ThomasBaruzier
commited on
Commit
•
b3d175c
1
Parent(s):
e1c8ae5
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,58 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: llama.cpp
|
3 |
+
license: gemma
|
4 |
+
widget:
|
5 |
+
- text: '<start_of_turn>user
|
6 |
+
|
7 |
+
How does the brain work?<end_of_turn>
|
8 |
+
|
9 |
+
<start_of_turn>model
|
10 |
+
|
11 |
+
'
|
12 |
+
inference:
|
13 |
+
parameters:
|
14 |
+
max_new_tokens: 200
|
15 |
+
extra_gated_heading: Access Gemma on Hugging Face
|
16 |
+
extra_gated_prompt: To access Gemma on Hugging Face, you’re required to review and
|
17 |
+
agree to Google’s usage license. To do this, please ensure you’re logged-in to Hugging
|
18 |
+
Face and click below. Requests are processed immediately.
|
19 |
+
extra_gated_button_content: Acknowledge license
|
20 |
+
---
|
21 |
+
|
22 |
+
# Gemma Model Card
|
23 |
+
|
24 |
+
**Model Page**: [Gemma](https://ai.google.dev/gemma/docs)
|
25 |
+
|
26 |
+
This model card corresponds to the 2b instruct version the Gemma 2 model in GGUF Format. The weights here are **float32**.
|
27 |
+
|
28 |
+
> [!IMPORTANT]
|
29 |
+
>
|
30 |
+
> In llama.cpp, and other related tools such as Ollama and LM Studio, please make sure that you have these flags set correctly, especially **`repeat-penalty`**. Georgi Gerganov (llama.cpp's author) shared his experience in https://huggingface.co/google/gemma-2b-it/discussions/38#65d2b14adb51f7c160769fa1.
|
31 |
+
|
32 |
+
You can also visit the model card of the [2B pretrained v2 model GGUF](https://huggingface.co/google/gemma-2b-v2-GGUF).
|
33 |
+
|
34 |
+
**Resources and Technical Documentation**:
|
35 |
+
|
36 |
+
* [Responsible Generative AI Toolkit](https://ai.google.dev/responsible)
|
37 |
+
* [Gemma on Kaggle](https://www.kaggle.com/models/google/gemma)
|
38 |
+
* [Gemma on Vertex Model Garden](https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/335?version=gemma-2b-it-gg-hf)
|
39 |
+
|
40 |
+
**Terms of Use**: [Terms](https://www.kaggle.com/models/google/gemma/license/consent/verify/huggingface?returnModelRepoId=google/gemma-2-2b-it-GGUF)
|
41 |
+
|
42 |
+
**Authors**: Google
|
43 |
+
|
44 |
+
## Model Information
|
45 |
+
|
46 |
+
Summary description and brief definition of inputs and outputs.
|
47 |
+
|
48 |
+
### Description
|
49 |
+
|
50 |
+
Gemma is a family of lightweight, state-of-the-art open models from Google,
|
51 |
+
built from the same research and technology used to create the Gemini models.
|
52 |
+
They are text-to-text, decoder-only large language models, available in English,
|
53 |
+
with open weights, pre-trained variants, and instruction-tuned variants. Gemma
|
54 |
+
models are well-suited for a variety of text generation tasks, including
|
55 |
+
question answering, summarization, and reasoning. Their relatively small size
|
56 |
+
makes it possible to deploy them in environments with limited resources such as
|
57 |
+
a laptop, desktop or your own cloud infrastructure, democratizing access to
|
58 |
+
state of the art AI models and helping foster innovation for everyone.
|