kim512's picture
Upload folder using huggingface_hub
3a6621d verified
---
tags:
- merge
- mergekit
- lazymergekit
- OmnicromsBrain/StoryFusion-7B
- jdqwoi/TooManyMixRolePlay-7B
base_model:
- OmnicromsBrain/StoryFusion-7B
- jdqwoi/TooManyMixRolePlay-7B
---
# EXL2 quants of [jdqwoi/TooManyMixRolePlay-7B-Story](https://huggingface.co/jdqwoi/TooManyMixRolePlay-7B-Story)
[4.00 bits per weight](https://huggingface.co/kim512/TooManyMixRolePlay-7B-Story-4.0bpw-exl2)
[5.00 bits per weight](https://huggingface.co/kim512/TooManyMixRolePlay-7B-Story-5.0bpw-exl2)
[6.00 bits per weight](https://huggingface.co/kim512/TooManyMixRolePlay-7B-Story-6.0bpw-exl2)
[7.00 bits per weight](https://huggingface.co/kim512/TooManyMixRolePlay-7B-Story-7.0bpw-exl2)
[8.00 bits per weight](https://huggingface.co/kim512/TooManyMixRolePlay-7B-Story-8.0bpw-exl2)
# TooManyMixRolePlay-7B-Story
TooManyMixRolePlay-7B-Story is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [OmnicromsBrain/StoryFusion-7B](https://huggingface.co/OmnicromsBrain/StoryFusion-7B)
* [jdqwoi/TooManyMixRolePlay-7B](https://huggingface.co/jdqwoi/TooManyMixRolePlay-7B)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: OmnicromsBrain/StoryFusion-7B
layer_range: [0, 32]
- model: jdqwoi/TooManyMixRolePlay-7B
layer_range: [0, 32]
merge_method: slerp
base_model: OmnicromsBrain/StoryFusion-7B
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 = "jdqwoi/TooManyMixRolePlay-7B-Story"
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"])
```