Commit
•
7240cb0
1
Parent(s):
e839a59
Update README.md
Browse files
README.md
CHANGED
|
@@ -16,6 +16,8 @@ GGUF quantized version using llama.cpp
|
|
| 16 |
|
| 17 |
Only BF16, Q8_0 and Q6 as it's a really small model already. If someone needs a smaller quant please open a discussion
|
| 18 |
|
|
|
|
|
|
|
| 19 |
# Gemma 2 model card
|
| 20 |
|
| 21 |
**Model Page**: [Gemma](https://ai.google.dev/gemma/docs/base)
|
|
|
|
| 16 |
|
| 17 |
Only BF16, Q8_0 and Q6 as it's a really small model already. If someone needs a smaller quant please open a discussion
|
| 18 |
|
| 19 |
+
Original model [google/gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it)
|
| 20 |
+
|
| 21 |
# Gemma 2 model card
|
| 22 |
|
| 23 |
**Model Page**: [Gemma](https://ai.google.dev/gemma/docs/base)
|