Commit graph

1461 commits

Author SHA1 Message Date
TK-Master
b8438f70b5
Added support for min_p (#921)
* Added support for min_p

My small contribution to this great project.

Ref: https://github.com/ggerganov/llama.cpp/pull/3841

Closes: https://github.com/abetlen/llama-cpp-python/issues/911

* Fix for negative temp (sample_softmax)
2023-11-20 23:21:33 -05:00
Andrei Betlen
63fe1370ed Update llama.cpp 2023-11-20 23:19:47 -05:00
Andrei Betlen
a34d480141 Fix #929 2023-11-20 22:50:59 -05:00
Andrei Betlen
2c2afa320f Update llama.cpp 2023-11-20 14:11:33 -05:00
zocainViken
6dde6bd09c
bug fixing (#925) 2023-11-20 12:31:52 -05:00
ZisisTsatsas
f3117c0cf6
fix: openblas_simple missing pkg-config to build (#920) 2023-11-20 12:31:02 -05:00
Andrei Betlen
55efc9e6b2 Update llama.cpp 2023-11-16 18:51:55 -05:00
Andrei Betlen
96a377648c Merge tag 'v0.2.18' into main 2023-11-14 15:32:15 -05:00
Andrei Betlen
ca30d898e9 Merge tag 'v0.2.17' into main 2023-11-14 15:32:12 -05:00
Andrei Betlen
3af167d8db Merge tag 'v0.2.16' into main 2023-11-14 15:32:08 -05:00
Andrei Betlen
cc0fe43849 Disable opencl test 2023-11-14 14:59:08 -05:00
Andrei Betlen
f2901d840e Bump version 2023-11-14 14:10:00 -05:00
Andrei Betlen
a14f46a720 Update llama.cpp 2023-11-14 14:08:52 -05:00
Andrei Betlen
020945049a Update llama.cpp 2023-11-13 22:20:19 -05:00
Andrei Betlen
01846a76b9 Bump version 2023-11-10 16:36:12 -05:00
Andrei Betlen
7e3e85b53d Update llama.cpp 2023-11-10 16:33:55 -05:00
Andrei Betlen
4388f33414 Set CUDA_ARCHITECTURES=OFF for windows 2023-11-10 16:32:36 -05:00
Andrei Betlen
74167bdfb2 Update Functions notebook 2023-11-10 13:02:30 -05:00
Andrei Betlen
85ead98a3e Update Functions notebook example 2023-11-10 12:49:14 -05:00
Andrei Betlen
b7e60b66f4 Bump version 2023-11-10 06:21:24 -05:00
Andrei Betlen
fb743f6c87 Update llama.cpp 2023-11-10 06:21:14 -05:00
Andrei Betlen
5f15a3d91c Disable wheel repair command 2023-11-10 06:05:42 -05:00
Andrei Betlen
e02d52df29 Try to clean before calling cibuildwheel 2023-11-10 06:01:58 -05:00
Andrei Betlen
ed5a9260f6 Force LD_LIBRARY_PATH 2023-11-10 05:54:23 -05:00
Andrei Betlen
2f070afd61 Don't install in editable mode for release 2023-11-10 05:45:44 -05:00
Andrei Betlen
e32ecb0516 Fix tests 2023-11-10 05:39:42 -05:00
Andrei Betlen
6f0b0b1b84 Fix sampling bug when logits_all=False 2023-11-10 05:15:41 -05:00
Andrei Betlen
d9b38e3e3a Potential bugfix for eval 2023-11-10 04:41:19 -05:00
Andrei Betlen
52350cc9d7 Merge branch 'main' of https://github.com/abetlen/llama-cpp-python into main 2023-11-10 04:24:51 -05:00
Andrei Betlen
b84d76a844 Fix: add default stop sequence to chatml chat format 2023-11-10 04:24:48 -05:00
Andrei Betlen
841f6167cc Add Code Completion section to docs 2023-11-10 04:06:14 -05:00
Andrei Betlen
1b376c62b7 Update functionary for new OpenAI API 2023-11-10 02:51:58 -05:00
Andrei Betlen
17da8fb446 Add missing tool_calls finish_reason 2023-11-10 02:51:06 -05:00
Andrei Betlen
770df34436 Add $ref and $defs support to json schema converter 2023-11-10 02:50:46 -05:00
Andrei Betlen
faeae181b1 Fix: json_schema_to_gbnf should take string dump of json schema as input 2023-11-10 02:50:17 -05:00
Andrei Betlen
e7962d2c73 Fix: default max_tokens matches openai api (16 for completion, max length for chat completion) 2023-11-10 02:49:27 -05:00
Andrei Betlen
82072802ea Add link to bakllava gguf model 2023-11-09 03:05:18 -05:00
Andrei Betlen
baeb7b34b3 Merge branch 'main' of github.com:abetlen/llama_cpp_python into main 2023-11-09 00:55:25 -05:00
Andrei Betlen
b62c449839 Bugfix: missing response_format for functionary and llava chat handlers 2023-11-09 00:55:23 -05:00
Kevin Jung
fb1f956a27
Fix server doc arguments (#892) 2023-11-08 23:53:00 -05:00
Andrei Betlen
80f4162bf4 Update llama.cpp 2023-11-08 11:18:15 -05:00
Andrei Betlen
fd41ed3a90 Add set_seed to Llama class 2023-11-08 11:09:41 -05:00
Andrei Betlen
ca4cb88351 Fix destructor NoneType is not callable error 2023-11-08 11:05:45 -05:00
Andrei Betlen
01cb3a0381 Bump version 2023-11-08 00:54:54 -05:00
Andrei Betlen
9ae9c86be0 Update server docs 2023-11-08 00:52:13 -05:00
Andrei Betlen
598780fde8 Update Multimodal notebook 2023-11-08 00:48:25 -05:00
Andrei Betlen
b30b9c338b Add JSON mode support. Closes #881 2023-11-08 00:07:16 -05:00
Andrei Betlen
4852a6a39c Fix built in GBNF grammar rules 2023-11-08 00:06:22 -05:00
Andrei Betlen
64f5153c35 Add seed parameter to chat handlers 2023-11-07 23:41:29 -05:00
Andrei Betlen
86aeb9f3a1 Add seed parameter support for completion and chat_completion requests. Closes #884 2023-11-07 23:37:28 -05:00