File size: 4,068 Bytes
a71c1d1 f15d0b0 a71c1d1 |
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 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 |
---
base_model:
- m-a-p/neo_7b
- m-a-p/neo_7b
tags:
- merge
- mergekit
- lazymergekit
- m-a-p/neo_7b
---
# Neo_7b-merge2
Neo_7b-merge2 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [m-a-p/neo_7b](https://huggingface.co/m-a-p/neo_7b)
* [m-a-p/neo_7b](https://huggingface.co/m-a-p/neo_7b)
## 🧩 Configuration
```yaml
slices:
# Group 1
- sources:
- model: m-a-p/neo_7b
layer_range: [0, 0]
- model: m-a-p/neo_7b
layer_range: [3, 3]
- sources:
- model: m-a-p/neo_7b
layer_range: [1, 1]
- model: m-a-p/neo_7b
layer_range: [3, 3]
- sources:
- model: m-a-p/neo_7b
layer_range: [2, 2]
- model: m-a-p/neo_7b
layer_range: [3, 3]
# Group 2
- sources:
- model: m-a-p/neo_7b
layer_range: [4, 4]
- model: m-a-p/neo_7b
layer_range: [7, 7]
- sources:
- model: m-a-p/neo_7b
layer_range: [5, 5]
- model: m-a-p/neo_7b
layer_range: [7, 7]
- sources:
- model: m-a-p/neo_7b
layer_range: [6, 6]
- model: m-a-p/neo_7b
layer_range: [7, 7]
# Group 3
- sources:
- model: m-a-p/neo_7b
layer_range: [8, 8]
- model: m-a-p/neo_7b
layer_range: [11, 11]
- sources:
- model: m-a-p/neo_7b
layer_range: [9, 9]
- model: m-a-p/neo_7b
layer_range: [11, 11]
- sources:
- model: m-a-p/neo_7b
layer_range: [10, 10]
- model: m-a-p/neo_7b
layer_range: [11, 11]
# Group 4
- sources:
- model: m-a-p/neo_7b
layer_range: [12, 12]
- model: m-a-p/neo_7b
layer_range: [15, 15]
- sources:
- model: m-a-p/neo_7b
layer_range: [13, 13]
- model: m-a-p/neo_7b
layer_range: [15, 15]
- sources:
- model: m-a-p/neo_7b
layer_range: [14, 14]
- model: m-a-p/neo_7b
layer_range: [15, 15]
# Group 5
- sources:
- model: m-a-p/neo_7b
layer_range: [16, 16]
- model: m-a-p/neo_7b
layer_range: [19, 19]
- sources:
- model: m-a-p/neo_7b
layer_range: [17, 17]
- model: m-a-p/neo_7b
layer_range: [19, 19]
- sources:
- model: m-a-p/neo_7b
layer_range: [18, 18]
- model: m-a-p/neo_7b
layer_range: [19, 19]
# Group 6
- sources:
- model: m-a-p/neo_7b
layer_range: [20, 20]
- model: m-a-p/neo_7b
layer_range: [23, 23]
- sources:
- model: m-a-p/neo_7b
layer_range: [21, 21]
- model: m-a-p/neo_7b
layer_range: [23, 23]
- sources:
- model: m-a-p/neo_7b
layer_range: [22, 22]
- model: m-a-p/neo_7b
layer_range: [23, 23]
# Group 7 (last group)
- sources:
- model: m-a-p/neo_7b
layer_range: [24, 24]
- model: m-a-p/neo_7b
layer_range: [27, 27]
- sources:
- model: m-a-p/neo_7b
layer_range: [25, 25]
- model: m-a-p/neo_7b
layer_range: [27, 27]
- sources:
- model: m-a-p/neo_7b
layer_range: [26, 26]
- model: m-a-p/neo_7b
layer_range: [27, 27]
merge_method: slerp
base_model: m-a-p/neo_7b
parameters:
t: 0.3333 # Apply 1/3 of the 4th layer to each of the previous 3 layers
dtype: bfloat16
output_path: ./merged_redistributed_neo_7b
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "DewEfresh/Neo_7b-merge2"
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"])
``` |