allknowingroger
commited on
Commit
•
4674c03
1
Parent(s):
9bc6eeb
Delete README.md
Browse files
README.md
DELETED
@@ -1,63 +0,0 @@
|
|
1 |
-
---
|
2 |
-
tags:
|
3 |
-
- merge
|
4 |
-
- mergekit
|
5 |
-
- lazymergekit
|
6 |
-
- chihoonlee10/T3-Mistral-Orca-Math-DPO
|
7 |
-
- allknowingroger/Weystacks-2.5-7B-Slerp
|
8 |
-
base_model:
|
9 |
-
- chihoonlee10/T3-Mistral-Orca-Math-DPO
|
10 |
-
- allknowingroger/Weystacks-2.5-7B-Slerp
|
11 |
-
---
|
12 |
-
|
13 |
-
# Rogerlee-2.5-7B-slerp
|
14 |
-
|
15 |
-
Rogerlee-2.5-7B-slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
16 |
-
* [chihoonlee10/T3-Mistral-Orca-Math-DPO](https://huggingface.co/chihoonlee10/T3-Mistral-Orca-Math-DPO)
|
17 |
-
* [allknowingroger/Weystacks-2.5-7B-Slerp](https://huggingface.co/allknowingroger/Weystacks-2.5-7B-Slerp)
|
18 |
-
|
19 |
-
## 🧩 Configuration
|
20 |
-
|
21 |
-
```yaml
|
22 |
-
slices:
|
23 |
-
- sources:
|
24 |
-
- model: chihoonlee10/T3-Mistral-Orca-Math-DPO
|
25 |
-
layer_range: [0, 32]
|
26 |
-
- model: allknowingroger/Weystacks-2.5-7B-Slerp
|
27 |
-
layer_range: [0, 32]
|
28 |
-
merge_method: slerp
|
29 |
-
base_model: OpenPipe/mistral-ft-optimized-1218
|
30 |
-
parameters:
|
31 |
-
t:
|
32 |
-
- filter: self_attn
|
33 |
-
value: [0, 0.5, 0.3, 0.7, 1]
|
34 |
-
- filter: mlp
|
35 |
-
value: [1, 0.5, 0.7, 0.3, 0]
|
36 |
-
- value: 0.5
|
37 |
-
dtype: bfloat16
|
38 |
-
```
|
39 |
-
|
40 |
-
## 💻 Usage
|
41 |
-
|
42 |
-
```python
|
43 |
-
!pip install -qU transformers accelerate
|
44 |
-
|
45 |
-
from transformers import AutoTokenizer
|
46 |
-
import transformers
|
47 |
-
import torch
|
48 |
-
|
49 |
-
model = "allknowingroger/Rogerlee-2.5-7B-slerp"
|
50 |
-
messages = [{"role": "user", "content": "What is a large language model?"}]
|
51 |
-
|
52 |
-
tokenizer = AutoTokenizer.from_pretrained(model)
|
53 |
-
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
54 |
-
pipeline = transformers.pipeline(
|
55 |
-
"text-generation",
|
56 |
-
model=model,
|
57 |
-
torch_dtype=torch.float16,
|
58 |
-
device_map="auto",
|
59 |
-
)
|
60 |
-
|
61 |
-
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
62 |
-
print(outputs[0]["generated_text"])
|
63 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|