github
/
InternLM
mirror of https://github.com/InternLM/InternLM
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
208 Commits
4 Branches
8 Tags
11 MiB
Commit Graph

208 Commits (8194c348c1e9667e1cf9191750d56afdcf6c56d9)

Author SHA1 Message Date
zhulinJulia24 8194c348c1
[CI] add transformers version converage (#674) 2024-01-30 23:07:31 +08:00
RangiLyu 3599ddd0e4
[doc]: update requirements (#667) 
Co-authored-by: Wenwei Zhang <40779233+ZwwWayne@users.noreply.github.com>
 2024-01-26 21:23:15 +08:00
Yuzhe Gu 78bcb07f0e
[CI]: fix and pass pre-commit hook (#666) 2024-01-26 17:26:04 +08:00
del-zhenwu 1cb9870cb3
[doc] Add the requirement for the transformers library version in usage section (#658) 2024-01-25 20:03:56 +08:00
kkscilife c1ecc0d3d5
test(workflow): add basic model test (#650) 
Co-authored-by: kkscilife <wangmengke@pjlab.org.cn>
 2024-01-24 20:50:39 +08:00
LYMDLUT f395c4b5d1
[Doc] Add bitsandbytes to Readme,and support usage on low-resource devices. (#636) 2024-01-24 16:06:45 +08:00
yinghy18 fe41bbc058
[Doc]: Add InternLM-Math (#652) 2024-01-23 20:18:05 +08:00
Yang Gao 0ad595b0a2
[Docs]: Update origin ckpts link info in README (#651) 2024-01-23 20:16:40 +08:00
liukuikun abbf036e5b
[Enchance] update chat format (#634) 2024-01-19 20:02:48 +08:00
Yang Gao 4281caf30b
[Tool]: Support converting InternLM2 to Llama format (#627) 
Co-authored-by: x54-729 <whxiaohao@163.com>
 2024-01-19 19:47:28 +08:00
zhengjie.xu 5d9ef216d8
[Fix Bugs] Update web_demo.py (#637) 2024-01-19 19:31:06 +08:00
Songyang Zhang e7d8f1d3ac
[Fix] Link error (#640) 2024-01-19 18:08:02 +08:00
Kai Chen b00e875ed5
Add a figure to show the relation of different models (#638) 2024-01-19 16:33:18 +08:00
Kai Chen 4fd9391594
Fix invalid urls of InternEvo (#635) 2024-01-19 14:12:21 +08:00
BigDong 56939d7589
[Update] Update PAL Inference (#625) 
Co-authored-by: BIGWangYuDong <yudongwang1226@gmain.com>
 2024-01-19 11:33:56 +08:00
del-zhenwu 28e8e54e62
[CI] Delete .owners.yml (#633) 2024-01-19 11:30:58 +08:00
Wenwei Zhang f08a18b9b7
[Fix]: Update web demo to be self-contained (#624) 2024-01-19 11:24:22 +08:00
del-zhenwu 519c7934c4
[CI]: Delete .github/workflows/demo_in_readme.yaml (#632) 2024-01-19 11:18:56 +08:00
Yang Gao 6e51133a4d
[Docs]: Update description in README for InternLM2 models (#622) 2024-01-18 20:37:34 +08:00
Wenwei Zhang 0cae239483
[Doc]: Update readme (#620) 2024-01-18 13:00:09 +08:00
Wenwei Zhang ee9a22f04a
[Doc] update chat format doc (#619) 2024-01-18 11:48:24 +08:00
LYMDLUT e408af7fb5
[Fix]: Update end token id in web_demo.py (#611) 2024-01-18 10:33:09 +08:00
liukuikun 39ffce9090
[Doc]: Update agent/README_zh-CN.md (#613) 2024-01-18 10:32:41 +08:00
del-zhenwu c449f14a6a
Update .owners.yml: disable auto assign (#616) 2024-01-18 10:27:36 +08:00
fly2tomato 112ed18575
[Doc]: update introduction of OpenAOE (#605) 2024-01-17 19:38:15 +08:00
BigDong 70478bfc61
[Docs] Update Agent docs (#590) 
Co-authored-by: BIGWangYuDong <yudongwang1226@gmain.com>
Co-authored-by: ZwwWayne <wayne.zw@outlook.com>
 2024-01-17 19:37:51 +08:00
Yang Gao 69db8d4574
[Doc]: Update model descriptions in README (#601) 2024-01-17 14:51:14 +08:00
Yang Gao 896bac06a6
[Doc]: Update README (#599) 2024-01-17 13:07:35 +08:00
Zhihao Lin 8c546c9eb9
[doc ]update xtuner docs (#593) 2024-01-17 12:43:26 +08:00
Kai Chen 3215e83cf3
Update README.md (#598) 2024-01-17 12:33:50 +08:00
Shuo Zhang 63aa7fe2fa
[Docs] add InternLM2 model cards (#596) 
* [Docs] update InternLM2 model cards

* [Docs] update model cards

* [Docs] update InternLM2 model cards
 2024-01-17 12:24:08 +08:00
liukuikun d163169143
[Docs] chat format (#595) 
* [Docs] chat format

* Update chat_format.md
 2024-01-17 12:22:09 +08:00
Songyang Zhang 3ebe24d92c
[Doc] Update Evaluation (#588) 
* [Doc] Update Evaluation

* Update performance

* Update performance

* Update README.md

* Update README_zh-CN.md

---------

Co-authored-by: Kai Chen <chenkaidev@gmail.com>
 2024-01-17 12:20:42 +08:00
Range King 13cd9d9b21
[Docs] Fix typos in README (#594) 2024-01-17 11:41:08 +08:00
Wenwei Zhang 468982bc76
[Doc]: Resolve comments in documentation (#587) 
* fix typos and try pass lint

* fix wrong path in CI

* fix wrong path in readme

* update lint doc

* update doc

* update doc
 2024-01-17 10:47:06 +08:00
Lyu Han c40b34798c
[Doc]: update deployment guide (#591) 2024-01-17 10:32:43 +08:00
fly2tomato 2ae6225891
[Doc]: add openaoe docs (#586) 
* add openaoe docs

add openaoe docs

* Update openaoe.md

* Update openaoe_zh_cn.md

* Update openaoe.md
 2024-01-17 10:25:28 +08:00
vansin 830944d061
Update README.md (#589) 2024-01-17 10:18:37 +08:00
Wenwei Zhang dbec726c62
Update main branch and docs (#585) 
* [Refactor]: refactor with pure documentations and examples

* update model information

* update model information

* Check-in lmdeploy user guide

* Update chat format doc

* update cn doc

* clean doc
 2024-01-17 09:46:11 +08:00
djsaber aaaf4d7b0e
fix(chat): fix stream_chat in modeling_internlm(hf) to avoid decode error (#560) 
* fixed the issue that the HF model spontaneously conducted multiple rounds of Q&A and stream_chat method generates garbled characters

Signed-off-by: daijun1 <daijun1@eccom.com.cn>

* Update modeling_internlm.py

fixed the issue that the HF model spontaneously conducted multiple rounds of Q&A and stream_chat method generates garbled characters

* Update modeling_internlm.py

Correct spelling mistakes: chche -> cache

---------

Signed-off-by: daijun1 <daijun1@eccom.com.cn>
Co-authored-by: daijun1 <daijun1@eccom.com.cn>
 2023-12-29 13:03:44 +08:00
x54-729 ac7509389b
fix(tools): set add_eos_token=True in tokenizer.py (#555) 2023-12-22 21:57:14 +08:00
Yining Li cb922d44e2
fix(readme): fix deprecated model path in code examples (#554) 2023-12-22 20:56:27 +08:00
Lyu Han fc1f05c265
[Doc] update deployment guide based on lmdeploy v0.1.0 (#551) 2023-12-21 11:06:19 +08:00
Yining Li 68d6abc64a
doc(readme): update 7b/20b chat model information (#537) 
* update chat model information in README

* modifications by pre-commit hook

* update 7b evaluation results

* fix readme
 2023-12-14 17:46:03 +08:00
Pryest 3028f07cb7
fix(readme): update README with original weight download link (#460) 
* update README with original weight download link.

* add extra info for original model weights.

* edit typo and polish
 2023-11-01 14:49:48 +08:00
vansin 2c6cfde332
fix(web_demo): remove <eoh> in user prompt (#440) 
delete <eoh>
 2023-10-27 22:44:30 +08:00
ytxiong 42e5f6f8a9
fix(optimizer):broadcast main (#452) 
* add broadcast synchronize

* add synchronize
 2023-10-26 17:54:48 +08:00
ytxiong f653e5af01
add broadcast synchronize (#451) 2023-10-26 17:38:51 +08:00
x54-729 7b1b892084
fix(tools): fix InternLMTokenizer to fit transformers==4.34.0 2023-10-23 18:35:30 +08:00
Shuo Zhang e611817442
fix(doc): add 20b releasing info to readme (#330) 
* fix(eval): StreamingDataset does not have an __len__ method.

* doc(readme): update readme

* update readme

* update readme

* update readme

* update readme

* update readme

* update readme
 2023-09-20 16:46:45 +08:00