File size: 1,563 Bytes
c7e14d5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
---
base_model:
- Quazim0t0/time-14b-stock
- Quazim0t0/Mithril-14B-sce
tags:
- merge
- mergekit
- lazymergekit
- Quazim0t0/time-14b-stock
- Quazim0t0/Mithril-14B-sce
---

# Rosemary-14b

Rosemary-14b is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Quazim0t0/time-14b-stock](https://huggingface.co/Quazim0t0/time-14b-stock)
* [Quazim0t0/Mithril-14B-sce](https://huggingface.co/Quazim0t0/Mithril-14B-sce)

## 🧩 Configuration

```yaml
base_model: Quazim0t0/time-14b-stock
dtype: bfloat16
merge_method: slerp
parameters:
  t:
  - filter: self_attn
    value: [0.0, 0.5, 0.3, 0.7, 1.0]
  - filter: mlp
    value: [1.0, 0.5, 0.7, 0.3, 0.0]
  - value: 0.5
slices:
- sources:
  - layer_range: [0, 40]
    model: Quazim0t0/time-14b-stock
  - layer_range: [0, 40]
    model: Quazim0t0/Mithril-14B-sce

```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Quazim0t0/Rosemary-14b"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```