Update README.md
Browse files
README.md
CHANGED
|
@@ -31,10 +31,6 @@ base_model: google/gemma-2-2b-it
|
|
| 31 |
**Original model**: [gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it)<br>
|
| 32 |
**GGUF quantization:** provided by [bartowski](https://huggingface.co/bartowski) based on `llama.cpp` release [b3496](https://github.com/ggerganov/llama.cpp/releases/tag/b3496)<br>
|
| 33 |
|
| 34 |
-
## Model Settings:
|
| 35 |
-
|
| 36 |
-
Requires LM Studio 0.2.27, update can be downloaded from here: https://lmstudio.ai
|
| 37 |
-
|
| 38 |
## Model Summary:
|
| 39 |
Gemma 2 instruct is a a brand new model from Google in the Gemma family based on the technology from Gemini. Trained on a combination of web documents, code, and mathematics, this model should excel at anything you throw at it.<br>
|
| 40 |
At only 2b parameters, this is a great size for edge and low power compute, or as an autocomplete or draft model.
|
|
|
|
| 31 |
**Original model**: [gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it)<br>
|
| 32 |
**GGUF quantization:** provided by [bartowski](https://huggingface.co/bartowski) based on `llama.cpp` release [b3496](https://github.com/ggerganov/llama.cpp/releases/tag/b3496)<br>
|
| 33 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
## Model Summary:
|
| 35 |
Gemma 2 instruct is a a brand new model from Google in the Gemma family based on the technology from Gemini. Trained on a combination of web documents, code, and mathematics, this model should excel at anything you throw at it.<br>
|
| 36 |
At only 2b parameters, this is a great size for edge and low power compute, or as an autocomplete or draft model.
|