-
Notifications
You must be signed in to change notification settings - Fork 769
Insights: datawhalechina/self-llm
Overview
Could not load contribution data
Please try again later
14 Pull requests merged by 7 people
-
Update 03-Yuan2.0-2B WebDemo部署.md
#200 merged
Jul 10, 2024 -
Update 03-Yuan2.0-M32 WebDemo部署.md
#201 merged
Jul 10, 2024 -
更正 transformers 拼写错误
#195 merged
Jul 8, 2024 -
Update 02-Yuan2.0-2B Langchain 接入.md
#192 merged
Jun 26, 2024 -
add Yuan2.0 & Yuan2.0-M32
#191 merged
Jun 26, 2024 -
update DeepSeek-Coder-V2-Lite-Instruct FastApi and Langchain
#183 merged
Jun 24, 2024 -
Update 01-GLM-4-9B-chat FastApi 部署调用.md
#182 merged
Jun 23, 2024 -
add DeepSeek-Coder-V2-Lite-Instruct WebDemo
#181 merged
Jun 23, 2024 -
更新modelscope下载方式
#168 merged
Jun 18, 2024 -
统一了全部四个教程都能跑通的requirements标准,修复了原先教程间的数处版本冲突
#160 merged
Jun 17, 2024 -
update 04-Index-1.9B-Chat Lora finetuning
#158 merged
Jun 16, 2024 -
upload 03-Index-1.9B-chat WebDemo部署.md and related images
#159 merged
Jun 16, 2024 -
Add 02-Index-1.9B-Chat 接入 LangChain
#156 merged
Jun 15, 2024 -
Add 01-Index-1.9B-chat FastApi 部署调用
#157 merged
Jun 15, 2024
1 Pull request opened by 1 person
-
add MiniCPM-2-V
#148 opened
Jun 11, 2024
7 Issues closed by 5 people
-
微调过glm4之后,open_api调用微调模型报错
#188 closed
Jun 26, 2024 -
使用阿里云部署glm-4-9b api报gpu内存不足
#169 closed
Jun 24, 2024 -
qwen2 lora微调报错:RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn
#172 closed
Jun 21, 2024 -
BUG:按照GLM-4示例不能启动API服务
#174 closed
Jun 18, 2024 -
使用最新的peft进行lora微调,保存的checkpoint已经是合并的参数了,所以不需要分别加载再合并的操作了。
#167 closed
Jun 18, 2024 -
可以出一版验证集的process-func吗(Qwen、llama模型的数据集格式)?
#151 closed
Jun 14, 2024 -
关于代码的组织问题
#150 closed
Jun 13, 2024
30 Issues opened by 28 people
-
请问能够加入deepspeed吗
#205 opened
Jul 10, 2024 -
qwen2微调后回复的文本出现大段复制的重复内容
#204 opened
Jul 10, 2024 -
采用多张显卡进行GLM-4微调时报错RuntimeError
#203 opened
Jul 10, 2024 -
请问Index-1.9B-Chat 有全参微调的教程吗
#202 opened
Jul 10, 2024 -
GLM-4-9B-chat微调部分运行至加载lora权重推理处报错value error
#199 opened
Jul 9, 2024 -
GLM-4-9B-chat微调过程中,加载Lora权重推理阶段报错ValueError: too many values to unpack (expected 2)
#198 opened
Jul 9, 2024 -
多GPU推理与训练
#197 opened
Jul 9, 2024 -
05-Qwen2-7B-Instruct Lora 微调报错
#196 opened
Jul 8, 2024 -
qwen2微调分类任务
#194 opened
Jul 1, 2024 -
GLM4推理速度
#193 opened
Jun 27, 2024 -
Lora微调反向传播loss.backward()报错
#189 opened
Jun 26, 2024 -
在自己服务器部署,fastapi返回Method Not Allowed错误!如何解决?
#187 opened
Jun 25, 2024 -
安装xtuner后,无法启用命令xtuner:bash: xtuner: command not found
#186 opened
Jun 25, 2024 -
GLM4接入langchain无法识别到RetrievalQA.from_chain_type下面的memory参数
#179 opened
Jun 21, 2024 -
index-1.9b-chat 接入langchain报错
#177 opened
Jun 20, 2024 -
05-Qwen2-7B-Instruct Lora 微调报错
#176 opened
Jun 20, 2024 -
GLM-4-9b-chat web版运行时报属性messges不存在
#173 opened
Jun 18, 2024 -
deepseek-llm-7b-chat微调报错
#171 opened
Jun 18, 2024 -
如何获取一个大模型的stop_token_ids
#170 opened
Jun 18, 2024 -
Index-1.9B-Chat webDemo部署报错问题
#166 opened
Jun 17, 2024 -
深圳市原子同学?
#165 opened
Jun 17, 2024 -
有考虑添加多模态大模型的内容吗?
#164 opened
Jun 17, 2024 -
llama3 langchain
#163 opened
Jun 17, 2024 -
04-GLM-4-9B-Chat vLLM 部署调用显存溢出问题
#162 opened
Jun 17, 2024 -
数据集如何构造?
#161 opened
Jun 17, 2024 -
WebDemo部署对话如何逐字逐句显示而不是一次性生成
#149 opened
Jun 12, 2024 -
华为昇腾服务器的部署方案
#147 opened
Jun 11, 2024
7 Unresolved conversations
Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.
-
04-Qwen-7B-Chat Lora 微调时报错
#119 commented on
Jun 13, 2024 • 0 new comments -
peft微调llama3 8b,从第10补开始loss一直都是0
#124 commented on
Jun 13, 2024 • 0 new comments -
DeepSeek-7B-chat-Lora微调训练时报错
#139 commented on
Jun 14, 2024 • 0 new comments -
微调出来会有不礼貌或攻击性的言语
#108 commented on
Jun 17, 2024 • 0 new comments -
使用 llama3 的 lora 微调报错:NotImplementedError: Cannot copy out of meta tensor; no data!
#115 commented on
Jun 17, 2024 • 0 new comments -
LlaMA3在英文或者中文上tokenizer是否需要加bos token?
#140 commented on
Jun 27, 2024 • 0 new comments -
在纯 CPU 上可以运行吗?比如苹果电脑没有 cuda?
#117 commented on
Jul 9, 2024 • 0 new comments