README.md

---
tags:
- merge
- mergekit
- lazymergekit
- jdqwoi/TooManyMixRolePlay-7B-Story_V2
- jdqwoi/TooManyMixRolePlay-7B-Story_V3
base_model:
- jdqwoi/TooManyMixRolePlay-7B-Story_V2
- jdqwoi/TooManyMixRolePlay-7B-Story_V3
---


# EXL2 quants of [jdqwoi/TooManyMixRolePlay-7B-Story_V3.5](https://huggingface.co./jdqwoi/TooManyMixRolePlay-7B-Story_V3.5)

[6.00 bits per weight](https://huggingface.co./kim512/TooManyMixRolePlay-7B-Story_V3.5-6.0bpw-h6-exl2)  
[8.00 bits per weight](https://huggingface.co./kim512/TooManyMixRolePlay-7B-Story_V3.5-8.0bpw-h8-exl2)  

Created using the defaults from exllamav2 0.1.3 convert.py  
6.0bpw head bits = 6  
8.0bpw head bits = 8  
length = 8192  
dataset rows = 200  
measurement rows = 32  
measurement length = 8192  

# TooManyMixRolePlay-7B-Story_V3.5

TooManyMixRolePlay-7B-Story_V3.5 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [jdqwoi/TooManyMixRolePlay-7B-Story_V2](https://huggingface.co./jdqwoi/TooManyMixRolePlay-7B-Story_V2)
* [jdqwoi/TooManyMixRolePlay-7B-Story_V3](https://huggingface.co./jdqwoi/TooManyMixRolePlay-7B-Story_V3)

## 🧩 Configuration

```yaml
slices:
  - sources:
      - model: jdqwoi/TooManyMixRolePlay-7B-Story_V2
        layer_range: [0, 32]
      - model: jdqwoi/TooManyMixRolePlay-7B-Story_V3
        layer_range: [0, 32]
merge_method: slerp
base_model: jdqwoi/TooManyMixRolePlay-7B-Story_V2
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_V3.5"
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"])
```