Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
|
| 5 |
+
- en
|
| 6 |
+
---
|
| 7 |
+
<!-- header start -->
|
| 8 |
+
<!-- 200823 -->
|
| 9 |
+
|
| 10 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
| 11 |
+
<img src="https://github.com/janhq/jan/assets/89722390/35daac7d-b895-487c-a6ac-6663daaad78e" alt="Jan banner" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
| 12 |
+
</div>
|
| 13 |
+
|
| 14 |
+
<p align="center">
|
| 15 |
+
<a href="https://jan.ai/">Jan</a>
|
| 16 |
+
- <a href="https://discord.gg/AsJ8krTT3N">Discord</a>
|
| 17 |
+
</p>
|
| 18 |
+
<!-- header end -->
|
| 19 |
+
|
| 20 |
+
# Model Description
|
| 21 |
+
This is a highly experimental model for merging models into a MOE model.
|
| 22 |
+
- base model: [trinity-v1](https://huggingface.co/janhq/trinity-v1)
|
| 23 |
+
1. [trinity-v1](https://huggingface.co/janhq/trinity-v1): for General Chat
|
| 24 |
+
2. [Toppy-M-7B](https://huggingface.co/Undi95/Toppy-M-7B): for Role-playing
|
| 25 |
+
3. [CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf): for Coding
|
| 26 |
+
4. [Seraph-7B](https://huggingface.co/Weyaxi/Seraph-7B): for Writing
|
| 27 |
+
|
| 28 |
+
Special thanks to the interested work of [Chargoddard](https://huggingface.co/chargoddard) and [Undi95](https://huggingface.co/Undi95)
|
| 29 |
+
|
| 30 |
+
```yaml
|
| 31 |
+
Updating
|
| 32 |
+
```
|
| 33 |
+
|
| 34 |
+
# Run this model
|
| 35 |
+
You can run this model using [Jan Desktop](https://jan.ai/) on Mac, Windows, or Linux.
|
| 36 |
+
|
| 37 |
+
Jan is an open source, ChatGPT alternative that is:
|
| 38 |
+
|
| 39 |
+
- 💻 **100% offline on your machine**
|
| 40 |
+
: Your conversations remain confidential, and visible only to you.
|
| 41 |
+
- 🗂️ **An Open File Format**: Conversations and model settings stay on your computer and can be exported or deleted at any time.
|
| 42 |
+
- 🌐 **OpenAI Compatible**: Local server on port `1337` with OpenAI compatible endpoints
|
| 43 |
+
- 🌍 **Open Source & Free**: We build in public; check out our [Github](https://github.com/janhq)
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
# About Jan
|
| 48 |
+
Jan believes in the need for an open-source AI ecosystem and is building the infra and tooling to allow open-source AIs to compete on a level playing field with proprietary ones.
|
| 49 |
+
|
| 50 |
+
Jan's long-term vision is to build a cognitive framework for future robots, who are practical, useful assistants for humans and businesses in everyday life.
|
| 51 |
+
|
| 52 |
+
# Jan Model Merger
|
| 53 |
+
This is a test project for merging models.
|
| 54 |
+
|
| 55 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 56 |
+
|
| 57 |
+
Detailed results can be found here.
|
| 58 |
+
|
| 59 |
+
| Metric | Value |
|
| 60 |
+
|-----------------------|---------------------------|
|
| 61 |
+
| Avg. | ?|
|
| 62 |
+
| ARC (25-shot) | ? |
|
| 63 |
+
| HellaSwag (10-shot) | ? |
|
| 64 |
+
| MMLU (5-shot) | ?|
|
| 65 |
+
| TruthfulQA (0-shot) | ? |
|
| 66 |
+
| Winogrande (5-shot) | ? |
|
| 67 |
+
| GSM8K (5-shot) | ? |
|
| 68 |
+
|
| 69 |
+
# Acknowlegement
|
| 70 |
+
- [mergekit]
|
| 71 |
+
(https://github.com/cg123/mergekit)
|
| 72 |
+
- [DARE](https://github.com/yule-BUAA/MergeLM/blob/main/README.md)
|
| 73 |
+
- [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness)
|