Commit Graph

1411 Commits

Author SHA1 Message Date
Xingchen Song(宋星辰)
02d2875def
llm : add bloom models (#3553)
* feat: Support bloom models

* fix(bloom): fix model size

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-10-10 17:48:21 +03:00
Jhen-Jie Hong
0aa6595ae0
swift : improvements and fixes (#3564)
* swift : use macOS 12 as minimum requirement

* swift : add missing ggml-backend.c source

* swift : add -O3 -DNDEBUG unsafe flags
2023-10-10 14:31:13 +03:00
Jan Ploski
f5f9121de1
llm : add MPT support (#3417)
* CUDA: added support for ggml_clamp (see also: https://github.com/ggerganov/ggml/issues/545)

* mpt : added an implementation based (mostly) on falcon integration, modified with deltas from ggml/examples/mpt

* mpt : protect against "clip_qkv": null in mpt-7b

* mpt : quick fix to avoid "Strange model" warning when quantizing MPT models

* mpt : addendum to changeset:84e30e8 - leave parameter clamp_kqv out from metadata rather than use 0.0 to indicate "no clamping" (more compliant with the current GGUF spec?)

* mpt : standardized all tensor names to follow GGUF spec

* mpt : addendum to changeset:1be89c40 - use "req" parameter of GGUF_GET_KEY macro instead of duplicate code

* mpt : fixed comment s/gptneox/mpt/

* mpt : remove tabs, trailing whitespace

* mpt : removed ne01 + n_past == ne00 assertion from alibi (cuda/f32) and rope_shift from build_mpt

* mpt : updated convert-mpt-hf-to-gguf.py to reflect changes made to convert-gptneox-hf-to-gguf.py in pr:3252

* comment out n_past instead of marking it unused

* mpt : removed hardcoded +178 from convert script in favor of utilizing hparams["vocab_size"]

* mpt : remove unused tokenizer_json in convert script

* ggml : remove obsolete n_past assert in ggml_alibi

* llama : print clam_kqv and max_alibi_bias hparams

---------

Co-authored-by: Cebtenzzre <cebtenzzre@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-10-10 10:50:23 +03:00
vvhg1
11ea5c7d96
infill. : fix tokenization (#3508)
* infill tokens correction

* serverinfill tokens correction

* removing any leading whitespace from infill suffix and removing leeading space token from suffix when params.escape

* removing any leading whitespace from infill suffix and removing leeading space token from suffix when params.escape

* only rm when params.escape, rm space if possible which is added back or rm added space token

* only rm when params.escape, rm space if possible which is added back or rm added space token

* Revert "only rm when params.escape, rm space if possible which is added back or rm added space token"

This reverts commit 63ba0b621f.

* fix interactive prompt escaping and fix server infill leading space handling

* rm unnecessary bool check
2023-10-10 10:31:21 +03:00
slaren
95bd60a0a6
ggml-alloc : fix assert in debug builds (#3555) 2023-10-09 15:44:58 +03:00
Georgi Gerganov
fcca0a7004
refact : fix convert script + zero out KV cache to avoid nans (#3523)
* refact : fix convert script + zero out KV cache to avoid nans

* ggml : silu(-inf) should never happen

* metal : assert various kernel requirements
2023-10-09 14:32:17 +03:00
Georgi Gerganov
dcc09d2596
metal : do not use mul_mm kernels when ne00 < 64 (#3542) 2023-10-09 14:28:27 +03:00
Georgi Gerganov
db3abcc114
sync : ggml (ggml-backend) (#3548)
* sync : ggml (ggml-backend)

ggml-ci

* zig : add ggml-backend to the build
2023-10-08 20:19:14 +03:00
Matheus C. França
eee42c670e
ci : add Zig CI/CD and fix build (#2996)
* zig CI/CD and fix build

Signed-off-by: Matheus Catarino França <matheus-catarino@hotmail.com>

* fix build_compiler

* ci : remove trailing whitespace

---------

Signed-off-by: Matheus Catarino França <matheus-catarino@hotmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-10-08 16:59:20 +03:00
Ryder Wishart
8e6716a102
api_like_OAI.py : compat with Microsoft Guidance (#2746)
Check for None in addition to empty string check in all request params

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-10-08 13:55:58 +03:00
arcrank
9c38d181d4
api_like_OAI.py : simplify function (#2796)
Simplify function
2023-10-08 13:52:57 +03:00
Johannes Rudolph
a1202a31ed
k-quants : fix comments about block sizing (#3499) 2023-10-08 13:21:19 +03:00
Georgi Gerganov
94e502dfb7
ci : enable on obj-c changes + fix metal build (#3540) 2023-10-08 11:24:50 +03:00
Luo Tian
7d8b24932f
zig : fix build by introducing train.cpp (#3539) 2023-10-08 11:24:01 +03:00
Georgi Gerganov
b0ec5218c3
metal : support MTLGPUFamily < Apple7, formatting, style (#3524)
* metal : improve decoding speed for batches of 2-16

* metal : rename kernels mul_mat_ to mul_mv_

* metal : indentations

* minor

* metal : print more GPU info + disable mul_mm for MTLGPUFamiliy < Apple7
2023-10-08 10:01:53 +03:00
Kerfuffle
63d3b06a43
llama : fix missing break in Persimmon arch case statements (#3535) 2023-10-08 08:22:17 +03:00
Kerfuffle
a16e89cec8
Fix trying to strip newline from empty prompt and cfg prompt file content (#3534) 2023-10-07 15:31:41 -06:00
M. Yusuf Sarıgöz
4d03833211
gguf.py : fix CI for publishing GGUF package (#3532)
* Fix CI for publishing GGUF package

* Bump version

* fix

* bump version

* bump version

* bump version
2023-10-07 22:14:10 +03:00
Tom C
c47066d833
py : change version of numpy requirement to 1.24.4 (#3515)
Co-authored-by: Lyjia <me@lyjia.us>
2023-10-07 12:56:15 +03:00
cebtenzzre
f1782c68de
quantize : fail fast on write errors (#3521) 2023-10-07 11:41:52 +03:00
Jhen-Jie Hong
c26765a0a1
metal : support default.metallib load & reuse code for swift package (#3522)
* metal : support load default.metallib & reuse code for swift package

* metal : use SWIFT_PACKAGE def instead of define GGML_SWIFT
2023-10-07 11:40:27 +03:00
Phillip Kravtsov
0e797c2fc5
llm : support Adept Persimmon 8B (#3410)
* Produces garbage output

* wip: correct tensors up to RoPE

* correct tensors thru RoPE

* Correct outputs through masked & softmax'd KQ

* fp32 works

* Rename adept->persimmon

* Produces correct outputs

* clean up convert scripts

* remove printing logic from ggml.c

* remove prints from llama.cpp & fix merge

* trivial cleanups

* Add offload funcs

* update conversion script to directly take adept artifacts rather than .saftensors file

* Fix norm eps bug

* Support sqr and concat on metal, persimmon-8b-q4 runs correctly

* Small changes from review

* Formatting changes

* Minor changes to conversion script

* Remove old script

* Fix editorconfig formatting

* Fix build

* add overlooked offload code ggml-ci
2023-10-07 10:12:43 +03:00
goerch
3a716b4dae
Fix for #3454 (#3455)
Fix: `sentencepiece` tokenizers with added tokens failed with an incorrect assertion
2023-10-07 06:57:01 +02:00
BarfingLemurs
1faaae8c2b
readme : update models, cuda + ppl instructions (#3510) 2023-10-06 22:13:36 +03:00
Mihai
cb13d73a72
server : docs fix default values and add n_probs (#3506) 2023-10-06 21:39:33 +03:00
Kerfuffle
9ca79d5cbb
kv cache slot search improvements (#3493)
* kv cache slot search improvements

* Use n_ctx in kv find slot for consistency

* Ensure kv cache head points to a valid slot in llama_decode internal

* Add some comments to prevent dumb people (like me) from getting confused.
2023-10-06 10:10:13 -06:00
Georgi Gerganov
0c731ca403
prompts : fix editorconfig checks after #3416 2023-10-06 16:36:32 +03:00
pudepiedj
a8777ad84e
parallel : add option to load external prompt file (#3416)
* Enable external file and add datestamp

* Add name of external file at end

* Upload ToK2024

* Delete ToK2024.txt

* Experiments with jeopardy

* Move ParallelQuestions to /proimpts and rename

* Interim commit

* Interim commit

* Final revision

* Remove trailing whitespace

* remove cmake_all.sh

* Remove cmake_all.sh

* Changed .gitignore

* Improved reporting and new question files.

* Corrected typo

* More LLM questions

* Update LLM-questions.txt

* Yet more LLM-questions

* Remove jeopardy results file

* Reinstate original jeopardy.sh

* Update examples/parallel/parallel.cpp

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-10-06 16:16:38 +03:00
Jhen-Jie Hong
97af49fa39
server : reuse llama_sample_token common util (#3494)
* server : reuse llama_sample_token common function

* common : use n_probs for temperature sampling
2023-10-06 15:44:24 +03:00
l3utterfly
16820a5a0d
llama : correct hparams comparison (#3446)
* fixed floating point comparison issues

* updated implementation for hparam comparison to handle inf and NaN

* fixed code review comments

* minor simplification

* rename is_float_eq -> is_float_close

---------

Co-authored-by: Cebtenzzre <cebtenzzre@gmail.com>
2023-10-06 13:47:59 +03:00
Jhen-Jie Hong
04b2f4386e
ci : fix xcodebuild destinations (#3491)
* ci : fix xcodebuild destinations

* ci : add .swift to paths
2023-10-06 13:36:43 +03:00
cebtenzzre
48edda30ee
convert : update Falcon script for new HF config (#3448)
Also adds Falcon-180B support.
Closes #3049

Co-authored-by: jb <jonathan.t.barnard@gmail.com>
2023-10-05 15:00:34 -04:00
Kenvix ⭐
45eba9369f
build : use std::make_tuple() for compatibility with older GCC versions (#3488) 2023-10-05 20:16:39 +03:00
staviq
acec9eaaa9
common : process escape sequences in reverse prompts (#3461) 2023-10-05 19:17:29 +03:00
shibe2
e2583cbc29 CLBlast: Fix handling of on-device tensor data
Fix uploading tensor data to device, including 3D, 4D, and non-contiguous tensors.
Use correct offsets into data that is already in VRAM.
Correct handling of OpenCL events when multiple commands are queued.
2023-10-05 18:25:23 +04:00
Jhen-Jie Hong
e8b8d32e86
server : fix incorrect num_tokens_predicted (#3480) 2023-10-05 17:02:55 +03:00
Jhen-Jie Hong
8f3a642ec1
swift : disable ACCELERATE_NEW_LAPACK (#3481) 2023-10-05 17:00:07 +03:00
Jhen-Jie Hong
0745384449
ci : add swift build via xcodebuild (#3482) 2023-10-05 16:56:21 +03:00
Kerfuffle
019ba1dcd0
convert : fix Baichuan2 models by using vocab size in config.json (#3299)
Use local GGUF package when possible in Baichuan converter
2023-10-04 17:20:28 +03:00
Georgi Gerganov
beabc8cfb0
readme : add project status link 2023-10-04 16:50:44 +03:00
Georgi Gerganov
0d152b37fe
ggml : fix build after #3329 2023-10-04 16:25:41 +03:00
ds5t5
f8c90cdbaa
llm : add Refact model (#3329)
* add refact model

* resolve comments

* rebase to the latest

* solve alibi cpu error

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-10-04 16:23:39 +03:00
Georgi Gerganov
f93af02488
sync : ggml (conv 1d + 2d updates, UB fixes) (#3468)
* sync : ggml (conv 1d + 2d updates)

ggml-ci

* ggml : fix UB in q5_0 and q5_1 quantize code

ggml.c:1033:39: runtime error: left shift of 1 by 31 places cannot be represented in type 'int'
SUMMARY: UndefinedBehaviorSanitizer: undefined-behavior

ggml.c:1081:39: runtime error: left shift of 1 by 31 places cannot be represented in type 'int'
SUMMARY: UndefinedBehaviorSanitizer: undefined-behavior

ggml-ci

* tests : fix UB in test-quantize-perf
2023-10-04 15:29:58 +03:00
Merrick Christensen
f72f8f22c9
finetune : readme fix typo (#3465)
Fix small typo
2023-10-04 09:33:13 +03:00
Tameem
79f34abddb
ggml : add RISC-V Vector Support for K-Quants and improved the existing intrinsics (#3453)
* Added RVV intrinsics support for Q8 quantize row and also improved the existing dot product function for risc-v.

The RVV intrinsics is added for the following quantize row functions
   quantize_row_q8_0
   quantize_row_q8_1

The following dot product functions have also been optimized by using LMUL = 1/2 instead of LMUL = 1
   ggml_vec_dot_q4_0_q8_0
   ggml_vec_dot_q4_1_q8_1
   ggml_vec_dot_q5_0_q8_0
   ggml_vec_dot_q5_1_q8_1

And vector initialization in Q5 by temporary array is also replaced by the vid intrinsics

Signed-off-by: Ahmad Tameem <ahmad.tameem@10xengineers.ai>

* Added RVV intrinsics support for k_quants

This adds RISC-V Vector intrinsics support for the following K_quants functions for both QKK = 256 and QKK = 64
   ggml_vec_dot_q2_K_q8_K
   ggml_vec_dot_q3_K_q8_K
   ggml_vec_dot_q4_K_q8_K
   ggml_vec_dot_q5_K_q8_K
   ggml_vec_dot_q6_K_q8_K

Signed-off-by: Ahmad Tameem <ahmad.tameem@10xengineers.ai>

---------

Signed-off-by: Ahmad Tameem <ahmad.tameem@10xengineers.ai>
2023-10-03 21:38:19 +03:00
h-h-h-h
8186242b6d
main : consistent prefix/suffix coloring (#3425)
* Typo

* No `--in-prefix` coloring

The `--in-prefix` text was inconsistently colored. Now, it's never colored, just like the `--in-suffix` text.
2023-10-03 21:16:15 +03:00
Georgi Gerganov
ac2219fef3
llama : fix session saving/loading (#3400)
* llama : fix session saving/loading

* llama : temp fix for clearing "future" tokens from the KV cache

* llama : fix handling of "future" tokens when loading sessions

* llama : fix comments for llama_kv_cache API
2023-10-03 21:04:01 +03:00
Alex Klinkhamer
48be797ffb
llama : expose model's rope_freq_scale in the API (#3418)
so it can be scaled further before creating a context.
2023-10-03 20:09:28 +03:00
Jiahao Li
f56e1baec3
metal : alibi for arbitrary number of heads (#3426) 2023-10-03 19:55:21 +03:00
Eve
017efe899d
cmake : make LLAMA_NATIVE flag actually use the instructions supported by the processor (#3273)
* fix LLAMA_NATIVE

* syntax

* alternate implementation

* my eyes must be getting bad...

* set cmake LLAMA_NATIVE=ON by default

* march=native doesn't work for ios/tvos, so disable for those targets. also see what happens if we use it on msvc

* revert 8283237 and only allow LLAMA_NATIVE on x86 like the Makefile

* remove -DLLAMA_MPI=ON

---------

Co-authored-by: netrunnereve <netrunnereve@users.noreply.github.com>
2023-10-03 19:53:15 +03:00