baalajimaestro/llama.cpp
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity
1176 commits 1 branch 0 tags 6 MiB
Commit graph

474 commits

Author SHA1 Message Date
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
Andrei Betlen e214a58422 Refactor Llama class internals 2023-11-06 09:16:36 -05:00
Andrei Betlen bbffdaebaa Refactor autotokenizer format to reusable function 2023-11-06 09:07:27 -05:00
Joe 4ff8def4d0
#717: Add support for Huggingface Autotokenizer (#790) 
Co-authored-by: Andrei <abetlen@gmail.com>
 2023-11-05 18:06:36 -05:00
earonesty 3580e2c5df
Update llama_chat_format.py (#869) 
* Update llama_chat_format.py

properly formal llama2 with first-message prompt embedded

* Update llama_chat_format.py
 2023-11-05 17:00:13 -05:00
Andrei Betlen f0b30ef7dc Update llama.cpp 2023-11-05 16:57:10 -05:00
Andrei Betlen 2ec043af76 Clean up stdout / stderr suppression 2023-11-03 13:02:15 -04:00
Andrei Betlen 4ea7027c41 Rename internal only module utils to _utils 2023-11-03 12:55:55 -04:00
Andrei Betlen df9362eeea Update llama.cpp 2023-11-03 11:34:50 -04:00
Andrei 3af7b21ff1
Add functionary support (#784) 
* Add common grammars and json-schema-to-grammar utility function from llama.cpp

* Pass functions to format function

* Add basic functionary formatting

* Add LlamaChatHandler for more complex chat use cases

* Add function calling example notebook

* Add support for regular chat completions alongside function calling
 2023-11-03 02:12:14 -04:00
Andrei ab028cb878
Migrate inference to llama_batch and llama_decode api (#795) 
* Add low-level batching notebook

* fix: tokenization of special characters: (#850)

It should behave like llama.cpp, where most out of the box usages
treat special characters accordingly

* Update CHANGELOG

* Cleanup

* Fix runner label

* Update notebook

* Use llama_decode and batch api

* Support logits_all parameter

---------

Co-authored-by: Antoine Lizee <antoine.lizee@gmail.com>
 2023-11-02 20:13:57 -04:00
Andrei Betlen 8350de9a18 Bump version 2023-11-02 15:53:01 -04:00
Andrei Betlen 011b95d7f3 Fix name 'open' is not defined exception. Closes #860 2023-11-02 15:30:55 -04:00
Andrei Betlen fa83cc5f9c Update llama.cpp 
Fix build examples

Exclude examples directory

Revert cmake changes

Try actions/checkout@v4

Try to update submodules

Revert

Update llama.cpp

Fix build examples

Exclude examples directory

Revert cmake changes

Try actions/checkout@v4

Try to update submodules

Revert
 2023-11-02 14:28:15 -04:00
Antoine Lizee 4d4e0f11e2 fix: tokenization of special characters: (#850) 
It should behave like llama.cpp, where most out of the box usages
treat special characters accordingly
 2023-11-02 14:28:14 -04:00
Andrei Betlen 6b3aa7fc8f Bump version 2023-11-01 19:25:03 -04:00
Sujeendran Menon 7b136bb5b1
Fix for shared library not found and compile issues in Windows (#848) 
* fix windows library dll name issue

* Updated README.md Windows instructions

* Update llama_cpp.py to handle different windows dll file versions
 2023-11-01 18:55:57 -04:00
cebtenzzre eefd76fe81
llama: fix exception in Llama.__del__ (#846) 2023-11-01 18:53:57 -04:00
David Ponce 3fc9147218
Iterate over tokens that should be biased rather than the entire vocabulary. (#851) 2023-11-01 18:53:47 -04:00
Marko Tasic 9c8f4dca5f
fixed Llama._create_completion suffix check, it can be either None or str instance (#854) 2023-11-01 18:52:50 -04:00
Daniel Thuerck 5f8f369d1b
Pass-Through grammar parameter in web server. (#855) Closes #778 2023-11-01 18:51:12 -04:00
Adam Katora 25cb710281
Update llama_types.py (#849) 
Minor typo fix, funcion -> function
 2023-11-01 18:50:11 -04:00
Andrei Betlen d808fd436c Update llama.cpp 2023-10-31 21:29:35 -04:00
Andrei Betlen 53861c9e53 Update llama.cpp 2023-10-24 03:13:32 -04:00
gmcgoldr 09a8406c83
Fix streaming doesn't return finish reason (#798) 
When streaming the yield that contains the finish can be skipped. This change ensures that yield isn't skipped.
 2023-10-19 02:55:56 -04:00
Andrei Betlen 28c2b884e2 Merge branch 'main' of github.com:abetlen/llama_cpp_python into main 2023-10-19 02:55:31 -04:00
Andrei Betlen ff580031d2 Update llama.cpp 2023-10-19 02:55:08 -04:00
Xiaoyu Kevin Hu a315128d66
update value check for n_gpu_layers field (#826) 2023-10-18 18:25:25 -04:00
Pierre Alexandre SCHEMBRI 10304d75fc
Make use of suppress_stdout_stderr when freeing model (#803) 2023-10-15 13:52:43 -04:00
Ma, Guokai a1ac199980
Fix repeat greeting (#808) 
* fix repeated greeting

* remove seperator between role and message
 2023-10-15 13:52:21 -04:00
Eric Liu b50166500e
Add validation for tensor_split size exceeding LLAMA_MAX_DEVICES (#820) 
* Add validation for tensor_split size exceeding LLAMA_MAX_DEVICES

* reword
 2023-10-15 13:51:51 -04:00
Andrei Betlen d6a130a052 Print traceback on server error 2023-10-10 15:56:04 -04:00
Andrei Betlen 43dfe1e2ab Update llama.cpp 2023-10-05 16:07:49 -04:00
Andrei Betlen a7d17b8ac9 Update llama.cpp 2023-10-03 15:23:35 -04:00
Andrei Betlen 305482bd41 Add chatml chat format 2023-09-30 21:01:34 -04:00
Andrei Betlen 5ef5280ef9 Log server exceptions to stdout 2023-09-30 19:13:36 -04:00
Andrei Betlen fab4bccc35 Bump version 2023-09-30 16:04:46 -04:00
Andrei Betlen d696251fbe Fix logits_all bug 2023-09-30 16:02:35 -04:00
Andrei Betlen 6ee413d79e Bump version 2023-09-30 13:23:09 -04:00