baalajimaestro/llama.cpp
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity
1276 commits 1 branch 0 tags 6 MiB
Commit graph

512 commits

Author SHA1 Message Date
Andrei Betlen 7f3704b896 Bump version 2023-11-27 19:14:25 -05:00
Andrei Betlen 396dbf0b2b docs: Improve low-level docstrings 2023-11-27 19:03:02 -05:00
Andrei Betlen a928893d03 Merge branch 'main' of github.com:abetlen/llama_cpp_python into main 2023-11-26 15:57:13 -05:00
Andrei Betlen 6308f21d5e docs: Update Llama docs 2023-11-26 15:56:40 -05:00
Gardner Bickford c2d63a7148
fix: Typo in the Open Orca chat format #874 (#947) 2023-11-26 15:39:18 -05:00
Andrei Betlen f03a38e62a Update llama.cpp 2023-11-26 15:38:22 -05:00
Andrei Betlen 1a7bf2037b docs: Update openapi endpoint names 2023-11-24 03:39:29 -05:00
Andrei Betlen 4026166e68 docs: Update completion and chat_completion parameter docstrings 2023-11-24 03:24:19 -05:00
Andrei Betlen 8c3aa7858b Merge branch 'main' of github.com:abetlen/llama_cpp_python into main 2023-11-24 00:15:36 -05:00
Andrei Betlen de2e2bc083 misc fix verbose printing in functionary model 2023-11-23 20:14:23 -05:00
Andrei Betlen 36048d46af Update llama.cpp 2023-11-23 16:26:00 -05:00
mrfakename d68fc07b1b
Add Zephyr format (#937) 2023-11-23 01:20:08 -05:00
caiyesd 4184835078
Add chat format to support baichuan (#938) 
Signed-off-by: caiyesd <caiyesd@gmail.com>
 2023-11-23 01:19:50 -05:00
Andrei Betlen c647f01609 Add from_json_schema to LlamaGrammar 2023-11-23 00:27:00 -05:00
Andrei Betlen be1f64d569 docs: Add docstrings from llama.cpp 2023-11-23 00:26:26 -05:00
Andrei Betlen b6bb7ac76a docs: Add Llama class example 2023-11-22 23:10:04 -05:00
caiyesd b8f29f4bf0
Add baichuan-2 chat format (#936) 
Signed-off-by: caiyesd <caiyesd@gmail.com>
 2023-11-22 06:08:06 -05:00
Andrei Betlen 8b6ca22846 Fix type warnings for json schema grammar converter 2023-11-21 13:32:00 -05:00
Andrei Betlen 230fc8b535 Bump version 2023-11-21 05:04:55 -05:00
Andrei Betlen 128dc4731f Fix #569 2023-11-21 04:39:05 -05:00
Andrei Betlen 7a3f87846b Format 2023-11-21 04:02:20 -05:00
Andrei Betlen 422ebc89ce Fix: Add logit_bias to all completion api methods 2023-11-21 04:01:36 -05:00
Andrei Betlen 07e47f55ba Add support for logit_bias outside of server api. Closes #827 2023-11-21 03:59:46 -05:00
Maarten ter Huurne c21edb6908
Do not set grammar to None for new LlamaGrammar objects (#834) 
* Do not set `grammar` to `None` for new `LlamaGrammar` objects

The `grammar` attribute is written by `init()`, but that method always
returns `None`, so `__init__()` would then discard the previously
written object.

* Add minimal test for grammar parsing
 2023-11-21 00:23:18 -05:00
mrfakename ef65fc5ff4
Add MistralLite, Intel, and OpenChat prompt formats (#927) 
* Add MistralLite format

* Update llama_chat_format.py

* Update llama_chat_format.py
 2023-11-21 00:19:25 -05:00
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 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
Andrei Betlen f2901d840e Bump version 2023-11-14 14:10:00 -05:00
Andrei Betlen 01846a76b9 Bump version 2023-11-10 16:36:12 -05:00
Andrei Betlen b7e60b66f4 Bump version 2023-11-10 06:21:24 -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 b84d76a844 Fix: add default stop sequence to chatml chat format 2023-11-10 04:24:48 -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 b62c449839 Bugfix: missing response_format for functionary and llava chat handlers 2023-11-09 00:55:23 -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 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
Damian Stewart aab74f0b2b
Multimodal Support (Llava 1.5) (#821) 
* llava v1.5 integration

* Point llama.cpp to fork

* Add llava shared library target

* Fix type

* Update llama.cpp

* Add llava api

* Revert changes to llama and llama_cpp

* Update llava example

* Add types for new gpt-4-vision-preview api

* Fix typo

* Update llama.cpp

* Update llama_types to match OpenAI v1 API

* Update ChatCompletionFunction type

* Reorder request parameters

* More API type fixes

* Even More Type Updates

* Add parameter for custom chat_handler to Llama class

* Fix circular import

* Convert to absolute imports

* Fix

* Fix pydantic Jsontype bug

* Accept list of prompt tokens in create_completion

* Add llava1.5 chat handler

* Add Multimodal notebook

* Clean up examples

* Add server docs

---------

Co-authored-by: Andrei Betlen <abetlen@gmail.com>
 2023-11-07 22:48:51 -05:00
Andrei Betlen 56171cf7bf Bump version 2023-11-06 09:37:55 -05:00
Andrei Betlen be0add1b2d Fix type bug 2023-11-06 09:30:38 -05:00