issues
search
Facico
/
Chinese-Vicuna
Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案,结构参考alpaca
https://github.com/Facico/Chinese-Vicuna
Apache License 2.0
4.14k
stars
422
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
关于中断训练继续训练。
#258
xxyNeepu
opened
6 months ago
16
可以更新一下requirements吗?
#257
estuday
opened
8 months ago
1
Add AWQ support.
#256
justairr
closed
10 months ago
0
如果更改數據集格式,要如何更改代碼
#255
alexaax
opened
11 months ago
0
官方colab安裝套件失效
#254
alexaax
opened
1 year ago
0
可以提供一下huggingface上的Chinese-Vicuna/llama7b_4bit_128g模型的config.json和tokenizer么?
#253
jasoncow007
opened
1 year ago
0
使用finetune.sh来指令微调llama-33b,出现ZeroDivisionError: integer division or modulo by zero错误
#252
BIUBIUBIU-JIAZHOU
closed
1 year ago
2
deepspeed跑模型相关问题
#250
sunpenglv
opened
1 year ago
0
从belle+guanaco数据集中抽取前5000条样本训练lora,效果不好
#249
huanghaifeng1234
opened
1 year ago
0
OSError: Not enough disk space. Needed: Unknown size (download: Unknown size, generated: Unknown size, post-processed: Unknown size)
#248
thugbobby
opened
1 year ago
0
运行generate脚本之后,在页面提问,很久没有产生回答,后台无报错
#247
mmmminyuhan
opened
1 year ago
2
这几个不同路径下的模型是否有区别?
#246
hdjghjb
opened
1 year ago
0
多卡训练 bash scripts/finetune.sh报错
#245
hdjghjb
opened
1 year ago
1
运行chat_7B.sh聊两句话out of memory
#244
hdjghjb
closed
1 year ago
0
请问llama7b_4bit_128g的input shape是多少呢
#243
KyrieZhang11
opened
1 year ago
1
请问多个lora模型怎么合并?
#242
Orangeices
opened
1 year ago
0
中文乱码
#241
NewEricWang
closed
1 year ago
5
多卡finetune_chat时报mat1 and mat2 shapes cannot be multiplied (1024x2 and 1x11008)
#240
18065013
opened
1 year ago
2
是因为梯度为0吗?
#239
X1a0X
opened
1 year ago
0
transformers和pydantic问题
#238
ww0o0
opened
1 year ago
1
有办法改成分类任务么,用LlamaForSequenceClassification模型类加载
#237
LeonhardtWang
opened
1 year ago
0
⁇ Below is an instruction that describes a task. Write a response
#236
vcbeaut
opened
1 year ago
0
用checkpoint-11600跑部分问题(目测10-20%的问题)有奇怪的无限循环
#235
Tongcheng
opened
1 year ago
1
运行bash scripts/generate.sh或者bash scripts/chat_7B.sh后一般多久就可以进行推理了
#234
Junglesl
closed
1 year ago
1
简单的问题,finetune_other_continue.sh中step = 样本量/(MICRO_BATCH_SIZE*GRADIENT_ACCUMULATION_STEPS)。多卡的时候,是不是应该得是 step = 样本量/batch/(MICRO_BATCH_SIZE*GRADIENT_ACCUMULATION_STEPS*gpu数量)数量呢?这边一直不是很理解
#233
niuhuluzhihao
closed
1 year ago
0
7B 模型单卡3090后处理非常耗时
#232
f18298335152h
opened
1 year ago
0
Traceback (most recent call last):RuntimeError: "addmm_impl_cpu_" not implemented for 'Half'
#231
alps008
opened
1 year ago
1
训练模型没有保存token信息
#230
apachemycat
opened
1 year ago
5
怎么区分user的问题是指令问题还是通用问题?
#229
suckseed5
opened
1 year ago
1
RuntimeError: mat1 and mat2 shapes cannot be multiplied (164x4096 and 1x8388608)
#228
adaaaaaa
opened
1 year ago
3
Not an issue but a question for going forwards
#227
thusinh1969
opened
1 year ago
1
支持不同词表大小的 llama模型训练 lora
#226
greatewei
closed
1 year ago
0
运行generate.py推理报错ValueError: We need an `offload_dir` to dispatch this model
#225
kakuibeyond
opened
1 year ago
3
llama-13b-hf做推理,CUDA out of memory. 问题
#224
Bingohong
opened
1 year ago
2
Generation问题
#223
Jiangchenglin521
closed
1 year ago
0
Infra问题
#222
Jiangchenglin521
closed
1 year ago
0
代码中关于EOS paddding的区别问题
#221
apachemycat
opened
1 year ago
1
scripts 中好像没有 直接从Chinese-Vicuna/Chinese-Vicuna-lora-7b-chatv1继续训练微调的版本
#220
svjack
opened
1 year ago
3
拉去最新分支之后,通过pip install安装好了bitsandbytes==0.37.2,但是通过finetune_other_continue执行的时候,报此模块没有__version__
#219
niuhuluzhihao
closed
1 year ago
5
finetune_deepspeed启动运行[ERROR] [launch.py:324:sigkill_handler]
#218
grantchenhuarong
opened
1 year ago
4
为什么我在 kaggle.com 上训练的 LoRA 模型效果比较不错,模型下载到本地进行推理效果却很差?
#217
jianghushinian
closed
1 year ago
2
target_modules 各参数是什么意思,如何选择参数进行针对性的微调?
#216
pan365wang
opened
1 year ago
2
官方 finetune colab 无法运行
#215
williamjqk
opened
1 year ago
1
我使用7B参数的上游模型 + 100万个问答数据集做微调,时间需要48天,如何能加快
#214
zjwlgr
opened
1 year ago
1
在实际应用中我如何将num_beams=4,但最终输出的时候可保证输出过程和结果是一致的
#213
zjwlgr
opened
1 year ago
1
可以使用原始文本微调吗
#212
gravitywp
opened
1 year ago
2
使用CPU运行13B的模型,有2个bin文件怎么选择呢
#211
hengxingtx
closed
1 year ago
1
推理报错:RuntimeError: expected scalar type Half but found Float
#210
zhouchangju
opened
1 year ago
2
现在哪个模型支持4060笔记本显卡下的推理或者训练吗?
#209
adaaaaaa
opened
1 year ago
1
运行chat_7B.sh报错
#208
hongshuo-wang
opened
1 year ago
0
Next