| Name | pygpt4all JSON |
| Version |
1.1.0
JSON |
| download |
| home_page | |
| Summary | Official Python CPU inference for GPT4All language models based on llama.cpp and ggml |
| upload_time | 2023-05-02 20:12:23 |
| maintainer | |
| docs_url | None |
| author | Abdeladim Sadiki |
| requires_python | >=3.8 |
| license | MIT |
| keywords |
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# PyGPT4All
Official Python CPU inference for [GPT4All](https://github.com/nomic-ai/gpt4all) language models based on [llama.cpp](https://github.com/ggerganov/llama.cpp) and [ggml](https://github.com/ggerganov/ggml)
[](https://opensource.org/licenses/MIT)
[](https://pypi.org/project/pygpt4all/)
<!-- TOC -->
* [Installation](#installation)
* [Tutorial](#tutorial)
* [Model instantiation](#model-instantiation)
* [Simple generation](#simple-generation)
* [Interactive Dialogue](#interactive-dialogue)
* [API reference](#api-reference)
* [License](#license)
<!-- TOC -->
# Installation
```bash
pip install pygpt4all
```
# Tutorial
You will need first to download the model weights
| Model | Download link |
|-----------|----------------------------------------------------------|
| GPT4ALL | http://gpt4all.io/models/ggml-gpt4all-l13b-snoozy.bin |
| GPT4ALL-j | https://gpt4all.io/models/ggml-gpt4all-j-v1.3-groovy.bin |
### Model instantiation
Once the weights are downloaded, you can instantiate the models as follows:
* GPT4All model
```python
from pygpt4all import GPT4All
model = GPT4All('path/to/ggml-gpt4all-l13b-snoozy.bin')
```
* GPT4All-J model
```python
from pygpt4all import GPT4All_J
model = GPT4All_J('path/to/ggml-gpt4all-j-v1.3-groovy.bin')
```
### Simple generation
The `generate` function is used to generate new tokens from the `prompt` given as input:
```python
for token in model.generate("Tell me a joke ?\n"):
print(token, end='', flush=True)
```
### Interactive Dialogue
You can set up an interactive dialogue by simply keeping the `model` variable alive:
```python
while True:
try:
prompt = input("You: ", flush=True)
if prompt == '':
continue
print(f"AI:", end='')
for token in model.generate(prompt):
print(f"{token}", end='', flush=True)
print()
except KeyboardInterrupt:
break
```
# API reference
You can check the [API reference documentation](https://nomic-ai.github.io/pygpt4all/) for more details.
# License
This project is licensed under the MIT [License](./LICENSE).
Raw data
{
"_id": null,
"home_page": "",
"name": "pygpt4all",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": "",
"keywords": "",
"author": "Abdeladim Sadiki",
"author_email": "",
"download_url": "https://files.pythonhosted.org/packages/9f/57/fe1203e28b8fa7d5ce3f3eecb415932084326a98c03430d200f0897ba316/pygpt4all-1.1.0.tar.gz",
"platform": null,
"description": "# PyGPT4All\nOfficial Python CPU inference for [GPT4All](https://github.com/nomic-ai/gpt4all) language models based on [llama.cpp](https://github.com/ggerganov/llama.cpp) and [ggml](https://github.com/ggerganov/ggml)\n\n[](https://opensource.org/licenses/MIT)\n[](https://pypi.org/project/pygpt4all/)\n\n<!-- TOC -->\n* [Installation](#installation)\n* [Tutorial](#tutorial)\n * [Model instantiation](#model-instantiation)\n * [Simple generation](#simple-generation)\n * [Interactive Dialogue](#interactive-dialogue)\n* [API reference](#api-reference)\n* [License](#license)\n<!-- TOC -->\n# Installation\n\n```bash\npip install pygpt4all\n```\n\n# Tutorial\n\nYou will need first to download the model weights\n\n| Model | Download link |\n|-----------|----------------------------------------------------------|\n| GPT4ALL | http://gpt4all.io/models/ggml-gpt4all-l13b-snoozy.bin |\n| GPT4ALL-j | https://gpt4all.io/models/ggml-gpt4all-j-v1.3-groovy.bin | \n\n### Model instantiation\nOnce the weights are downloaded, you can instantiate the models as follows:\n* GPT4All model\n\n```python\nfrom pygpt4all import GPT4All\n\nmodel = GPT4All('path/to/ggml-gpt4all-l13b-snoozy.bin')\n```\n\n* GPT4All-J model\n\n```python\nfrom pygpt4all import GPT4All_J\n\nmodel = GPT4All_J('path/to/ggml-gpt4all-j-v1.3-groovy.bin')\n```\n\n\n### Simple generation\nThe `generate` function is used to generate new tokens from the `prompt` given as input:\n\n```python\nfor token in model.generate(\"Tell me a joke ?\\n\"):\n print(token, end='', flush=True)\n```\n\n### Interactive Dialogue\nYou can set up an interactive dialogue by simply keeping the `model` variable alive:\n\n```python\nwhile True:\n try:\n prompt = input(\"You: \", flush=True)\n if prompt == '':\n continue\n print(f\"AI:\", end='')\n for token in model.generate(prompt):\n print(f\"{token}\", end='', flush=True)\n print()\n except KeyboardInterrupt:\n break\n```\n\n# API reference\nYou can check the [API reference documentation](https://nomic-ai.github.io/pygpt4all/) for more details.\n\n\n# License\nThis project is licensed under the MIT [License](./LICENSE).\n\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Official Python CPU inference for GPT4All language models based on llama.cpp and ggml",
"version": "1.1.0",
"project_urls": {
"Documentation": "https://nomic-ai.github.io/pygpt4all/",
"Source": "https://github.com/nomic-ai/pygpt4all",
"Tracker": "https://github.com/nomic-ai/pygpt4all/issues"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "9f57fe1203e28b8fa7d5ce3f3eecb415932084326a98c03430d200f0897ba316",
"md5": "2914cdda13976819f81bcbce78eb9a5f",
"sha256": "d78fd0d7e85e014a10de90becc0867747fe081fd4d190088410e10fc58349c4f"
},
"downloads": -1,
"filename": "pygpt4all-1.1.0.tar.gz",
"has_sig": false,
"md5_digest": "2914cdda13976819f81bcbce78eb9a5f",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 4393,
"upload_time": "2023-05-02T20:12:23",
"upload_time_iso_8601": "2023-05-02T20:12:23.342586Z",
"url": "https://files.pythonhosted.org/packages/9f/57/fe1203e28b8fa7d5ce3f3eecb415932084326a98c03430d200f0897ba316/pygpt4all-1.1.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-05-02 20:12:23",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "nomic-ai",
"github_project": "pygpt4all",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [],
"lcname": "pygpt4all"
}
