|
--- |
|
base_model: mobiuslabsgmbh/aanaphi2-v0.1 |
|
license: mit |
|
train: false |
|
inference: false |
|
language: |
|
- en |
|
model_creator: mobiuslabsgmbh |
|
model_name: aanaphi2-v0.1 |
|
model_type: phi |
|
pipeline_tag: text-generation |
|
quantized_by: brittlewis12 |
|
--- |
|
|
|
 |
|
|
|
# aanaphi2-v0.1 GGUF |
|
|
|
**Original model**: [aanaphi2-v0.1](https://huggingface.co/mobiuslabsgmbh/aanaphi2-v0.1) |
|
|
|
**Model creator**: [mobiuslabsgmbh](https://huggingface.co/mobiuslabsgmbh) |
|
|
|
This repo contains GGUF format model files for Mobius Labs’ aanaphi2-v0.1. |
|
|
|
> aanaphi2-v0.1 is a finetuned (SFT + DPO) chat model based on [Microsoft's Phi-2 base model](https://huggingface.co/microsoft/phi-2) (2.8B parameters). |
|
|
|
### What is GGUF? |
|
|
|
GGUF is a file format for representing AI models. It is the third version of the format, introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. |
|
Converted using llama.cpp build 2276 (revision [b11a93d](https://github.com/ggerganov/llama.cpp/commit/b11a93df41921846a10628a7c306d5c82a549939)) |
|
|
|
### Prompt template |
|
|
|
``` |
|
### Human: {{prompt}} |
|
### Assistant: |
|
``` |
|
|
|
--- |
|
|
|
## Download & run with [cnvrs](https://twitter.com/cnvrsai) on iPhone, iPad, and Mac! |
|
|
|
 |
|
|
|
[cnvrs](https://testflight.apple.com/join/sFWReS7K) is the best app for private, local AI on your device: |
|
- create & save **Characters** with custom system prompts & temperature settings |
|
- download and experiment with any **GGUF model** you can [find on HuggingFace](https://huggingface.co/models?library=gguf)! |
|
- make it your own with custom **Theme colors** |
|
- powered by Metal ⚡️ & [Llama.cpp](https://github.com/ggerganov/llama.cpp), with **haptics** during response streaming! |
|
- **try it out** yourself today, on [Testflight](https://testflight.apple.com/join/sFWReS7K)! |
|
- follow [cnvrs on twitter](https://twitter.com/cnvrsai) to stay up to date |
|
|
|
--- |
|
|
|
## Original Model Evaluation |
|
|
|
| Models | phi-2 | aanaphi2-v0.1 | |
|
|-------------------|------------------|------------------| |
|
| ARC (25-shot) | 61.09 | <b>63.74</b> | |
|
| HellaSwag (10-shot)| 75.11 | <b>78.30</b> | |
|
| MMLU (5-shot) | <b>58.11</b> | 57.70 | |
|
| TruthfulQA-MC2 | 44.47 | <b>51.56</b> | |
|
| Winogrande (5-shot)| <b>74.35</b> | 73.40 | |
|
| GSM8K (5-shot) | 54.81 | <b>58.61</b> | |
|
| Average | 61.33 | <b>63.89</b> | |
|
|
