Update README.md
Browse files
README.md
CHANGED
|
@@ -10,9 +10,9 @@ tags:
|
|
| 10 |
---
|
| 11 |
|
| 12 |
# 🐮cow architecture gguf encoder
|
| 13 |
-
- don't need to rebuild tokenizer from metadata
|
| 14 |
-
- don't need separate tokenizer file
|
| 15 |
-
- no more oom issues (possibly)
|
| 16 |
|
| 17 |
## eligible model example
|
| 18 |
- use **cow-gemma2** [2.33GB](https://huggingface.co/calcuis/cow-encoder/blob/main/cow-gemma2-2b-q4_0.gguf) for [lumina](https://huggingface.co/calcuis/lumina-gguf)
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
# 🐮cow architecture gguf encoder
|
| 13 |
+
- don't need to rebuild tokenizer from metadata 🥊⏳
|
| 14 |
+
- don't need separate tokenizer file 🥊🐱
|
| 15 |
+
- no more oom issues (possibly) 🥊💻💫
|
| 16 |
|
| 17 |
## eligible model example
|
| 18 |
- use **cow-gemma2** [2.33GB](https://huggingface.co/calcuis/cow-encoder/blob/main/cow-gemma2-2b-q4_0.gguf) for [lumina](https://huggingface.co/calcuis/lumina-gguf)
|