Commit Graph

231 Commits

Author SHA1 Message Date
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
4a16a920a3 python: actually fix python 3.8 compatibility (#1973)
importlib.resources.files also didn't exist until python 3.9.

Fixes #1972

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
2024-02-26 13:15:02 -05:00
Jared Van Bortel
a59645c839 python: fix mistakes from PR #1970 (#2023)
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
2024-02-26 13:11:51 -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
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
TareHimself
a153cc5b25 typescript: async generator and token stream (#1897)
Signed-off-by: Tare Ebelo <75279482+TareHimself@users.noreply.github.com>
Signed-off-by: jacob <jacoobes@sern.dev>
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Co-authored-by: jacob <jacoobes@sern.dev>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
2024-02-24 17:50:14 -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
Simon Willison
f2024a1f9e python: README and project links for PyPI listing (#1964)
Signed-off-by: Simon Willison <swillison@gmail.com>
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
2024-02-13 17:44:33 -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
6da62a62f0 python: this was supposed to be an f-string
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
2024-02-09 15:09:13 -05:00
Jared Van Bortel
ec13ba2818 docs: update list of supported localdocs formats (#1944)
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
2024-02-07 17:09:29 -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
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
b881598166 py: improve README (#1860)
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
2024-01-21 19:53:55 -05:00
Jared Van Bortel
f8564398fc minor change to trigger CircleCI 2024-01-12 16:13:46 -05:00
Jared Van Bortel
eef604fd64 python: release bindings version 2.1.0
The backend has a breaking change for Falcon and MPT models, so we need
to make a new release.
2024-01-12 09:38:16 -05:00
Jared Van Bortel
d1c56b8b28 Implement configurable context length (#1749) 2023-12-16 17:58:15 -05:00
Jacob Nguyen
7aa0f779de Update mkdocs.yml (#1759)
update doc routing
2023-12-15 13:37:29 -06:00
Jacob Nguyen
a1f27072c2 fix/macm1ts (#1746)
* make runtime library backend universal searchable

* corepack enable

* fix

* pass tests

* simpler

* add more jsdoc

* fix testS

* fix up circle ci

* bump version

* remove false positive warning

* add disclaimer

* update readme

* revert

* update ts docs

---------

Co-authored-by: Matthew Nguyen <matthewpnguyen@Matthews-MacBook-Pro-7.local>
2023-12-15 12:44:39 -06:00
Jared Van Bortel
778264fbab python: don't use importlib as_file for a directory
The only reason to use as_file is to support copying a file from a
frozen package. We don't currently support this anyway, and as_file
isn't supported until Python 3.9, so get rid of it.

Fixes #1605
2023-12-11 13:35:56 -05:00
AT
84749a4ced Update gpt4all_chat.md
Signed-off-by: AT <manyoso@users.noreply.github.com>
2023-11-21 12:21:43 -05:00
AT
f1c58d0e2c Update gpt4all_chat.md
Signed-off-by: AT <manyoso@users.noreply.github.com>
2023-11-21 11:55:14 -05:00
Jared Van Bortel
d4ce9f4a7c llmodel_c: improve quality of error messages (#1625) 2023-11-07 11:20:14 -05:00
cebtenzzre
3c561bcdf2 python: bump bindings version for AMD fixes 2023-10-30 17:00:05 -04:00
cebtenzzre
e90263c23f make scripts executable (#1555) 2023-10-24 09:28:21 -04:00
cebtenzzre
7e5e84fbb7 python: change default extension to .gguf (#1559) 2023-10-23 22:18:50 -04:00
cebtenzzre
37b007603a bindings: replace references to GGMLv3 models with GGUF (#1547) 2023-10-22 11:58:28 -04:00
Andriy Mulyar
d50803ff8e GGUF Python Release (#1539) 2023-10-19 19:11:03 -04:00
cebtenzzre
245c5ce5ea update default model URLs (#1538) 2023-10-19 15:25:37 -04:00
cebtenzzre
0fe2e19691 llamamodel: re-enable error messages by default (#1537) 2023-10-19 13:46:33 -04:00
cebtenzzre
5fbeeb1cb4 python: connection resume and MSVC support (#1535) 2023-10-19 12:06:38 -04:00
cebtenzzre
017c3a9649 python: prepare version 2.0.0rc1 (#1529) 2023-10-18 20:24:54 -04:00
cebtenzzre
fd3014016b docs: clarify Vulkan dep in build instructions for bindings (#1525) 2023-10-18 12:09:52 -04:00
cebtenzzre
4d4275d1b8 python: replace deprecated pkg_resources with importlib (#1505) 2023-10-12 13:35:27 -04:00
Aaron Miller
f39df0906e fix embed4all filename
https://discordapp.com/channels/1076964370942267462/1093558720690143283/1161778216462192692

Signed-off-by: Aaron Miller <apage43@ninjawhale.com>
2023-10-12 07:52:56 -04:00
cebtenzzre
aed2068342 python: always check status code of HTTP responses (#1502) 2023-10-11 18:11:28 -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
f81b4b45bf python: support Path in GPT4All.__init__ (#1462) 2023-10-11 14:12:40 -04:00
Aaron Miller
a10f3aea5e python/embed4all: use gguf model, allow passing kwargs/overriding model 2023-10-05 18:16:19 -04:00
Adam Treat
ea66669cef Switch to new models2.json for new gguf release and bump our version to
2.5.0.
2023-10-05 18:16:19 -04:00
Cebtenzzre
40c78d2f78 python binding: print debug message to stderr 2023-10-05 18:16:19 -04:00
Cebtenzzre
4392bf26e0 pyllmodel: print specific error message 2023-10-05 18:16:19 -04:00
Cebtenzzre
34f2ec2b33 gpt4all.py: GGUF 2023-10-05 18:16:19 -04:00
kevinbazira
17cb4a86d1 Replace git clone SSH URI with HTTPS URL
Running `git clone --recurse-submodules git@github.com:nomic-ai/gpt4all.git`
returns `Permission denied (publickey)` as shown below:
```
git clone --recurse-submodules git@github.com:nomic-ai/gpt4all.git
Cloning into gpt4all...
git@github.com: Permission denied (publickey).
fatal: Could not read from remote repository.
```

This change replaces `git@github.com:nomic-ai/gpt4all.git` with
`https://github.com/nomic-ai/gpt4all.git` which runs without permission issues.

resolves nomic-ai/gpt4all#8, resolves nomic-ai/gpt4all#49
2023-09-20 09:48:47 -04:00
Adam Treat
0f046cf905 Bump the Python version to python-v1.0.12 to restrict the quants that vulkan recognizes. 2023-09-15 09:12:20 -04:00
Aaron Miller
f0735efa7d vulkan python bindings on windows fixes 2023-09-12 14:16:02 -07:00
Aaron Miller
0ad1472b62 bump python version (library linking fix) 2023-09-11 09:42:06 -07:00
Andriy Mulyar
b6e38d69ed Python version bump
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
2023-09-01 13:21:41 -04:00
Andriy Mulyar
707b91a24f Update Python bindings README.md (#1389)
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
2023-09-01 13:01:40 -04:00
Adam Treat
987546c63b Nomic vulkan backend licensed under the Software for Open Models License (SOM), version 1.0. 2023-08-31 15:29:54 -04:00