Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: other
|
4 |
+
license_name: gemma-terms-of-use
|
5 |
+
license_link: https://ai.google.dev/gemma/terms
|
6 |
+
tags:
|
7 |
+
- mlx
|
8 |
+
- mlx
|
9 |
+
widget:
|
10 |
+
- text: '<start_of_turn>user
|
11 |
+
|
12 |
+
How does the brain work?<end_of_turn>
|
13 |
+
|
14 |
+
<start_of_turn>model
|
15 |
+
|
16 |
+
'
|
17 |
+
inference:
|
18 |
+
parameters:
|
19 |
+
max_new_tokens: 200
|
20 |
+
extra_gated_heading: Access Gemma on Hugging Face
|
21 |
+
extra_gated_prompt: To access Gemma on Hugging Face, you’re required to review and
|
22 |
+
agree to Google’s usage license. To do this, please ensure you’re logged-in to Hugging
|
23 |
+
Face and click below. Requests are processed immediately.
|
24 |
+
extra_gated_button_content: Acknowledge license
|
25 |
+
---
|
26 |
+
|
27 |
+
# david4096/gemma-2b-finetune-graph-genome
|
28 |
+
|
29 |
+
The Model [david4096/gemma-2b-finetune-graph-genome](https://huggingface.co/david4096/gemma-2b-finetune-graph-genome) was converted to MLX format from [mlx-community/quantized-gemma-2b-it](https://huggingface.co/mlx-community/quantized-gemma-2b-it) using mlx-lm version **0.16.0**.
|
30 |
+
|
31 |
+
It was trained on text from about 180 papers with the phrase "graph genome" in them from biorxiv.
|
32 |
+
|
33 |
+
## Use with mlx
|
34 |
+
|
35 |
+
```bash
|
36 |
+
pip install mlx-lm
|
37 |
+
```
|
38 |
+
|
39 |
+
```python
|
40 |
+
from mlx_lm import load, generate
|
41 |
+
|
42 |
+
model, tokenizer = load("david4096/gemma-2b-finetune-graph-genome")
|
43 |
+
response = generate(model, tokenizer, prompt="hello", verbose=True)
|
44 |
+
```
|