File size: 1,686 Bytes
ead693d 0a45191 a2f21e9 ead693d |
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 |
---
tags:
- merge
- mergekit
- lazymergekit
- google-bert/bert-base-uncased
- KM4STfulltext/SSCI-SciBERT-e4
base_model:
- google-bert/bert-base-uncased
- KM4STfulltext/SSCI-SciBERT-e4
license: apache-2.0
pipeline_tag: depth-estimation
---
# test_merge7_
test_merge7_ is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased)
* [KM4STfulltext/SSCI-SciBERT-e4](https://huggingface.co/KM4STfulltext/SSCI-SciBERT-e4)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: google-bert/bert-base-uncased
layer_range: [0, 32]
- model: KM4STfulltext/SSCI-SciBERT-e4
layer_range: [0, 32]
merge_method: slerp
base_model: google-bert/bert-base-uncased
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "nagayama0706/test_merge7_"
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"])
``` |