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
2,070 Commits 491 Branches 56 Tags 46 MiB
3682b242e7
Commit Graph

277 Commits

Author SHA1 Message Date
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
Jared Van Bortel
061d1969f8
expose n_gpu_layers parameter of llama.cpp (#1890) 
Also dynamically limit the GPU layers and context length fields to the maximum supported by the model.

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-01-31 14:17:44 -05:00
Jared Van Bortel
f549d5a70a backend : quick llama.cpp update to fix fallback to CPU 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-01-29 17:16:40 -05:00
Jared Van Bortel
38c61493d2 backend: update to latest commit of llama.cpp Vulkan PR 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-01-29 15:47:26 -06:00
Jared Van Bortel
26acdebafa
convert: replace GPTJConfig with AutoConfig (#1866) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-01-22 12:14:55 -05:00
Jared Van Bortel
a9c5f53562 update llama.cpp for nomic-ai/llama.cpp#12 
Fixes #1477

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-01-17 14:05:33 -05:00
Jared Van Bortel
b7c92c5afd
sync llama.cpp with latest Vulkan PR and newer upstream (#1819) 2024-01-16 16:36:21 -05:00
Jared Van Bortel
7e9786fccf chat: set search path early 
This fixes the issues with installed versions of v2.6.0.
 2024-01-11 12:04:18 -05:00
AT
96cee4f9ac
Explicitly clear the kv cache each time we eval tokens to match n_past. (#1808) 2024-01-03 14:06:08 -05:00
ThiloteE
2d566710e5 Address review 2024-01-03 11:13:07 -06:00
ThiloteE
a0f7d7ae0e Fix for "LLModel ERROR: Could not find CPU LLaMA implementation" v2 2024-01-03 11:13:07 -06:00
ThiloteE
38d81c14d0 Fixes https://github.com/nomic-ai/gpt4all/issues/1760 LLModel ERROR: Could not find CPU LLaMA implementation. 
Inspired by Microsoft docs for LoadLibraryExA (https://learn.microsoft.com/en-us/windows/win32/api/libloaderapi/nf-libloaderapi-loadlibraryexa).
When using LOAD_LIBRARY_SEARCH_DLL_LOAD_DIR, the lpFileName parameter must specify a fully qualified path, also it needs to be backslashes (\), not forward slashes (/).
 2024-01-03 11:13:07 -06:00
Jared Van Bortel
d1c56b8b28
Implement configurable context length (#1749) 2023-12-16 17:58:15 -05:00
Jared Van Bortel
3acbef14b7
fix AVX support by removing direct linking to AVX2 libs (#1750) 2023-12-13 12:11:09 -05:00
Jared Van Bortel
0600f551b3
chatllm: do not attempt to serialize incompatible state (#1742) 2023-12-12 11:45:03 -05:00
Jared Van Bortel
1df3da0a88 update llama.cpp for clang warning fix 2023-12-11 13:07:41 -05:00
Jared Van Bortel
dfd8ef0186
backend: use ggml_new_graph for GGML backend v2 (#1719) 2023-12-06 14:38:53 -05:00
Jared Van Bortel
9e28dfac9c
Update to latest llama.cpp (#1706) 2023-12-01 16:51:15 -05:00
Adam Treat
cce5fe2045 Fix macos build. 2023-11-17 11:59:31 -05:00
Adam Treat
371e2a5cbc LocalDocs version 2 with text embeddings. 2023-11-17 11:59:31 -05:00
Jared Van Bortel
d4ce9f4a7c
llmodel_c: improve quality of error messages (#1625) 2023-11-07 11:20:14 -05:00
cebtenzzre
64101d3af5 update llama.cpp-mainline 2023-11-01 09:47:39 -04:00
Adam Treat
ffef60912f Update to llama.cpp 2023-10-30 11:40:16 -04:00
Adam Treat
f5f22fdbd0 Update llama.cpp for latest bugfixes. 2023-10-28 17:47:55 -04:00
cebtenzzre
7bcd9e8089 update llama.cpp-mainline 2023-10-27 19:29:36 -04:00
cebtenzzre
fd0c501d68
backend: support GGUFv3 (#1582) 2023-10-27 17:07:23 -04:00
Adam Treat
14b410a12a Update to latest version of llama.cpp which fixes issue 1507. 2023-10-27 12:08:35 -04:00
Adam Treat
ab96035bec Update to llama.cpp submodule for some vulkan fixes. 2023-10-26 13:46:38 -04:00
cebtenzzre
e90263c23f
make scripts executable (#1555) 2023-10-24 09:28:21 -04:00
Aaron Miller
f414c28589 llmodel: whitelist library name patterns 
this fixes some issues that were being seen on installed windows builds of 2.5.0

only load dlls that actually might be model impl dlls, otherwise we pull all sorts of random junk into the process before it might expect to be

Signed-off-by: Aaron Miller <apage43@ninjawhale.com>
 2023-10-23 21:40:14 -07:00
cebtenzzre
4338e72a51
MPT: use upstream llama.cpp implementation (#1515) 2023-10-19 15:25:17 -04:00
cebtenzzre
0fe2e19691
llamamodel: re-enable error messages by default (#1537) 2023-10-19 13:46:33 -04:00
cebtenzzre
017c3a9649
python: prepare version 2.0.0rc1 (#1529) 2023-10-18 20:24:54 -04:00
cebtenzzre
9a19c740ee
kompute: fix library loading issues with kp_logger (#1517) 2023-10-16 16:58:17 -04:00
Aaron Miller
f79557d2aa speedup: just use mat*vec shaders for mat*mat 
so far my from-scratch mat*mats are still slower than just running more
invocations of the existing Metal ported mat*vec shaders - it should be
theoretically possible to make a mat*mat that's faster (for actual
mat*mat cases) than an optimal mat*vec, but it will need to be at
*least* as fast as the mat*vec op and then take special care to be
cache-friendly and save memory bandwidth, as the # of compute ops is the
same
 2023-10-16 13:45:51 -04:00
cebtenzzre
22de3c56bd
convert scripts: fix AutoConfig typo (#1512) 2023-10-13 14:16:51 -04:00
Aaron Miller
2490977f89 q6k, q4_1 mat*mat 2023-10-12 14:56:54 -04:00
Aaron Miller
afaa291eab python bindings should be quiet by default 
* disable llama.cpp logging unless GPT4ALL_VERBOSE_LLAMACPP envvar is
  nonempty
* make verbose flag for retrieve_model default false (but also be
  overridable via gpt4all constructor)

should be able to run a basic test:

```python
import gpt4all
model = gpt4all.GPT4All('/Users/aaron/Downloads/rift-coder-v0-7b-q4_0.gguf')
print(model.generate('def fib(n):'))
```

and see no non-model output when successful
 2023-10-11 14:14:36 -07:00
cebtenzzre
7b611b49f2
llmodel: print an error if the CPU does not support AVX (#1499) 2023-10-11 15:09:40 -04:00
Aaron Miller
043617168e do not process prompts on gpu yet 2023-10-11 13:15:50 -04:00
Aaron Miller
64001a480a mat*mat for q4_0, q8_0 2023-10-11 13:15:50 -04:00
cebtenzzre
7a19047329
llmodel: do not call magic_match unless build variant is correct (#1488) 2023-10-11 11:30:48 -04:00
Cebtenzzre
5fe685427a chat: clearer CPU fallback messages 2023-10-06 11:35:14 -04:00
Adam Treat
eec906aa05 Speculative fix for build on mac. 2023-10-05 18:37:33 -04:00
Adam Treat
a9acdd25de Push a new version number for llmodel backend now that it is based on gguf. 2023-10-05 18:18:07 -04:00
Cebtenzzre
8bb6a6c201 rebase on newer llama.cpp 2023-10-05 18:16:19 -04:00
Cebtenzzre
d87573ea75 remove old llama.cpp submodules 2023-10-05 18:16:19 -04:00
Cebtenzzre
cc6db61c93 backend: fix build with Visual Studio generator 
Use the $<CONFIG> generator expression instead of CMAKE_BUILD_TYPE. This
is needed because Visual Studio is a multi-configuration generator, so
we do not know what the build type will be until `cmake --build` is
called.

Fixes #1470
 2023-10-05 18:16:19 -04:00
Adam Treat
f605a5b686 Add q8_0 kernels to kompute shaders and bump to latest llama/gguf. 2023-10-05 18:16:19 -04:00
Cebtenzzre
672cb850f9 differentiate between init failure and unsupported models 2023-10-05 18:16:19 -04:00
Adam Treat
906699e8e9 Bump to latest llama/gguf branch. 2023-10-05 18:16:19 -04:00
Cebtenzzre
088afada49 llamamodel: fix static vector in LLamaModel::endTokens 2023-10-05 18:16:19 -04:00
Adam Treat
b4d82ea289 Bump to the latest fixes for vulkan in llama. 2023-10-05 18:16:19 -04:00
Adam Treat
12f943e966 Fix regenerate button to be deterministic and bump the llama version to latest we have for gguf. 2023-10-05 18:16:19 -04:00
Adam Treat
5d346e13d7 Add q6_k kernels for vulkan. 2023-10-05 18:16:19 -04:00
Adam Treat
4eefd386d0 Refactor for subgroups on mat * vec kernel. 2023-10-05 18:16:19 -04:00
Cebtenzzre
3c2aa299d8 gptj: remove unused variables 2023-10-05 18:16:19 -04:00
Cebtenzzre
f9deb87d20 convert scripts: add feed-forward length for better compatiblilty 
This GGUF key is used by all llama.cpp models with upstream support.
 2023-10-05 18:16:19 -04:00
Cebtenzzre
cc7675d432 convert scripts: make gptj script executable 2023-10-05 18:16:19 -04:00
Cebtenzzre
0493e6eb07 convert scripts: use bytes_to_unicode from transformers 2023-10-05 18:16:19 -04:00
Cebtenzzre
d5d72f0361 gpt-j: update inference to match latest llama.cpp insights 
- Use F16 KV cache
- Store transposed V in the cache
- Avoid unnecessary Q copy

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

ggml upstream commit 0265f0813492602fec0e1159fe61de1bf0ccaf78
 2023-10-05 18:16:19 -04:00
Cebtenzzre
050e7f076e backend: port GPT-J to GGUF 2023-10-05 18:16:19 -04:00
Cebtenzzre
8f3abb37ca fix references to removed model types 2023-10-05 18:16:19 -04:00
Cebtenzzre
4219c0e2e7 convert scripts: make them directly executable 2023-10-05 18:16:19 -04:00
Cebtenzzre
ce7be1db48 backend: use llamamodel.cpp for Falcon 2023-10-05 18:16:19 -04:00
Cebtenzzre
cca9e6ce81 convert_mpt_hf_to_gguf.py: better tokenizer decoding 2023-10-05 18:16:19 -04:00
Cebtenzzre
25297786db convert scripts: load model as late as possible 2023-10-05 18:16:19 -04:00
Cebtenzzre
fd47088f2b conversion scripts: cleanup 2023-10-05 18:16:19 -04:00
Cebtenzzre
6277eac9cc backend: use llamamodel.cpp for StarCoder 2023-10-05 18:16:19 -04:00
Cebtenzzre
17fc9e3e58 backend: port Replit to GGUF 2023-10-05 18:16:19 -04:00
Cebtenzzre
7c67262a13 backend: port MPT to GGUF 2023-10-05 18:16:19 -04:00
Cebtenzzre
42bcb814b3 backend: port BERT to GGUF 2023-10-05 18:16:19 -04:00
Cebtenzzre
1d29e4696c llamamodel: metal supports all quantization types now 2023-10-05 18:16:19 -04:00
Aaron Miller
507753a37c macos build fixes 2023-10-05 18:16:19 -04:00
Adam Treat
d90d003a1d Latest rebase on llama.cpp with gguf support. 2023-10-05 18:16:19 -04:00
Adam Treat
99c106e6b5 Fix a bug seen on AMD RADEON cards with vulkan backend. 2023-09-26 11:59:47 -04:00