Update README.md
Browse files
README.md
CHANGED
@@ -13,6 +13,32 @@ tags:
|
|
13 |
quantized_by: Davidqian123
|
14 |
base_model: google/gemma-2-2b-it
|
15 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
# Quantized GGUF Models Benchmark
|
17 |
|
18 |
| Name | Quant method | Bits | Size | Use Cases |
|
@@ -35,27 +61,20 @@ base_model: google/gemma-2-2b-it
|
|
35 |
|
36 |
_Quantized with llama.cpp_
|
37 |
|
38 |
-
##
|
39 |
|
40 |
-
|
41 |
|
42 |
-
|
43 |
|
44 |
-
|
45 |
-
- 2 billion parameters
|
46 |
-
- Trained on 2 trillion tokens of web documents, code, and mathematics
|
47 |
-
- Suitable for edge devices and low-power compute
|
48 |
-
- Versatile for text generation, coding, and mathematical tasks
|
49 |
-
- Retains the large vocabulary from Gemma 1.1 for enhanced multilingual and coding capabilities
|
50 |
|
51 |
-
|
|
|
|
|
52 |
|
53 |
-
|
54 |
|
55 |
-
|
56 |
-
- Chatbots and conversational AI
|
57 |
-
- Text summarization
|
58 |
-
- Code generation
|
59 |
-
- Mathematical problem-solving
|
60 |
|
61 |
-
|
|
|
13 |
quantized_by: Davidqian123
|
14 |
base_model: google/gemma-2-2b-it
|
15 |
---
|
16 |
+
|
17 |
+
## Gemma-2-2b-Instruct-GGUF Introduction
|
18 |
+
|
19 |
+
Gemma 2 Instruct is the latest addition to Google's Gemma family of lightweight, state-of-the-art open models. Built on Gemini technology, this 2 billion parameter model excels at various text generation tasks while being compact enough for edge and low-power computing environments.
|
20 |
+
|
21 |
+
## Key Features
|
22 |
+
|
23 |
+
- Based on Gemini technology
|
24 |
+
- 2 billion parameters
|
25 |
+
- Trained on 2 trillion tokens of web documents, code, and mathematics
|
26 |
+
- Suitable for edge devices and low-power compute
|
27 |
+
- Versatile for text generation, coding, and mathematical tasks
|
28 |
+
- Retains the large vocabulary from Gemma 1.1 for enhanced multilingual and coding capabilities
|
29 |
+
|
30 |
+
## Applications
|
31 |
+
|
32 |
+
Gemma 2 Instruct is designed for a wide range of applications, including:
|
33 |
+
|
34 |
+
- Content creation
|
35 |
+
- Chatbots and conversational AI
|
36 |
+
- Text summarization
|
37 |
+
- Code generation
|
38 |
+
- Mathematical problem-solving
|
39 |
+
|
40 |
+
For more details check out their blog post here: https://developers.googleblog.com/en/smaller-safer-more-transparent-advancing-responsible-ai-with-gemma/
|
41 |
+
|
42 |
# Quantized GGUF Models Benchmark
|
43 |
|
44 |
| Name | Quant method | Bits | Size | Use Cases |
|
|
|
61 |
|
62 |
_Quantized with llama.cpp_
|
63 |
|
64 |
+
## Invitation to join our beta test to accelerate your on-device AI development
|
65 |
|
66 |
+
We're excited to invite you to join our beta test for a new platform designed to enhance on-device AI development.
|
67 |
|
68 |
+
By participating, you'll have the opportunity to connect with fellow developers and researchers and contribute to the open-source future of on-device AI.
|
69 |
|
70 |
+
Here's how you can get involved:
|
|
|
|
|
|
|
|
|
|
|
71 |
|
72 |
+
1. Sign an NDA.
|
73 |
+
2. Receive a link to our beta testing community on Discord.
|
74 |
+
3. Join a brief 15-minute online chat to share your valuable feedback.
|
75 |
|
76 |
+
### Beta Test Sign-Up
|
77 |
|
78 |
+
Sign up using this Link: **https://forms.gle/vuoktPjPmotnT4sM7**
|
|
|
|
|
|
|
|
|
79 |
|
80 |
+
Your insights are invaluable to us as we build this platform together.
|