---
license: apache-2.0
language:
- en
---

![image/png](https://cdn-uploads.huggingface.co/production/uploads/6589d7e6586088fd2784a12c/IclpTHDxA6a7xc7TZ5vth.png)

# Made using Cultrix's Model, which can be found [here](https://huggingface.co/CultriX/NeuralTrix-7B-dpo).
[Join our Discord!](https://discord.gg/ZgU79QDnE2)

[BASE MODEL HERE](https://huggingface.co/Kquant03/NeuralTrix-7B-dpo-laser)

NeuralTrix-7B-v1 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [mlabonne/OmniBeagle-7B](https://huggingface.co/mlabonne/OmniBeagle-7B)
* [flemmingmiguel/MBX-7B-v3](https://huggingface.co/flemmingmiguel/MBX-7B-v3)
* [AiMavenAi/AiMaven-Prometheus](https://huggingface.co/AiMavenAi/AiMaven-Prometheus)

It was then trained with DPO by Cultrix using: 
* https://huggingface.co/datasets/jondurbin/truthy-dpo-v0.1

I performed laser_snr_math on it afterwards to see if I could improve it.

## 🧩 Configuration

```yaml
models:
  - model: mistralai/Mistral-7B-v0.1
    # no parameters necessary for base model
  - model: mlabonne/OmniBeagle-7B
    parameters:
      density: 0.65
      weight: 0.4
  - model: flemmingmiguel/MBX-7B-v3
    parameters:
      density: 0.6
      weight: 0.35
  - model: AiMavenAi/AiMaven-Prometheus
    parameters:
      density: 0.6
      weight: 0.35
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/NeuralTrix-7B-v1"
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"])
```