File size: 1,437 Bytes
7e250cd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: [0.7079805582767552, 0.4027623376589091, 0.5324831706531206, 0.3871687404251074, 0.772048887948157]
    - filter: mlp
      value: [0.2920194417232448, 0.5972376623410909, 0.6128312595748926, 0.6128312595748926, 0.22795111205184304]
    - value: 0.08955691661940723
dtype: bfloat16
random_seed: 0
    ```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "aaron-di/Yamshadowexperiment28M70.71-0.4-0.53-0.39-0.77-0.09-7B"
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"])
```