a97f7d5f91
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .devops/full-cuda.Dockerfile
# .devops/full-rocm.Dockerfile
# .devops/full.Dockerfile
# .devops/main-cuda.Dockerfile
# .devops/main-intel.Dockerfile
# .devops/main-rocm.Dockerfile
# .devops/main.Dockerfile
# .devops/server-cuda.Dockerfile
# .devops/server-intel.Dockerfile
# .devops/server-rocm.Dockerfile
# .devops/server.Dockerfile
# .devops/tools.sh
# .github/workflows/docker.yml
# CMakeLists.txt
# Makefile
# README-sycl.md
# README.md
# ci/run.sh
# llama.cpp
# requirements.txt
# requirements/requirements-convert-hf-to-gguf-update.txt
# requirements/requirements-convert-hf-to-gguf.txt
# requirements/requirements-convert-legacy-llama.txt
# requirements/requirements-convert-llama-ggml-to-gguf.txt
# scripts/check-requirements.sh
# scripts/compare-llama-bench.py
# scripts/convert-gg.sh
# scripts/pod-llama.sh
# scripts/sync-ggml-am.sh
# scripts/sync-ggml.last
# scripts/sync-ggml.sh
# tests/CMakeLists.txt
# tests/test-backend-ops.cpp
# tests/test-tokenizer-0.sh
# tests/test-tokenizer-random.py
2024-06-02 12:28:38 +08:00
9c4c9cc83f
Move convert.py to examples/convert-legacy-llama.py ( #7430 )
...
* Move convert.py to examples/convert-no-torch.py
* Fix CI, scripts, readme files
* convert-no-torch -> convert-legacy-llama
* Move vocab thing to vocab.py
* Fix convert-no-torch -> convert-legacy-llama
* Fix lost convert.py in ci/run.sh
* Fix imports
* Fix gguf not imported correctly
* Fix flake8 complaints
* Fix check-requirements.sh
* Get rid of ADDED_TOKENS_FILE, FAST_TOKENIZER_FILE
* Review fixes
2024-05-30 21:40:00 +10:00
4ed9ba7352
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/workflows/docker.yml
# CMakeLists.txt
# Makefile
# README.md
# flake.lock
# tests/test-backend-ops.cpp
2024-05-28 21:57:19 +08:00
74b239b3d5
llava : update clip.h ( #7580 )
...
overriden -> overridden
2024-05-28 12:48:16 +10:00
9282c307ed
this commit does not work, just for debugging
2024-05-23 20:13:47 +08:00
6ff13987ad
common : normalize naming style ( #7462 )
...
* common : normalize naming style
ggml-ci
* common : match declaration / definition order
* zig : try to fix build
2024-05-22 20:04:20 +03:00
47cbfd6150
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/workflows/build.yml
# CMakeLists.txt
# README.md
# llama.cpp
# scripts/sync-ggml-am.sh
# scripts/sync-ggml.last
# scripts/sync-ggml.sh
# tests/test-backend-ops.cpp
2024-05-17 22:30:41 +08:00
344f9126cc
ggml : tag ggml_tensor::backend as deprecated ( #7290 )
2024-05-15 15:08:48 +02:00
2ee808a747
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/workflows/build.yml
# CMakeLists.txt
# README.md
# ci/run.sh
# llama.cpp
# models/ggml-vocab-llama-bpe.gguf.inp
# models/ggml-vocab-llama-bpe.gguf.out
# requirements.txt
# scripts/compare-llama-bench.py
# scripts/sync-ggml.last
# tests/CMakeLists.txt
# tests/test-backend-ops.cpp
# tests/test-grammar-integration.cpp
# tests/test-tokenizer-1-bpe.cpp
2024-05-14 19:28:47 +08:00
30e70334f7
llava-cli: fix base64 prompt ( #7248 )
2024-05-14 00:02:36 +10:00
4e3880978f
Fix memory bug in grammar parser ( #7194 )
...
The llama.cpp grammar parser had a bug where forgetting to add a closing
quotation mark to strings would cause parsing to crash. Anyone running a
server on a public endpoint is advised to upgrade. To reproduce this bug
./llamafile -m foo.gguf -p bar --grammar 'root::="'
Credit for discovering and reporting this issue goes to Eclypsium
Security Researcher Richard Johnson <Richard.johnson@eclypsium.com >.
2024-05-10 21:01:08 +10:00
d11afd6652
llava : fix moondream support ( #7163 )
...
* Revert "Revert "llava : add support for moondream vision language model (#6899 )""
This reverts commit 9da243b36a
2024-05-10 09:41:10 +03:00
9da243b36a
Revert "llava : add support for moondream vision language model ( #6899 )"
...
This reverts commit 46e12c4692
2024-05-08 22:14:39 +03:00
bc39b4d98a
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# CMakeLists.txt
# README.md
# ci/run.sh
# docs/BLIS.md
# flake.lock
# grammars/README.md
2024-05-08 09:58:23 +08:00
04976db7a8
docs: fix typos ( #7124 )
...
* fix typo
* fix typos
* fix typo
* fix typos
* fix typo
* fix typos
2024-05-07 18:20:33 +03:00
89db8afded
revert moondream to try and fix llava
2024-05-04 10:07:54 +08:00
17a24d753c
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .devops/main-intel.Dockerfile
# .devops/main-vulkan.Dockerfile
# .devops/server-intel.Dockerfile
# .devops/server-vulkan.Dockerfile
# .github/workflows/bench.yml
# .github/workflows/build.yml
# .github/workflows/python-lint.yml
# .github/workflows/server.yml
# .gitignore
# Makefile
# README-sycl.md
# README.md
# ci/run.sh
# flake.lock
# llama.cpp
# models/ggml-vocab-falcon.gguf
# models/ggml-vocab-llama-spm.gguf
# models/ggml-vocab-mpt.gguf
# models/ggml-vocab-stablelm.gguf
# models/ggml-vocab-starcoder.gguf
# requirements.txt
# scripts/check-requirements.sh
# tests/CMakeLists.txt
# tests/test-backend-ops.cpp
# tests/test-grammar-integration.cpp
# tests/test-tokenizer-0-bpe.py
# tests/test-tokenizer-0-spm.py
# tests/test-tokenizer-1-spm.cpp
2024-04-30 21:04:17 +08:00
ffe666572f
llava-cli : multiple images ( #6969 )
...
Co-authored-by: root <root@nenya.lothlorien.ca >
2024-04-29 17:34:24 +03:00
544c36f751
merge, deprecate openblas
2024-04-26 19:24:59 +08:00
46e12c4692
llava : add support for moondream vision language model ( #6899 )
...
* add support for moondream vision language model
This required making the following changes to the CLIP model:
1. Support for patch embedding bias.
2. Make class embedding and pre-layernorm optional.
3. Add support for post-layernorm.
* Update examples/llava/clip.cpp
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
2024-04-25 22:38:31 +03:00
4ab99d8d47
clip : rename lerp function to avoid conflict ( #6894 )
...
This commit renamesthe lerp (linear interpolation) function in clip.cpp
to avoid a conflict with the lerp function in the <cmath> standard C++
library when using c++20.
The motivation for this change is to enable projects that use c++20 to
be able to compile clip.cpp without having to resort to patching it. The
lerp function was added to cmath in version C++20 (202002L) and is why
this is not causing any issue at the moment as C++11/C++17 is currently
used by llama.cpp.
I realize that llama.cpp uses either C++11 (or C++17 in the case for
SYCL) but wanted to ask if this would be an acceptable change just the
same.
Refs: https://en.cppreference.com/w/cpp/numeric/lerp
Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com >
2024-04-25 15:38:14 +03:00
b4d2031215
merged, added ability to render special tokens
2024-04-22 18:19:58 +08:00
89b0bf0d5d
llava : use logger in llava-cli ( #6797 )
...
This change removes printf() logging so llava-cli is shell scriptable.
2024-04-21 15:19:04 +03:00
b97bc3966e
llama : support Llama 3 HF conversion ( #6745 )
...
* Support Llama 3 conversion
The tokenizer is BPE.
* style
* Accept suggestion
Co-authored-by: Sourab Mangrulkar <13534540+pacman100@users.noreply.github.com >
* llama : add llama_token_is_eog()
ggml-ci
* llama : auto-detect more EOT tokens when missing in KV data
* convert : replacing EOS token is a hack
* llama : fix codegemma EOT token + add TODOs
* llama : fix model type string for 8B model
---------
Co-authored-by: Sourab Mangrulkar <13534540+pacman100@users.noreply.github.com >
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
2024-04-21 14:50:41 +03:00
9a25d77cc1
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/workflows/build.yml
# .github/workflows/docker.yml
# Makefile
# README-sycl.md
# README.md
# ci/run.sh
# ggml-cuda.cu
# ggml.c
# grammars/README.md
# scripts/get-wikitext-2.sh
# scripts/hf.sh
# scripts/sync-ggml.last
# tests/test-backend-ops.cpp
# tests/test-grammar-integration.cpp
# tests/test-json-schema-to-grammar.cpp
2024-04-14 21:18:39 +08:00
5c4d767ac0
chore: Fix markdown warnings ( #6625 )
2024-04-12 10:52:36 +02:00
1b67731e18
BERT tokenizer fixes ( #6498 )
...
Key changes:
* BERT conversion: fix abuse of LlamaHfVocab, do not set BOS or EOS
* Nomic Embed conversion: pad vocab instead of slicing embedding tensor
* llama_tokenize: handle added special tokens like HF does
2024-04-09 13:44:08 -04:00
81ac0e5656
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .devops/full-cuda.Dockerfile
# .devops/full-rocm.Dockerfile
# .devops/full.Dockerfile
# .devops/llama-cpp-clblast.srpm.spec
# .devops/llama-cpp-cuda.srpm.spec
# .devops/llama-cpp.srpm.spec
# .devops/nix/package.nix
# .devops/server-cuda.Dockerfile
# .devops/server-intel.Dockerfile
# .devops/server-rocm.Dockerfile
# .devops/server-vulkan.Dockerfile
# .devops/server.Dockerfile
# .github/workflows/build.yml
# .github/workflows/code-coverage.yml
# .github/workflows/docker.yml
# .github/workflows/editorconfig.yml
# .github/workflows/gguf-publish.yml
# .github/workflows/nix-ci-aarch64.yml
# .github/workflows/nix-ci.yml
# .github/workflows/python-check-requirements.yml
# .github/workflows/python-lint.yml
# .github/workflows/server.yml
# .github/workflows/zig-build.yml
# CMakeLists.txt
# Makefile
# README-sycl.md
# README.md
# ci/run.sh
# examples/gguf-split/gguf-split.cpp
# flake.lock
# flake.nix
# llama.cpp
# scripts/compare-llama-bench.py
# scripts/sync-ggml-am.sh
# scripts/sync-ggml.last
# scripts/sync-ggml.sh
# tests/CMakeLists.txt
# tests/test-backend-ops.cpp
# tests/test-chat-template.cpp
2024-04-07 22:07:27 +08:00
a530afa1e4
Merge commit '280345968dabc00d212d43e31145f5c9961a7604' into concedo_experimental
...
# Conflicts:
# .devops/full-cuda.Dockerfile
# .devops/llama-cpp-cuda.srpm.spec
# .devops/main-cuda.Dockerfile
# .devops/nix/package.nix
# .devops/server-cuda.Dockerfile
# .github/workflows/build.yml
# CMakeLists.txt
# Makefile
# README.md
# ci/run.sh
# docs/token_generation_performance_tips.md
# flake.lock
# llama.cpp
# scripts/LlamaConfig.cmake.in
# scripts/compare-commits.sh
# scripts/server-llm.sh
# tests/test-quantize-fns.cpp
2024-04-07 20:27:17 +08:00
9c0fbf9f73
Merge commit 'ad3a0505e3b6cd777259ee35e61d428357ffc565' into concedo_experimental
...
# Conflicts:
# .github/workflows/build.yml
# .github/workflows/close-issue.yml
# .github/workflows/code-coverage.yml
# .github/workflows/docker.yml
# .github/workflows/editorconfig.yml
# .github/workflows/nix-ci-aarch64.yml
# .github/workflows/nix-ci.yml
# .github/workflows/python-check-requirements.yml
# .github/workflows/python-lint.yml
# .github/workflows/server.yml
# .github/workflows/zig-build.yml
# .gitignore
# CMakeLists.txt
# Makefile
# README-sycl.md
# README.md
# build.zig
# common/CMakeLists.txt
# llama.cpp
# tests/CMakeLists.txt
# tests/test-backend-ops.cpp
2024-04-06 18:32:57 +08:00
66ba560256
llava : fix MobileVLM ( #6364 )
...
* fix empty bug
* Update MobileVLM-README.md
added more results on devices
* Update MobileVLM-README.md
* Update MobileVLM-README.md
* Update MobileVLM-README.md
* Update MobileVLM-README.md
* Update MobileVLM-README.md
* Update MobileVLM-README.md
* Update examples/llava/MobileVLM-README.md
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
* Update MobileVLM-README.md
remove gguf links
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
2024-03-28 16:33:10 +02:00
d0e2f6416b
doc: fix typo in MobileVLM-README.md ( #6181 )
2024-03-28 13:03:30 +09:00
280345968d
cuda : rename build flag to LLAMA_CUDA ( #6299 )
2024-03-26 01:16:01 +01:00
f9c7ba3447
llava : update MobileVLM-README.md ( #6180 )
2024-03-20 17:29:51 +02:00
272935b281
llava : add MobileVLM_V2 backup ( #6175 )
...
* Add MobileVLM_V2 backup
* Update MobileVLM-README.md
* Update examples/llava/MobileVLM-README.md
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
* Update examples/llava/convert-image-encoder-to-gguf.py
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
* clip : fix whitespace
* fix deifinition mistake in clip.cpp
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
2024-03-20 17:02:32 +02:00
d795988d9e
Revert "llava : add a MobileVLM_V2-1.7B backup ( #6152 )"
...
This reverts commit f8c4e745e1
2024-03-20 13:29:49 +02:00
f8c4e745e1
llava : add a MobileVLM_V2-1.7B backup ( #6152 )
...
* Add MobileVLM_V2 backup
* Update MobileVLM-README.md
* Update examples/llava/MobileVLM-README.md
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
* Update examples/llava/convert-image-encoder-to-gguf.py
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
* clip : fix whitespace
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
2024-03-20 13:20:37 +02:00
a3fa919c67
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/workflows/build.yml
# Makefile
# flake.lock
# ggml-cuda.cu
# ggml-cuda.h
2024-03-19 18:57:22 +08:00
104f5e0fc1
clip : fix memory leak ( #6138 )
2024-03-18 17:40:22 +02:00
8b360b661c
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# Makefile
# README.md
# common/common.h
2024-03-17 23:03:12 +08:00
4e9a7f7f7f
llava : change API to pure C style for Rust FFI bindgen ( #6079 )
...
Co-authored-by: Lou Ting <louting.t@alibaba-inc.com >
2024-03-15 16:31:05 +02:00
93d3871056
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/workflows/build.yml
# CMakeLists.txt
# Makefile
# ggml-metal.m
2024-03-15 10:37:48 +08:00
6e0438da3c
gguf : fix resource leaks ( #6061 )
...
There several places where a gguf context is allocated. A call to gguf_free
is missing in some error paths. Also on linux, llama-bench was missing a
fclose.
2024-03-14 20:29:32 +02:00
15a333260a
readme : improve readme for Llava-1.6 example ( #6044 )
...
Co-authored-by: Jian Liao <jianliao@adobe.com >
2024-03-14 13:18:23 +02:00
6a32c14e86
Merge branch 'master' into concedo_experimental
...
# Conflicts:
# .github/workflows/build.yml
# CMakeLists.txt
# Makefile
# README-sycl.md
# README.md
# flake.lock
# scripts/sync-ggml-am.sh
# scripts/sync-ggml.last
# scripts/sync-ggml.sh
# tests/.gitignore
# tests/test-backend-ops.cpp
2024-03-11 23:00:47 +08:00
227f59dab6
added a simple program to do quantization for clip models
2024-03-11 21:50:30 +08:00
5b09797321
ggml : remove old quantization functions ( #5942 )
...
* ggml : remove old quantization functions
ggml-ci
* ggml : simplify ggml_quantize_chunk
ggml-ci
* ggml : restrict correctness
ggml-ci
* ggml : remove hist data from the quantization API
ggml-ci
* tests : remove hist usage in test-backend-ops
ggml-ci
* vulkan : remove hist and fix typo
2024-03-09 15:53:59 +02:00
ab336a9d5e
code : normalize enum names ( #5697 )
...
* coda : normalize enum names
ggml-ci
* code : cont
* code : cont
2024-02-25 12:09:09 +02:00
cc6cac08e3
llava : add --skip-unknown to 1.6 convert.py ( #5632 )
...
This commit adds the `--skip-unknown` option to the convert.py script
and removes the saving of the updated checkpoints to avoid updating
possibly checked out files.
The motivation for this change is that this was done for 1.5
in Commit fc0c8d286adaniel.bevenius@gmail.com >
2024-02-21 15:36:57 +02:00
6560bed3f0
server : support llava 1.6 ( #5553 )
...
* server: init working 1.6
* move clip_image to header
* remove commented code
* remove c++ style from header
* remove todo
* expose llava_image_embed_make_with_clip_img
* fix zig build
2024-02-20 21:07:22 +02:00
Concedo
Galunid
Ikko Eltociear Ashimine
Georgi Gerganov
slaren
k.h.lai
Justine Tunney
Andrei
omahs
cpumaxx
vik
Daniel Bevenius
Pedro Cuenca
Rene Leonhardt
Jared Van Bortel
Ziang Wu
Felix
Ting Lou
Steve Grubb
Jian Liao
CJ Pais