|
--- |
|
license: cc-by-nc-4.0 |
|
tags: |
|
- merge |
|
- lazymergekit |
|
dataset: |
|
- mlabonne/truthy-dpo-v0.1 |
|
- mlabonne/distilabel-intel-orca-dpo-pairs |
|
base_model: |
|
- mlabonne/Monarch-7B |
|
language: |
|
- en |
|
--- |
|
|
|
 |
|
|
|
# 👑 NeuralMonarch-7B |
|
|
|
NeuralMonarch-7B is a DPO fine-tuned of [mlabonne/Monarch-7B](https://huggingface.co/mlabonne/Monarch-7B/) using the [jondurbin/truthy-dpo-v0.1](https://huggingface.co/datasets/jondurbin/truthy-dpo-v0.1) and [argilla/distilabel-intel-orca-dpo-pairs](https://huggingface.co/datasets/argilla/distilabel-intel-orca-dpo-pairs) preference datasets. |
|
|
|
It is based on a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing): |
|
* [mlabonne/OmniTruthyBeagle-7B-v0](https://huggingface.co/mlabonne/OmniTruthyBeagle-7B-v0) |
|
* [mlabonne/NeuBeagle-7B](https://huggingface.co/mlabonne/NeuBeagle-7B) |
|
* [mlabonne/NeuralOmniBeagle-7B](https://huggingface.co/mlabonne/NeuralOmniBeagle-7B) |
|
|
|
Special thanks to [Jon Durbin](https://huggingface.co/jondurbin), [Intel](https://huggingface.co/Intel), and [Argilla](https://huggingface.co/argilla) for the preference datasets. |
|
|
|
## 🔍 Applications |
|
|
|
This model uses a context window of 8k. It is compatible with different templates, like chatml, Llama's and Mistral's chat templates. |
|
|
|
Compared to other 7B models, it displays good performance in instruction following and reasoning tasks. It can also be used for RP and storytelling. |
|
|
|
## ⚡ Quantized models |
|
|
|
* **GGUF**: TBD |
|
|
|
## 🏆 Evaluation |
|
|
|
The evaluation was performed using [LLM AutoEval](https://github.com/mlabonne/llm-autoeval) on Nous suite. See the entire leaderboard [here](https://huggingface.co/spaces/mlabonne/Yet_Another_LLM_Leaderboard). |
|
|
|
| Model | Average | AGIEval | GPT4All | TruthfulQA | Bigbench | |
|
|---|---:|---:|---:|---:|---:| |
|
| [Monarch-7B](https://huggingface.co/mlabonne/Monarch-7B) [📄](https://gist.github.com/mlabonne/0b8d057c5ece41e0290580a108c7a093) | 62.68 | 45.48 | 77.07 | 78.04 | 50.14 | |
|
| [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) [📄](https://gist.github.com/mlabonne/88b21dd9698ffed75d6163ebdc2f6cc8) | 52.42 | 42.75 | 72.99 | 52.99 | 40.94 | |
|
| [mlabonne/NeuralHermes-2.5-Mistral-7B](https://huggingface.co/mlabonne/NeuralHermes-2.5-Mistral-7B) [📄](https://gist.github.com/mlabonne/14687f1eb3425b166db511f31f8e66f6) | 53.51 | 43.67 | 73.24 | 55.37 | 41.76 | |
|
| [mlabonne/NeuralBeagle14-7B](https://huggingface.co/mlabonne/NeuralBeagle14-7B) [📄](https://gist.github.com/mlabonne/ad0c665bbe581c8420136c3b52b3c15c) | 60.25 | 46.06 | 76.77 | 70.32 | 47.86 | |
|
| [eren23/dpo-binarized-NeuralTrix-7B](https://huggingface.co/eren23/dpo-binarized-NeuralTrix-7B) [📄](https://gist.github.com/CultriX-Github/dbdde67ead233df0c7c56f1b091f728c) | 62.5 | 44.57 | 76.34 | 79.81 | 49.27 | |
|
| [CultriX/NeuralTrix-7B-dpo](https://huggingface.co/CultriX/NeuralTrix-7B-dpo) [📄](https://gist.github.com/CultriX-Github/df0502599867d4043b45d9dafb5976e8) | 62.5 | 44.61 | 76.33 | 79.8 | 49.24 | |
|
|
|
## 💻 Usage |
|
|
|
```python |
|
!pip install -qU transformers accelerate |
|
|
|
from transformers import AutoTokenizer |
|
import transformers |
|
import torch |
|
|
|
model = "mlabonne/NeuralMonarch-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"]) |
|
``` |
