baalajimaestro/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity
1712 commits 1 branch 0 tags 2.1 MiB
Commit graph

327 commits

Author SHA1 Message Date
Andrei Betlen
84615adbc6 Add split_mode option. Closes #1085 2024-01-15 12:49:20 -05:00
Phil H
76aafa6149
Implement GGUF metadata KV overrides (#1011) 
* Implement GGUF metadata overrides

* whitespace fix

* Fix kv overrides.

* Fix pointer and pickle

* Match llama.cpp kv_overrides cli argument

---------

Co-authored-by: Andrei <abetlen@gmail.com>
 2024-01-15 12:29:29 -05:00
Stephen Hankinson
df3be58d6c
Add ability to pass in penalize_nl param (#1068) 2024-01-10 02:46:27 -05:00
Andrei Betlen
d9a1d90fd7 Fix typo 2023-12-22 15:12:27 -05:00
swg
4b01a873ef
server: Support none defaulting to infinity for completions (#111) 
* Support defaulting to infinity or -1 for chat completions

* Check if completion_tokens is none in error handler.

* fix: max_tokens in create completion should match openai spec

* Fix __call__

---------

Co-authored-by: Andrei Betlen <abetlen@gmail.com>
 2023-12-22 14:05:13 -05:00
twaka
2f03fb0231
fix text_offset of multi-token characters (#1037) 
* fix text_offsets for bytes tokens

* fix
 2023-12-22 00:03:29 -05:00
Andrei Betlen
a05b4da80a fix: float32 is not JSON serializable when streaming logits. 2023-12-18 18:40:36 -05:00
Andrei Betlen
095c650006 Add offload_kqv option to llama and server 2023-12-18 15:36:09 -05:00
Andrei Betlen
472b344ae3 Remove unnused import 2023-12-18 15:32:40 -05:00
kddubey
6b2e0e05b4
perf: Don't convert logprobs arrays to lists (#1021) 2023-12-18 14:28:12 -05:00
Brandon Roberts
62944df142
Bugfix: Remove f16_kv, add offload_kqv field (#1019) 
F16_KV appears to have been removed here: af99c6fbfc

This addresses two issues:

 - #995 which just requests to add the KV cache offloading param
 - #1006 a NULL ptr exception when using the embeddings (introduced by
   leaving f16_kv in the fields struct)
 2023-12-18 14:27:11 -05:00
Daniele Morotti
f1c631dc53
Bug fixed with n_ctx=0 (#1015) 
If the n_ctx is set to 0 the code should use the maximum context length of the selected model, but it didn't work. There was a problem with the initialization of this parameter and a related problem with 'n_batch'.
 2023-12-16 18:59:50 -05:00
kddubey
5a8944672f
Fix logits_to_logprobs for 2-D and 3-D logits (#1002) 
* Fix logits_to_logprobs for 2-D and 3-D logits

* Set dtype to single

* Test size
 2023-12-16 18:59:26 -05:00
Tanner Hobson
ef22e478db
Replace logits_to_logprobs implementation with numpy equivalent to llama.cpp (#991) 
See #990. This change makes the logits_to_logprobs function equivalent to the version in the llama.cpp repository. It uses numpy so it's much faster than the previous version.
 2023-12-11 20:46:27 -05:00
Andrei Betlen
ec26f364cc Remove f16_kv 2023-12-11 10:25:37 -05:00
kddubey
b069d06346
Fix #891 (#952) 2023-11-29 05:39:52 -05:00
Andrei Betlen
6308f21d5e docs: Update Llama docs 2023-11-26 15:56:40 -05:00
Andrei Betlen
4026166e68 docs: Update completion and chat_completion parameter docstrings 2023-11-24 03:24:19 -05:00
Andrei Betlen
b6bb7ac76a docs: Add Llama class example 2023-11-22 23:10:04 -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
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
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
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
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
b30b9c338b Add JSON mode support. Closes #881 2023-11-08 00:07:16 -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
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
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
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
cebtenzzre
eefd76fe81
llama: fix exception in Llama.__del__ (#846) 2023-11-01 18:53:57 -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
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
ff580031d2 Update llama.cpp 2023-10-19 02:55:08 -04:00
Pierre Alexandre SCHEMBRI
10304d75fc
Make use of suppress_stdout_stderr when freeing model (#803) 2023-10-15 13:52:43 -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
d696251fbe Fix logits_all bug 2023-09-30 16:02:35 -04:00
Andrei Betlen
42bb721d64 Fix bug in embedding 2023-09-30 13:20:22 -04:00
Andrei
3bca7708fb
Configurable Chat Formats (#711) 
* Add configurable default chat completion format.

* Remove chat_template file to avoid circular import

* Update llama_types

* Add chat format
 2023-09-29 19:52:04 -04:00
Josh XT
a945404b4a
Fix rope scaling defaults (#767) 
* Fix rope scale with backwards compatibility

* Fix defaults

* Fix op

* Remove backwards compatibility

* Check single val
 2023-09-29 16:03:57 -04:00
Andrei Betlen
1a1c3dc418 Update llama.cpp 2023-09-28 22:42:03 -04:00
Andrei Betlen
38e34c97f0 Update llama.cpp 2023-09-18 16:11:27 -04:00
Andrei Betlen
f4090a0bb2 Add numa support, low level api users must now explicitly call llama_backend_init at the start of their programs. 2023-09-13 23:00:43 -04:00
Andrei Betlen
6a20293fc2 Reorder init params to match llama.cpp order 2023-09-13 21:20:26 -04:00
Andrei Betlen
c8f9b8a734 Explicitly make all init params other than model_path into keyword only params 2023-09-13 21:19:47 -04:00
Andrei Betlen
a68f9e2791 Add kwargs to init to catch extra params 2023-09-13 21:19:02 -04:00
Andrei Betlen
9e345a47a2 remove print 2023-09-13 21:12:27 -04:00
Andrei Betlen
517f9ed80b Convert missed llama.cpp constants into standard python types 2023-09-13 21:11:52 -04:00
Andrei Betlen
c4c440ba2d Fix tensor_split cli option 2023-09-13 20:00:42 -04:00
Andrei Betlen
1910793f56 Merge branch 'main' into v0.2-wip 2023-09-12 16:43:32 -04:00
Andrei Betlen
3f76e1de52 cjk pr minor cleanup 2023-08-29 07:21:59 -04:00
Andrei
bae44ec8bf
Merge pull request #309 from MeouSker77/fix-CJK 
Fix CJK and emoji stream output
 2023-08-29 06:58:10 -04:00
Andrei Betlen
4887973c22 Update llama.cpp 2023-08-27 12:59:20 -04:00
Andrei Betlen
3a29d65f45 Update llama.cpp 2023-08-26 23:36:24 -04:00
Andrei Betlen
ac47d55577 Merge branch 'main' into v0.2-wip 2023-08-25 15:45:22 -04:00
Andrei Betlen
48cf43b427 Use _with_model variants for tokenization 2023-08-25 13:43:16 -04:00
Andrei Betlen
8ac59465b9 Strip leading space when de-tokenizing. 2023-08-25 04:56:48 -04:00
Andrei Betlen
4ed632c4b3 Remove deprecated params 2023-08-24 01:01:05 -04:00
Andrei Betlen
cf405f6764 Merge branch 'main' into v0.2-wip 2023-08-24 00:30:51 -04:00
Andrei Betlen
bbbf0f4fc4 Update llama.cpp 2023-08-24 00:17:00 -04:00
Andrei Betlen
620cd2fd69 Merge branch 'main' of github.com:abetlen/llama_cpp_python into main 2023-08-14 22:41:47 -04:00
Andrei Betlen
5788f1f2b2 Remove unnused import 2023-08-14 22:41:37 -04:00
Billy Cao
c471871d0b
make n_gpu_layers=-1 offload all layers 2023-08-13 11:21:28 +08:00
Billy Cao
d018c7b01d
Add doc string for n_gpu_layers argument 2023-08-12 18:41:47 +08:00
MeouSker77
88184ed217 fix CJK output again 2023-08-09 22:04:35 +08:00
Andrei Betlen
66fb0345e8 Move grammar to function call argument 2023-08-08 15:08:54 -04:00
Andrei Betlen
1e844d3238 fix 2023-08-08 15:07:28 -04:00
Andrei Betlen
843b7ccd90 Merge branch 'main' into c0sogi/main 2023-08-08 14:43:02 -04:00
Andrei Betlen
d015bdb4f8 Add mul_mat_q option 2023-08-08 14:35:06 -04:00
c0sogi
b07713cb9f reset grammar for every generation 2023-08-07 15:16:25 +09:00
c0sogi
418aa83b01 Added grammar based sampling 2023-08-07 02:21:37 +09:00
Andrei Betlen
ce57920e60 Suppress llama.cpp output when loading model. 2023-07-28 14:45:18 -04:00
Andrei Betlen
a9b9f0397c Format 2023-07-28 01:53:08 -04:00
Andrei Betlen
abc538fcd5 fix: annoying bug where attribute exceptions were droining out file not found exceptions 2023-07-28 01:43:00 -04:00
Shouyi Wang
426dbfe3f4 Change tensor_split from array to pointer 2023-07-25 18:29:59 +10:00
Andrei Betlen
343480364f Merge branch 'main' into v0.2-wip 2023-07-24 15:26:08 -04:00
Andrei Betlen
11dd2bf382 Add temporary rms_norm_eps parameter 2023-07-24 14:09:24 -04:00
Andrei Betlen
8cd64d4ac3 Add rms_eps_norm 2023-07-24 13:52:12 -04:00
bretello
0f09f10e8c
add support for llama2 70b 2023-07-24 19:38:24 +02:00
Andrei Betlen
0538ba1dab Merge branch 'main' into v0.2-wip 2023-07-20 19:06:26 -04:00
Andrei
365d9a4367
Merge pull request #481 from c0sogi/main 
Added `RouteErrorHandler` for server
 2023-07-20 17:41:42 -04:00
Carlos Tejada
0756a2d3fb Now the last token sent when stream=True 2023-07-19 22:47:14 -04:00
Andrei Betlen
b43917c144 Add functions parameters 2023-07-19 03:48:20 -04:00
Andrei Betlen
19ba9d3845 Use numpy arrays for logits_processors and stopping_criteria. Closes #491 2023-07-18 19:27:41 -04:00
c0sogi
1551ba10bd Added RouteErrorHandler for server 2023-07-16 14:57:39 +09:00
Andrei Betlen
8ab098e49d Re-order Llama class params 2023-07-15 15:35:08 -04:00
Andrei Betlen
f0797a6054 Merge branch main into custom_rope 2023-07-15 15:11:01 -04:00
randoentity
3f8f276f9f Add bindings for custom_rope 2023-07-10 17:37:46 +02:00