baalajimaestro/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity
654 commits 1 branch 0 tags 2.1 MiB
Commit graph

654 commits

This branch
This branch
All branches
Author SHA1 Message Date
Your Name
0b079a658c make git module accessible anonymously 2023-05-20 02:25:59 +01:00
Simon Chabot
e783f1c191 feat: make embedding support list of string as input 
makes the /v1/embedding route similar to OpenAI api.
 2023-05-20 01:23:32 +02:00
Andrei Betlen
01a010be52 Fix llama_cpp and Llama type signatures. Closes #221 2023-05-19 11:59:33 -04:00
Andrei Betlen
fb57b9470b Merge branch 'main' of github.com:abetlen/llama_cpp_python into main 2023-05-19 03:19:32 -04:00
Andrei Betlen
f82d85fbee Bump version 2023-05-19 03:19:27 -04:00
Andrei Betlen
c7788c85ab Add Guidance example 2023-05-19 03:16:58 -04:00
Andrei Betlen
a8cd169251 Bugfix: Stop sequences can be strings 2023-05-19 03:15:08 -04:00
Andrei Betlen
f0812c4d8c Add upgrade instructions to the README 2023-05-19 02:20:41 -04:00
Andrei Betlen
17d4271b04 Fix logprobs for completions and implement for streaming logprobs. 2023-05-19 02:20:27 -04:00
Andrei Betlen
a634a2453b Allow first logprob token to be null to match openai api 2023-05-19 02:04:57 -04:00
Andrei Betlen
dc39cc0fa4 Use server sent events function for streaming completion 2023-05-19 02:04:30 -04:00
Andrei
69f9d50090
Merge pull request #235 from Pipboyguy/main 
Decrement CUDA version and bump Ubuntu
 2023-05-18 13:42:04 -04:00
Andrei Betlen
f0ec6e615e Stream tokens instead of text chunks 2023-05-18 11:35:59 -04:00
Andrei Betlen
21d8f5fa9f Remove unnused union 2023-05-18 11:35:15 -04:00
Marcel Coetzee
6ece8a225a Set CUDA_VERSION as build ARG 
Signed-off-by: Marcel Coetzee <marcel@mooncoon.com>
 2023-05-18 16:59:42 +02:00
Marcel Coetzee
6c57d38552 Decrement CUDA version and bump Ubuntu 
Signed-off-by: Marcel Coetzee <marcel@mooncoon.com>
 2023-05-18 16:02:42 +02:00
Andrei Betlen
50e136252a Update llama.cpp 2023-05-17 16:14:12 -04:00
Andrei Betlen
db10e0078b Update docs 2023-05-17 16:14:01 -04:00
Andrei Betlen
61d58e7b35 Check for CUDA_PATH before adding 2023-05-17 15:26:38 -04:00
Andrei Betlen
7c95895626 Merge branch 'main' of github.com:abetlen/llama_cpp_python into main 2023-05-17 15:19:32 -04:00
Andrei
47921a312c
Merge pull request #225 from aneeshjoy/main 
Fixed CUBLAS DLL load issues on Windows
 2023-05-17 15:17:37 -04:00
Aneesh Joy
e9794f91f2
Fixd CUBLAS dll load issue in Windows 2023-05-17 18:04:58 +01:00
Andrei Betlen
70695c430b Move docs link up 2023-05-17 11:40:12 -04:00
Andrei Betlen
4f342795e5 Update token checks 2023-05-17 03:35:13 -04:00
Andrei Betlen
626003c884 Merge branch 'main' of github.com:abetlen/llama_cpp_python into main 2023-05-17 02:00:48 -04:00
Andrei Betlen
f5c2f998ab Format 2023-05-17 02:00:39 -04:00
Andrei Betlen
d28b753ed2 Implement penalize_nl 2023-05-17 01:53:26 -04:00
Andrei Betlen
f11e2a781c Fix last_n_tokens_size 2023-05-17 01:42:51 -04:00
Andrei Betlen
7e55244540 Fix top_k value. Closes #220 2023-05-17 01:41:42 -04:00
Andrei Betlen
e37a808bc0 Update llama.cpp 2023-05-16 23:33:53 -04:00
Andrei Betlen
a7c9e38287 Update variable name 2023-05-16 18:07:25 -04:00
Andrei Betlen
a3352923c7 Add model_alias option to override model_path in completions. Closes #39 2023-05-16 17:22:00 -04:00
Andrei Betlen
214589e462 Update llama.cpp 2023-05-16 17:20:45 -04:00
Andrei Betlen
a65125c0bd Add sampling defaults for generate 2023-05-16 09:35:50 -04:00
Andrei Betlen
341c50b5b0 Fix CMakeLists.txt 2023-05-16 09:07:14 -04:00
Andrei
1a13d76c48
Merge pull request #215 from zxybazh/main 
Update README.md
 2023-05-15 17:57:58 -04:00
Xiyou Zhou
408dd14e5b
Update README.md 
Fix typo.
 2023-05-15 14:52:25 -07:00
Andrei
e0cca841bf
Merge pull request #214 from abetlen/dependabot/pip/mkdocs-material-9.1.12 
Bump mkdocs-material from 9.1.11 to 9.1.12
 2023-05-15 17:24:06 -04:00
dependabot[bot]
7526b3f6f9
Bump mkdocs-material from 9.1.11 to 9.1.12 
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 9.1.11 to 9.1.12.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/9.1.11...9.1.12)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:development
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
 2023-05-15 21:05:54 +00:00
Andrei
cda9cecd5f
Merge pull request #212 from mzbac/patch-1 
chore: add note for Mac m1 installation
 2023-05-15 16:19:00 -04:00
Andrei Betlen
cbac19bf24 Add winmode arg only on windows if python version supports it 2023-05-15 09:15:01 -04:00
Anchen
3718799b37
chore: add note for Mac m1 installation 2023-05-15 20:46:59 +10:00
Andrei Betlen
c804efe3f0 Fix obscure Wndows DLL issue. Closes #208 2023-05-14 22:08:11 -04:00
Andrei Betlen
ceec21f1e9 Update llama.cpp 2023-05-14 22:07:35 -04:00
Andrei Betlen
d90c9df326 Bump version 2023-05-14 00:04:49 -04:00
Andrei Betlen
cdf59768f5 Update llama.cpp 2023-05-14 00:04:22 -04:00
Andrei Betlen
7a536e86c2 Allow model to tokenize strings longer than context length and set add_bos. Closes #92 2023-05-12 14:28:22 -04:00
Andrei Betlen
8740ddc58e Only support generating one prompt at a time. 2023-05-12 07:21:46 -04:00
Andrei Betlen
8895b9002a Revert "llama_cpp server: prompt is a string". Closes #187 
This reverts commit b9098b0ef7.
 2023-05-12 07:16:57 -04:00
Andrei Betlen
684d7c8c17 Fix docker command 2023-05-11 22:12:35 -04:00