Update README.md
Browse files
README.md
CHANGED
|
@@ -14,6 +14,19 @@ tags:
|
|
| 14 |
|
| 15 |
<a href="https://ibb.co/4g2SJVM"><img src="https://i.ibb.co/PzMWt64/Screenshot-2024-05-18-at-11-08-12-PM.png" alt="Screenshot-2024-05-18-at-11-08-12-PM" border="0"></a>
|
| 16 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
### About this model
|
| 18 |
|
| 19 |
This is a 128B model based on [Bllossom/llama-3-Korean-Bllossom-70B](https://huggingface.co/Bllossom/llama-3-Korean-Bllossom-70B)
|
|
|
|
| 14 |
|
| 15 |
<a href="https://ibb.co/4g2SJVM"><img src="https://i.ibb.co/PzMWt64/Screenshot-2024-05-18-at-11-08-12-PM.png" alt="Screenshot-2024-05-18-at-11-08-12-PM" border="0"></a>
|
| 16 |
|
| 17 |
+
```
|
| 18 |
+
About Bllossom/llama-3-Korean-Bllossom-70B
|
| 19 |
+
- Full model released in Korean over 100GB by Blossom team
|
| 20 |
+
- First in Korean! Expansion of Korean vocabulary to over 30,000 words
|
| 21 |
+
- Capable of processing Korean context that is approximately 25% longer than Llama3
|
| 22 |
+
- Connecting Korean-English knowledge using the Korean-English Parallel Corpus (pre-study)
|
| 23 |
+
- Fine tuning using data produced by linguists considering Korean culture and language
|
| 24 |
+
- Reinforcement learning
|
| 25 |
+
|
| 26 |
+
About asiansoul/llama-3-Korean-Bllossom-120B-GGUF
|
| 27 |
+
- Q4_K_M : On a GPU with 68GB or more or a CPU with 68GB or more memory
|
| 28 |
+
```
|
| 29 |
+
|
| 30 |
### About this model
|
| 31 |
|
| 32 |
This is a 128B model based on [Bllossom/llama-3-Korean-Bllossom-70B](https://huggingface.co/Bllossom/llama-3-Korean-Bllossom-70B)
|