CultriX's picture
Update README.md
a406c71 verified
---
tags:
- merge
- mergekit
- lazymergekit
- PetroGPT/WestSeverus-7B-DPO
- CultriX/MergeTrix-7B-v2
- mlabonne/NeuralBeagle14-7B
base_model:
- PetroGPT/WestSeverus-7B-DPO
- CultriX/MergeTrix-7B-v2
- mlabonne/NeuralBeagle14-7B
license: apache-2.0
---
# EDIT:
Always check my space for the latest benchmark results for my models!
* https://huggingface.co/spaces/CultriX/Yet_Another_LLM_Leaderboard
# SevereNeuralBeagleTrix-7B
SevereNeuralBeagleTrix-7B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [PetroGPT/WestSeverus-7B-DPO](https://huggingface.co/PetroGPT/WestSeverus-7B-DPO)
* [CultriX/MergeTrix-7B-v2](https://huggingface.co/CultriX/MergeTrix-7B-v2)
* [mlabonne/NeuralBeagle14-7B](https://huggingface.co/mlabonne/NeuralBeagle14-7B)
## 🧩 Configuration
```yaml
models:
- model: mistralai/Mistral-7B-v0.1
# No parameters necessary for base model
- model: PetroGPT/WestSeverus-7B-DPO
parameters:
density: 0.53
weight: 0.3
- model: CultriX/MergeTrix-7B-v2
parameters:
density: 0.53
weight: 0.4
- model: mlabonne/NeuralBeagle14-7B
parameters:
density: 0.53
weight: 0.3
merge_method: dare_ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
int8_mask: true
dtype: float16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "CultriX/SevereNeuralBeagleTrix-7B"
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"])
```