Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
tags:
|
6 |
+
- mamba-hf
|
7 |
+
---
|
8 |
+
|
9 |
+
# Mamba-3B
|
10 |
+
|
11 |
+
<img src="https://th.bing.com/th/id/OIG.Jp5dA01tOAFcwSp544nv?pid=ImgGn" width="300" height="300" alt="mamba-hf">
|
12 |
+
|
13 |
+
Mamba Models with hf_integration.
|
14 |
+
[**mamba-hf** Github Repo](https://github.com/LegallyCoder/mamba-hf)
|
15 |
+
|
16 |
+
# Usage:
|
17 |
+
|
18 |
+
```python
|
19 |
+
from transformers import AutoModelForCausalLM , AutoTokenizer
|
20 |
+
|
21 |
+
model = AutoModelForCausalLM.from_pretrained('Q-bert/Mamba-3B', trust_remote_code=True)
|
22 |
+
tokenizer = AutoTokenizer.from_pretrained('Q-bert/Mamba-3B')
|
23 |
+
|
24 |
+
text = "Hi"
|
25 |
+
|
26 |
+
input_ids = tokenizer.encode(text, return_tensors="pt")
|
27 |
+
|
28 |
+
output = model.generate(input_ids, max_length=20, num_beams=5, no_repeat_ngram_size=2)
|
29 |
+
|
30 |
+
generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
|
31 |
+
|
32 |
+
print(generated_text)
|
33 |
+
|
34 |
+
```
|
35 |
+
> Hi, I'm looking for a new job. I've been working at a company for about a year now.
|
36 |
+
|
37 |
+
# Credits:
|
38 |
+
|
39 |
+
https://huggingface.co/state-spaces
|
40 |
+
|
41 |
+
Special thanks to Albert Gu and Tri Dao for their articles. (https://arxiv.org/abs/2312.00752)
|
42 |
+
|