supermario-v2 / README.md
davanstrien's picture
davanstrien HF staff
add merge tag
21e2608
|
raw
history blame
3.58 kB
metadata
license: apache-2.0
language:
  - en
tags:
  - merge
Jan banner

Jan - Discord

Model Description

This model uses the DARE_TIES merge method from 3 models:

  1. OpenHermes-2.5-neural-chat-v3-3-Slerp
  2. MetaMath-Cybertron-Starling
  3. Marcoroni-7B-v3

The yaml config file for this model here:

base_model: mistralai/Mistral-7B-v0.1
dtype: bfloat16
merge_method: dare_ties
models:
- model: mistralai/Mistral-7B-v0.1
- model: Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp
  parameters:
    density: 0.8
    weight: 0.4
- model: Q-bert/MetaMath-Cybertron-Starling
  parameters:
    density: 0.8
    weight: 0.3
- model: AIDC-ai-business/Marcoroni-7B-v3
  parameters:
    density: 0.8
    weight: 0.3
parameters:
  int8_mask: true

Prompt template:

  • ChatML
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
  • System
### System:
{system}
### User:
{user}
### Assistant:

Run this model

You can run this model using Jan Desktop on Mac, Windows, or Linux.

Jan is an open source, ChatGPT alternative that is:

  • πŸ’» 100% offline on your machine: Your conversations remain confidential, and visible only to you.
  • πŸ—‚οΈ An Open File Format: Conversations and model settings stay on your computer and can be exported or deleted at any time.
  • 🌐 OpenAI Compatible: Local server on port 1337 with OpenAI compatible endpoints
  • 🌍 Open Source & Free: We build in public; check out our Github

image/png

About Jan

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.

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.

Jan Model Merger

This is a test project for merging models.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here.

Metric Value
Avg. 72.36
ARC (25-shot) 68.52
HellaSwag (10-shot) 86.51
MMLU (5-shot) 64.88
TruthfulQA (0-shot) 60.58
Winogrande (5-shot) 81.37
GSM8K (5-shot) 72.18

Acknowlegement