006861
e8b2e69393
EmoLLM V3.0: internlm2.5-chat-7B,multi_turn_dataset_2.json+全量微调 3 epoch, 双卡A100(max_length = int(32768/4)), + streamlit demo
2024-07-15 15:28:40 +08:00
Kevin Rose
0f29a835ad
Update internlm2_5_chat_7b_qlora_oasst1_e3.py
2024-07-09 21:18:21 +08:00
Kevin Rose
fc4210f11a
Create internlm2_5_chat_7b_qlora_oasst1_e3.py
2024-07-09 19:52:33 +08:00
HongCheng
a372fb5499
Merge branch 'dev' into main
2024-05-08 11:52:26 +09:00
aJupyter
c9791814cf
add Incremental Pre-training Guide
2024-05-07 23:11:37 +08:00
HongCheng
10e6973a82
Update llama3 web demo and tutorials
2024-05-04 13:25:51 +09:00
HongCheng
683c40df5e
Update README_llama3_8b_instruct_qlora_alpaca_e3_M.md
2024-04-29 16:06:30 +09:00
HongCheng
e94028f019
update new training config and Tutorial
2024-04-29 15:55:09 +09:00
HongCheng
ac18474b1d
Update llama3_8b_instruct_qlora_alpaca_e3_M_ruozhi_scM.py
2024-04-29 11:22:06 +09:00
HongCheng
ddf404ccf2
llama3 3.0 config
2024-04-29 11:20:15 +09:00
HongCheng
67588a95ec
更新git-lfs conda安装方法 ( #205 )
2024-04-21 11:18:52 +09:00
HongCheng
cbce44a99e
[Update] add LLAMA3 fine-tuning and doc
2024-04-20 22:35:10 +08:00
HongCheng
b8609cad1f
删除原始的llama3配置文件
2024-04-20 21:14:25 +09:00
HongCheng
1d9ee54555
自我认知数据集和处理代码
2024-04-20 21:04:00 +09:00
HongCheng
140217593c
更新数据集位置
2024-04-20 13:50:46 +09:00
HongCheng
08716bbb23
更新link
2024-04-20 13:48:51 +09:00
HongCheng
044bff515e
更新link
2024-04-20 13:47:31 +09:00
HongCheng
89dea4826a
更正示例数据集 multi_turn_dataset_2, 添加更多描述, 移动处理文件
2024-04-20 13:44:46 +09:00
HongCheng
302c7229a8
添加cli_Llama3.py参考链接
2024-04-20 13:28:58 +09:00
HongCheng
f58f6711ca
更新测试对话文件，添加执行截图
2024-04-20 04:53:42 +09:00
HongCheng
282fb3bf69
添加图片
2024-04-20 01:42:10 +09:00
HongCheng
74f07dd43c
update download and model.generate
2024-04-20 01:28:36 +09:00
HongCheng
151b3aebf9
update 添加中文回答prompt
2024-04-20 01:06:55 +09:00
HongCheng
6fa7c5398b
删除旧版本文件
2024-04-20 00:57:32 +09:00
HongCheng
51e6609248
快速llama3 qlora微调指南
2024-04-20 00:55:12 +09:00
HongCheng
d994a2c193
Update Lamma3_qlora_e10_M_1e4_32_64.py
2024-04-19 23:49:18 +09:00
HongCheng
7d570d2b79
upload llama3 qlora config files
2024-04-19 23:45:21 +09:00
ZhouXinAo
3366b8a8bf
Create internlm2_20b_chat_lora_alpaca_e3.py
...
20b模型的配置文件
2024-04-12 11:33:32 +08:00
HongCheng
2a9ef19c5b
InternLM2-Base-7B QLoRA微调模型 链接和测评结果更新
2024-04-10 10:11:39 +09:00
Bryce Wang
c682725d96
多轮对话母亲角色的微调的脚本
2024-04-03 16:53:36 -07:00
HongCheng
6958611e0b
Update requirements.txt
...
update mpi4py installation
2024-04-02 17:57:56 +09:00
HongCheng
5e3e2f44e7
update xtuner_config\README_internlm2_7b_base_qlora.md
...
add hyperparamters
update model release part
update environment building part
2024-03-24 13:31:32 +09:00
xzw
70a080c0a8
[DOC]README_scientist.md ( #132 )
2024-03-23 21:14:07 +08:00
zealot52099
17c18a3197
[DOC]README_scientist.md
2024-03-23 20:10:13 +08:00
xzw
aaacfb149b
加入微调README.md 以及相关文件 ( #130 )
2024-03-23 19:59:26 +08:00
zealot52099
063b4d8692
update
2024-03-23 19:39:43 +08:00
HongCheng
383789e869
Create README_internlm2_7b_base_qlora.md
...
InternLM2 7B Base QLoRA 微调指南
2024-03-23 19:52:52 +09:00
HongCheng
affd90b177
create upload_modelscope.py
2024-03-23 15:45:11 +09:00
HongCheng
0124001926
other 2 configs for base model
2024-03-23 15:26:46 +09:00
HongCheng
df81a99f53
add full finetune code from internlm2
2024-03-23 15:26:01 +09:00
HongCheng
252adc7eef
add base model qlora fintuning config file: internlm2_7b_base_qlora_e10_M_1e4_32_64.py
2024-03-23 15:25:37 +09:00
HongCheng
d42f378eaa
add internlm2_7b_base_qlora_e3.py and modify requirements.txt
2024-03-21 15:55:50 +09:00
王友昉
6e7bd5e5d4
GLM-6B ft
2024-03-19 18:03:26 +08:00
HongCheng
5174fcb68b
Update ChatGLM3-6b-ft_EN.md
2024-03-16 20:21:20 +09:00
HongCheng
72b6c4a000
Update ChatGLM3-6b-ft.md
2024-03-16 15:59:22 +09:00
aJupyter
4d8ae7d428
feat: add internlm2-chat-7b-config
2024-03-03 21:08:52 +08:00
HongCheng
a84732794b
solve conflict in readme files
2024-03-03 19:56:51 +09:00
HongCheng
6cd83b6b0e
README files translation
...
The English version README files of the following documents are created and translated.
1. demo/README.md
2. evaluate/README.md
3. xtuner_config/README.md
4. xtuner_config/images/README.md
5. xtuner_config/ChatGLM3-6b-ft.md
There are some format problem and language expression in the Chinese version, I also adapted them.
By the way, I modified the file name of `evaluate/General evaluation.md` and `evaluate/Professional evaluation.md` since they are shown in the `xtuner_config/README.md`
2024-03-03 19:24:55 +09:00
ZhouXinAo
c9008e4e37
Add files via upload
...
Update airen(tiangou) configuration.
2024-02-29 11:58:55 +08:00
aJupyter
c696e163cd
feat: Update Aiwei configuration.
2024-02-23 20:11:17 +08:00
