0218e3131c
feat(tools): support origin internlm architecture in web_demo ( #478 )
...
* debug for web_demo_internlm
* support web_demo_internlm
* update readme.md
* update web_demo.py
* update InternLM/tools/load_internlm_model.py
* update apis/inference.py
* update apis/inference.py
* update tools/load_internlm_model
* del private info in load_internlm_model.py
* fix some info
* fix some info
---------
Co-authored-by: YWMditto <862779238@qq.com>
2023-11-09 20:01:55 +08:00
a38af602bc
feat(doc): add torch_dtype to examples in README ( #479 )
...
* add torch_dtype to README examples
* typo
2023-11-09 15:58:58 +08:00
42ad9cc786
fix(readme): fix model path in readme ( #474 )
2023-11-06 19:26:48 +08:00
b9c813a972
fix(tools): fix streaming_chat and update docs ( #467 )
...
* move hf model to tools/transformers/internlm_model
* fix stream_chat
* Add stream_chat example
* fix import
* Add __init__ to internlm_model
* Add hf link
* fix import of tools/tokenizer.py
* fix huggingface url in readme
2023-11-03 16:12:37 +08:00
8b65e2e3c4
fix(doc): fix huggingface url ( #392 )
2023-10-07 02:03:44 -05:00
5e5d160685
fix(readme): fix readme about 20B releasing ( #329 )
...
* fix(eval): StreamingDataset does not have an __len__ method.
* doc(readme): update readme
* update readme
* update readme
* update readme
* update readme
* update readme
2023-09-20 16:26:43 +08:00
2a09ebd5c1
doc(readme): update readme, add 20B releasing info ( #328 )
...
* fix(eval): StreamingDataset does not have an __len__ method.
* doc(readme): update readme
* update readme
2023-09-20 16:04:43 +08:00
2710fa7343
Merge develop to main ( #314 )
...
* feat: add unitest for model (#300 )
* feat: add unitest for model
* feat:add model test
* Merge main to develop (#309 )
* fix(chat): fix stream_chat to return generator (#123 )
* fix(configs/7B_sft.py): model dtype float16 to bfloat16 (#302 )
* fix(convert2hf.py): fix the rotary_emb.inv_freq KeyError (#299 )
---------
Co-authored-by: yingtongxiong <974106207@qq.com>
Co-authored-by: zhjunqin <zhjunqin@users.noreply.github.com>
Co-authored-by: jiangtann <39088437+jiangtann@users.noreply.github.com>
* docs(doc/code-docs): add figure for training docs (#307 )
* add training image for docs
* docs(doc/code-docs): add training img for en doc
* docs(doc/code-docs): fix en docs for initialize
* docs(doc/code-docs): update conf file for readthedocs
* docs(doc/code-docs): fix typos
* docs(doc/code-docs): fix typos for reathedocs
* docs(doc/code-docs): minor typo fix for reathedocs
* docs(doc/code-docs): fix readthedocs conf file
* docs(doc/code-docs): update training image
* docs(doc/code-docs): fix typos
* docs(doc/code-docs): update training image
* docs(doc/code-docs): move training image to section initialize
* docs(doc/code-docs): fix lint
* add badge about reathedocs status
* Merge main to develop (#312 )
* fix(chat): fix stream_chat to return generator (#123 )
* fix(configs/7B_sft.py): model dtype float16 to bfloat16 (#302 )
* fix(convert2hf.py): fix the rotary_emb.inv_freq KeyError (#299 )
* docs(doc/code-docs): update quickstart usage (#301 )
* docs(usage.md): update usage.md
* docs(doc/code-docs): update en usage
---------
Co-authored-by: huangting4201 <huangting3@sensetime.com>
* docs(doc/code-docs): update en usage
---------
Co-authored-by: yingtongxiong <974106207@qq.com>
Co-authored-by: zhjunqin <zhjunqin@users.noreply.github.com>
Co-authored-by: jiangtann <39088437+jiangtann@users.noreply.github.com>
Co-authored-by: huangting4201 <huangting3@sensetime.com>
* feat: more tgs (#310 )
* feat:more tgs
* feat:add more tgs
* feat:more tgs
* feat: add optimizer_unitest (#303 )
* feat: add optimizer_unitest
* feat: add optimizer test
* feat: add optimizer test
* feat:add optimizer test
* fianl change
* feat:add optimizer test
* feat:add optimizer test
* feat:add optimizer test
---------
Co-authored-by: jiaxingli <43110891+li126com@users.noreply.github.com>
Co-authored-by: yingtongxiong <974106207@qq.com>
Co-authored-by: zhjunqin <zhjunqin@users.noreply.github.com>
Co-authored-by: jiangtann <39088437+jiangtann@users.noreply.github.com>
Co-authored-by: Season <caizheng@pjlab.org.cn>
Co-authored-by: huangting4201 <huangting3@sensetime.com>
2023-09-15 19:12:38 +08:00
e1cefaef6b
fix huggingface link ( #219 )
2023-08-22 22:20:01 +08:00
716131e477
introduce how to deploy 4-bit quantized internlm model ( #207 )
2023-08-22 11:31:01 +08:00
075648cd70
update readme related to internlm-chat-7v-v1.1 ( #214 )
2023-08-22 08:08:44 +08:00
58108413bd
Update readme for news of InternLM-Chat-7B-v1.1 and Lagent ( #213 )
...
* update readme
* fix typo
2023-08-22 07:46:01 +08:00
fbe6ef1da5
[Doc] update deployment guide to keep consistency with lmdeploy ( #136 )
...
* update deployment guide
* fix error
2023-07-31 14:42:07 +08:00
2fee4220a6
Doc: add twitter link ( #141 )
2023-07-27 15:24:50 +08:00
e746754b6e
delete torch_dtype of README's example code ( #100 )
2023-07-17 23:19:19 +08:00
0c1060435d
Use tempfile for convert2hf.py ( #23 )
...
Fix https://github.com/InternLM/InternLM/issues/50
2023-07-17 21:08:10 +08:00
cb991b6865
use fp16 in instruction ( #80 )
2023-07-14 17:56:15 +08:00
be50c02949
[Docs]: add Japanese README ( #43 )
...
* Add Japanese README
* Update README-ja-JP.md
replace message
* Update README-ja-JP.md
2023-07-14 16:29:34 +08:00
28bc0ebebe
[Doc] Add wechat and discord link in readme ( #78 )
...
* Doc：add wechat and discord link
* Doc：update wechat and discord link
* Doc：update wechat and discord link
* Doc：update wechat and discord link
* Doc：update wechat and discord link
* Doc：update wechat and discord link
* Doc：update wechat and discord link
* Doc：update wechat and discord link
* Doc：update wechat and discord link
* Doc：update wechat and discord link
* Doc：update wechat and discord link
2023-07-14 16:19:10 +08:00
73de6622a9
fix(readme, requirements): fix typo at Chinese readme and select a lower version of transformers ( #73 )
...
* fix a typo in readme
* in order to find InternLMTokenizer, select a lower version of Transformers
---------
Co-authored-by: gouhchangjiang <gouhchangjiang@gmail.com>
2023-07-13 18:44:33 +08:00
c7287e2584
feat(readme): add huggingface url ( #52 )
...
Co-authored-by: wangguoteng.p <wangguoteng@sensetime.com>
2023-07-11 22:04:46 +08:00
c18bec9361
fix[performance]: fix the performance evaluation mistakes ( #40 )
...
* fix(no_pp_scheduler): drop out and label if not used
* Update train_performance.md
* Update readme with new tested data
* update some typos
* doc(performance): fix some typos
2023-07-08 20:42:34 +08:00
dfb2751f00
add commercial license application form ( #38 )
2023-07-08 10:37:11 +08:00
c690bf3779
[Doc]: fix citation blocks ( #32 )
2023-07-08 00:17:41 +08:00
2066b36693
add citation ( #30 )
2023-07-07 22:58:48 +08:00
912fc8f8aa
doc: update the training examples ( #27 )
...
* doc: update the training examples
* update README
* change all "++++" log
* Update pylint
* solve lint err
2023-07-07 15:54:09 +08:00
ed04c7edb0
Add 8k transformers link ( #14 )
...
* add links for 8k
* fix acknowledgement
2023-07-06 22:00:50 +08:00
a290085512
Update readme ( #9 )
...
* Update README.md
* Update README-zh-Hans.md
2023-07-06 17:06:48 +08:00
f01a2832b8
Update README-zh-Hans.md
2023-07-06 16:38:22 +08:00
24ca402081
Update README-zh-Hans.md
2023-07-06 16:20:59 +08:00
7e415e2933
build(*): add gitsubmodule and gitignore
2023-07-06 14:08:02 +08:00
e9cb4b8e02
Update README-zh-Hans.md img
2023-07-06 13:00:28 +08:00
fa7337b37b
initial commit
2023-07-06 12:55:23 +08:00
YWMditto