root
/
tabby
mirror of https://gitee.com/zhang_1334717033/tabby.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

docs: add device recommendations based on model size

release-0.2
Meng Zhang 2023-09-14 14:07:21 +08:00
parent 3d00cc5e87
commit 5897a776bb
1 changed files with 9 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
website/docs/models/index.md
View File

@ -4,7 +4,10 @@ sidebar_position: 4
# 🧑‍🔬 Models Directory
We maintains a curated list of models varies from 200M to 10B+.
We recommend using
* small models (less than 400M) for CPU devices.
* For 1B to 7B models, it's advisable to have at least NVIDIA T4, 10 Series, or 20 Series GPUs.
* For 7B to 13B models, we recommend using NVIDIA V100, A100, 30 Series, or 40 Series GPUs.
| Model ID | License | <span title="Apple M1/M2 Only">Metal Support</span> |
| --------------------------------------------------------------------- | ------------------------------------------------------------------------------------------- | :-------------------------------------------------: |
@ -16,16 +19,20 @@ We maintains a curated list of models varies from 200M to 10B+.
| [TabbyML/T5P-220M](https://huggingface.co/TabbyML/T5P-220M) | [BSD-3](https://opensource.org/license/bsd-3-clause/) | ❌ |
### CodeLlama-7B / CodeLlama-13B
Code Llama is a collection of pretrained and fine-tuned generative text models. Theses model is designed for general code synthesis and understanding.
### StarCoder-1B
StarCoderBase-1B is a 1B parameter model trained on 80+ programming languages from The Stack (v1.2), with opt-out requests excluded. The model uses Multi Query Attention, a context window of 8192 tokens, and was trained using the Fill-in-the-Middle objective on 1 trillion tokens.
### SantaCoder-1B
SantaCoder is the smallest member of the BigCode family of models, boasting just 1.1 billion parameters. This model is specifically trained with a fill-in-the-middle objective, enabling it to efficiently auto-complete function parameters. It offers support for three programming languages: Python, Java, and JavaScript.
### J-350M
Derived from [Salesforce/codegen-350M-multi](https://huggingface.co/Salesforce/codegen-350M-multi), a model of CodeGen family.
### T5P-220M
Derived from [Salesforce/codet5p-220m](https://huggingface.co/Salesforce/codet5p-220m), a model of CodeT5+ family.
Derived from [Salesforce/codet5p-220m](https://huggingface.co/Salesforce/codet5p-220m), a model of CodeT5+ family.