Update README.md
Browse files
README.md
CHANGED
|
@@ -19,7 +19,6 @@ tags:
|
|
| 19 |
- openthaigpt
|
| 20 |
- llama
|
| 21 |
---
|
| 22 |
-
# ----Quantized 4 bit GGML of OpenThaiGPT 1.0.0-alpha----
|
| 23 |
|
| 24 |
# 🇹🇠OpenThaiGPT 1.0.0-alpha
|
| 25 |
<img src="https://1173516064-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FvvbWvIIe82Iv1yHaDBC5%2Fuploads%2Fb8eiMDaqiEQL6ahbAY0h%2Fimage.png?alt=media&token=6fce78fd-2cca-4c0a-9648-bd5518e644ce
|
|
@@ -27,6 +26,8 @@ https://openthaigpt.aieat.or.th/" width="200px">
|
|
| 27 |
|
| 28 |
OpenThaiGPT Version 1.0.0-alpha is the first Thai implementation of a 7B-parameter LLaMA v2 Chat model finetuned to follow Thai translated instructions below and makes use of the Huggingface LLaMA implementation.
|
| 29 |
|
|
|
|
|
|
|
| 30 |
## Upgrade from OpenThaiGPT 0.1.0-beta
|
| 31 |
- Using Facebook LLama v2 model 7b chat as a base model which is pretrained on over 2 trillion token.
|
| 32 |
- Context Length is upgrade from 2048 token to 4096 token
|
|
|
|
| 19 |
- openthaigpt
|
| 20 |
- llama
|
| 21 |
---
|
|
|
|
| 22 |
|
| 23 |
# 🇹🇠OpenThaiGPT 1.0.0-alpha
|
| 24 |
<img src="https://1173516064-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FvvbWvIIe82Iv1yHaDBC5%2Fuploads%2Fb8eiMDaqiEQL6ahbAY0h%2Fimage.png?alt=media&token=6fce78fd-2cca-4c0a-9648-bd5518e644ce
|
|
|
|
| 26 |
|
| 27 |
OpenThaiGPT Version 1.0.0-alpha is the first Thai implementation of a 7B-parameter LLaMA v2 Chat model finetuned to follow Thai translated instructions below and makes use of the Huggingface LLaMA implementation.
|
| 28 |
|
| 29 |
+
# ---- Quantized 4 bit GGML of OpenThaiGPT 1.0.0-alpha ----
|
| 30 |
+
|
| 31 |
## Upgrade from OpenThaiGPT 0.1.0-beta
|
| 32 |
- Using Facebook LLama v2 model 7b chat as a base model which is pretrained on over 2 trillion token.
|
| 33 |
- Context Length is upgrade from 2048 token to 4096 token
|