AI/gpt4all
1
0
Fork 0
mirror of https://github.com/nomic-ai/gpt4all.git synced 2024-10-01 01:06:10 -04:00
Code Issues Packages Projects Releases Wiki Activity
1,812 Commits 491 Branches 56 Tags 46 MiB
e94177ee9a
Commit Graph

252 Commits

Author SHA1 Message Date
Jared Van Bortel
e94177ee9a
llamamodel: fix embedding crash for >512 tokens after #2310 (#2383) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-05-29 10:51:00 -04:00
Jared Van Bortel
f047f383d0
llama.cpp: update submodule for "code" model crash workaround (#2382) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-05-29 10:50:00 -04:00
Jared Van Bortel
f1b4092ca6
llamamodel: fix BERT tokenization after llama.cpp update (#2381) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-05-28 13:11:57 -04:00
Jared Van Bortel
c779d8a32d
python: init_gpu fixes (#2368) 
* python: tweak GPU init failure message
* llama.cpp: update submodule for use-after-free fix

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-05-20 18:04:11 -04:00
Jared Van Bortel
2025d2d15b
llmodel: add CUDA to the DLL search path if CUDA_PATH is set (#2357) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-05-16 17:39:49 -04:00
Jared Van Bortel
a92d266cea
cmake: fix Metal build after #2310 (#2350) 
I don't understand why this is needed, but it works.

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-05-15 18:12:32 -04:00
Jared Van Bortel
d2a99d9bc6
support the llama.cpp CUDA backend (#2310) 
* rebase onto llama.cpp commit ggerganov/llama.cpp@d46dbc76f
* support for CUDA backend (enabled by default)
* partial support for Occam's Vulkan backend (disabled by default)
* partial support for HIP/ROCm backend (disabled by default)
* sync llama.cpp.cmake with upstream llama.cpp CMakeLists.txt
* changes to GPT4All backend, bindings, and chat UI to handle choice of llama.cpp backend (Kompute or CUDA)
* ship CUDA runtime with installed version
* make device selection in the UI on macOS actually do something
* model whitelist: remove dbrx, mamba, persimmon, plamo; add internlm and starcoder2

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-05-15 15:27:50 -04:00
Jared Van Bortel
9f9d8e636f
backend: do not crash if GGUF lacks general.architecture (#2346) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-05-15 13:57:13 -04:00
Jared Van Bortel
6d8888b267
llamamodel: free the batch in embedInternal (#2348) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-05-15 12:46:12 -04:00
Jared Van Bortel
577ebd4826
mixpanel: report cpu_supports_avx2 on startup (#2299) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-05-02 16:09:41 -04:00
Jared Van Bortel
adaecb7a72
mixpanel: improved GPU device statistics (plus GPU sort order fix) (#2297) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-05-01 16:15:48 -04:00
Jared Van Bortel
c622921894
improve mixpanel usage statistics (#2238) 
Other changes:
- Always display first start dialog if privacy options are unset (e.g. if the user closed GPT4All without selecting them)
- LocalDocs scanQueue is now always deferred
- Fix a potential crash in magic_match
- LocalDocs indexing is now started after the first start dialog is dismissed so usage stats are included

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-04-25 13:16:52 -04:00
Jared Van Bortel
ba53ab5da0
python: do not print GPU name with verbose=False, expose this info via properties (#2222) 
* llamamodel: only print device used in verbose mode

Signed-off-by: Jared Van Bortel <jared@nomic.ai>

* python: expose backend and device via GPT4All properties

Signed-off-by: Jared Van Bortel <jared@nomic.ai>

* backend: const correctness fixes

Signed-off-by: Jared Van Bortel <jared@nomic.ai>

* python: bump version

Signed-off-by: Jared Van Bortel <jared@nomic.ai>

* python: typing fixups

Signed-off-by: Jared Van Bortel <jared@nomic.ai>

* python: fix segfault with closed GPT4All

Signed-off-by: Jared Van Bortel <jared@nomic.ai>

---------

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-04-18 14:52:02 -04:00
Jared Van Bortel
ac498f79ac
fix regressions in system prompt handling (#2219) 
* python: fix system prompt being ignored
* fix unintended whitespace after system prompt

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-04-15 11:39:48 -04:00
Jared Van Bortel
3f8257c563
llamamodel: fix semantic typo in nomic client dynamic mode (#2216) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-04-12 17:25:15 -04:00
Jared Van Bortel
46818e466e
python: embedding cancel callback for nomic client dynamic mode (#2214) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-04-12 16:00:39 -04:00
Jared Van Bortel
459289b94c
embed4all: small fixes related to nomic client local embeddings (#2213) 
* actually submit larger batches with increased n_ctx
* fix crash when llama_tokenize returns no tokens

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-04-12 10:54:15 -04:00
Jared Van Bortel
1b84a48c47
python: add list_gpus to the GPT4All API (#2194) 
Other changes:
* fix memory leak in llmodel_available_gpu_devices
* drop model argument from llmodel_available_gpu_devices
* breaking: make GPT4All/Embed4All arguments past model_name keyword-only

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-04-04 14:52:13 -04:00
Jared Van Bortel
67843edc7c
backend: update llama.cpp submodule for wpm locale fix (#2163) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-26 11:04:22 -04:00
Jared Van Bortel
83ada4ca89
backend: update llama.cpp submodule for Unicode paths fix (#2162) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-26 11:01:02 -04:00
Jared Van Bortel
0455b80b7f
Embed4All: optionally count tokens, misc fixes (#2145) 
Key changes:
* python: optionally return token count in Embed4All.embed
* python and docs: models2.json -> models3.json
* Embed4All: require explicit prefix for unknown models
* llamamodel: fix shouldAddBOS for Bert and Nomic Bert

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-20 11:24:02 -04:00
Jared Van Bortel
a1bb6084ed
python: documentation update and typing improvements (#2129) 
Key changes:
* revert "python: tweak constructor docstrings"
* docs: update python GPT4All and Embed4All documentation
* breaking: require keyword args to GPT4All.generate

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-19 17:25:22 -04:00
Jared Van Bortel
699410014a
fix non-AVX CPU detection (#2141) 
* chat: fix non-AVX CPU detection on Windows
* bindings: throw exception instead of logging to console

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-19 10:56:14 -04:00
Jared Van Bortel
255568fb9a
python: various fixes for GPT4All and Embed4All (#2130) 
Key changes:
* honor empty system prompt argument
* current_chat_session is now read-only and defaults to None
* deprecate fallback prompt template for unknown models
* fix mistakes from #2086

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-15 11:49:58 -04:00
Jared Van Bortel
53f109f519
llamamodel: fix macOS build (#2125) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-14 12:06:07 -04:00
Jared Van Bortel
406e88b59a
implement local Nomic Embed via llama.cpp (#2086) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-13 18:09:24 -04:00
Jared Van Bortel
5c248dbec9
models: new MPT model file without duplicated token_embd.weight (#2006) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-08 17:18:38 -05:00
Jared Van Bortel
c19b763e03
llmodel_c: expose fakeReply to the bindings (#2061) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-06 13:32:24 -05:00
Jared Van Bortel
f500bcf6e5
llmodel: default to a blank line between reply and next prompt (#1996) 
Also make some related adjustments to the provided Alpaca-style prompt templates
and system prompts.

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-02-26 13:11:15 -05:00
Jared Van Bortel
007d469034
bert: fix layer norm epsilon value (#1946) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-02-26 13:09:01 -05:00
Adam Treat
f720261d46 Fix another vulnerable spot for crashes. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-02-26 12:04:16 -06:00
chrisbarrera
f8b1069a1c
add min_p sampling parameter (#2014) 
Signed-off-by: Christopher Barrera <cb@arda.tx.rr.com>
Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
 2024-02-24 17:51:34 -05:00
Jared Van Bortel
e7f2ff189f fix some compilation warnings on macOS 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-02-22 15:09:06 -05:00
Jared Van Bortel
88e330ef0e
llama.cpp: enable Kompute support for 10 more model arches (#2005) 
These are Baichuan, Bert and Nomic Bert, CodeShell, GPT-2, InternLM,
MiniCPM, Orion, Qwen, and StarCoder.

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-02-22 14:34:42 -05:00
Jared Van Bortel
fc6c5ea0c7
llama.cpp: gemma: allow offloading the output tensor (#1997) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-02-22 14:06:18 -05:00
Jared Van Bortel
4fc4d94be4
fix chat-style prompt templates (#1970) 
Also use a new version of Mistral OpenOrca.

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-02-21 15:45:32 -05:00
Jared Van Bortel
7810b757c9 llamamodel: add gemma model support 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-02-21 13:36:31 -06:00
Adam Treat
d948a4f2ee Complete revamp of model loading to allow for more discreet control by 
the user of the models loading behavior.

Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-02-21 10:15:20 -06:00
Jared Van Bortel
6fdec808b2 backend: update llama.cpp for faster state serialization 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-02-13 17:39:18 -05:00
Jared Van Bortel
a1471becf3 backend: update llama.cpp for Intel GPU blacklist 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-02-12 13:16:24 -05:00
Jared Van Bortel
eb1081d37e cmake: fix LLAMA_DIR use before set 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-02-09 22:00:14 -05:00
Jared Van Bortel
e60b388a2e cmake: fix backwards LLAMA_KOMPUTE default 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-02-09 21:53:32 -05:00
Jared Van Bortel
fc7e5f4a09
ci: fix missing Kompute support in python bindings (#1953) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-02-09 21:40:32 -05:00
Jared Van Bortel
bf493bb048
Mixtral crash fix and python bindings v2.2.0 (#1931) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-02-06 11:01:15 -05:00
Jared Van Bortel
92c025a7f6
llamamodel: add 12 new architectures for CPU inference (#1914) 
Baichuan, BLOOM, CodeShell, GPT-2, Orion, Persimmon, Phi and Phi-2,
Plamo, Qwen, Qwen2, Refact, StableLM

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-02-05 16:49:31 -05:00
Jared Van Bortel
10e3f7bbf5
Fix VRAM leak when model loading fails (#1901) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-02-01 15:45:45 -05:00
Jared Van Bortel
eadc3b8d80 backend: bump llama.cpp for VRAM leak fix when switching models 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-01-31 17:24:01 -05:00
Jared Van Bortel
6db5307730 update llama.cpp for unhandled Vulkan OOM exception fix 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-01-31 16:44:58 -05:00
Jared Van Bortel
0a40e71652
Maxwell/Pascal GPU support and crash fix (#1895) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-01-31 16:32:32 -05:00
Jared Van Bortel
b11c3f679e bump llama.cpp-mainline for C++11 compat 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-01-31 15:02:34 -05:00