DominaTrix-7B-v2 / README.md
CultriX's picture
Upload folder using huggingface_hub
942d931 verified
---
tags:
- merge
- mergekit
- lazymergekit
- CultriX/MonaTrix-v4
- bardsai/jaskier-7b-dpo-v5.6
- eren23/ogno-monarch-jaskier-merge-7b
base_model:
- CultriX/MonaTrix-v4
- bardsai/jaskier-7b-dpo-v5.6
- eren23/ogno-monarch-jaskier-merge-7b
---
# DominaTrix-7B-v2
DominaTrix-7B-v2 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [CultriX/MonaTrix-v4](https://huggingface.co/CultriX/MonaTrix-v4)
* [bardsai/jaskier-7b-dpo-v5.6](https://huggingface.co/bardsai/jaskier-7b-dpo-v5.6)
* [eren23/ogno-monarch-jaskier-merge-7b](https://huggingface.co/eren23/ogno-monarch-jaskier-merge-7b)
## 🧩 Configuration
```yaml
models:
- model: mistralai/Mistral-7B-Instruct-v0.2
# No parameters necessary for base model
- model: CultriX/MonaTrix-v4
#Emphasize the beginning of Vicuna format models
parameters:
weight: 0.36
density: 0.65
- model: bardsai/jaskier-7b-dpo-v5.6
parameters:
weight: 0.34
density: 0.6
# Vicuna format
- model: eren23/ogno-monarch-jaskier-merge-7b
parameters:
weight: 0.3
density: 0.6
merge_method: dare_ties
base_model: mistralai/Mistral-7B-Instruct-v0.2
parameters:
int8_mask: true
dtype: bfloat16
random_seed: 0
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "CultriX/DominaTrix-7B-v2"
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"])
```