File size: 1,440 Bytes
54f39f2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- automerger
base_model:
- liminerity/M7-7b
- AurelPx/Percival_01-7b-slerp
---

## 🧩 Configuration
```yaml
slices:
  - sources:
      - model: liminerity/M7-7b
        layer_range: [0, 32]
      - model: AurelPx/Percival_01-7b-slerp
        layer_range: [0, 32]
merge_method: slerp
base_model: liminerity/M7-7b
parameters:
  t:
    - filter: self_attn
      value: [0.2236609428446562, 0.7745314871737711, 0.5239172244275849, 0.8690735271195046, 0.4129909450097137]
    - filter: mlp
      value: [0.7763390571553438, 0.22546851282622893, 0.4760827755724151, 0.13092647288049541, 0.5870090549902863]
    - value: 0.01387971344725658
dtype: bfloat16
random_seed: 0
    ```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "aaron-di/Yamshadowexperiment28M70.22-0.77-0.52-0.87-0.41-0.01-7B"
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"])
```