回答均为空白
#351
Kong-Chang
closed
9 months ago
4
16K模型經過fine-tune後還會是16K的token len嗎?
#350
ian08005454
closed
10 months ago
0
华为手机,termux 上make后,生成的chat.sh文件,不在scripts/llama-cpp目录下
#345
ewwerpm
closed
10 months ago
2
v100显卡, 开启vllm与不开启, 相同prompt下, 结果不一致
#344
neal668
closed
10 months ago
5
项目中的微调方法已经是适配的qlora方法了吗
#342
lower01
closed
10 months ago
3
windows10, cmake 编译报错
#341
ewwerpm
closed
10 months ago
5
请问新词表(大小:55296)的chises_sp.model在哪里获取呢?
#340
xiaobai52HZ
closed
10 months ago
2
关于数据集的随机性
#336
nuoma
closed
11 months ago
2
求助meta-llama/Llama-2-7b-hf模型,由于**的原因申请不到。有资源的麻烦可以提供下吗,谢谢?
#335
cwqJim2023
closed
10 months ago
3
如何并发 同时处理多个用户的会话
#334
zhuyetuo
closed
10 months ago
3
运行指令精调脚本报错,位置build_dataset.py
#333
Kong-Chang
closed
11 months ago
3
中文对话问题
#332
hsinlung
closed
10 months ago
2
使用llama.cpp 在win11电脑上运行量化后的模型中文问答出现乱码
#331
FWorldCodeZ
closed
10 months ago
4
Fix bugs in speculative sampling
#330
GoGoJoestar
closed
11 months ago
0
Add Speculative sampling support
#328
airaria
closed
10 months ago
0
项目中的推理程序可以直接应用于Codellama的推理吗
#327
lower01
closed
11 months ago
1
TypeError: xformers_forward() got an unexpected keyword argument 'padding_mask'
#326
xiaowuzicode
closed
10 months ago
5
多个.bin怎么合并?或者指定model的名字路径应该是什么?
#325
fgyang
closed
10 months ago
18
Add speculative sampling support
#324
GoGoJoestar
closed
11 months ago
1
Question: Do I have to use Flash-Attention all the way from pretrain and finetune and inference ? And if so can I quantize with AutoGPTQ after all ?
#323
thusinh1969
closed
11 months ago
1
对预训练的一些疑惑
#322
Zheng-Jay
closed
10 months ago
2
使用 text generation web ui 部署 chinese-alpaca-2-7b-16k-hf 模型,AI 回复乱码
#321
librame
closed
10 months ago
5
项目中的推理部署工具能否直接支持原版llama2相关模型的推理
#320
lower01
closed
11 months ago
1
预训练的输入数据量级和实际训练量级会相差很大?
#319
zhangjiawei5911
closed
11 months ago
3
增加数据进行模型微调训练正确逻辑流程
#318
lower01
closed
11 months ago
2
使用llama.cpp的时候,V100显卡的 提词速度还不如mac pro的M1为什么,是哪里设置问题吗?
#315
Ouyang-Wenbin
closed
11 months ago
4
训练完成打印日志的训练时间与实际的训练时间不一致
#314
jiejie1993
closed
10 months ago
2
Previous
Next