jan-hq/supermario-slerp

Jan - Discord

Model Description

This model uses the Slerp merge method from 2 models:

1. Seraph-7B
2. Marcoroni-7B-v3

• base model: Mistral-7B-v0.1

The yaml config file for this model is here:

slices:
  - sources:
      - model: Weyaxi/Seraph-7B
        layer_range: [0, 32]

      - model: AIDC-ai-business/Marcoroni-7B-v3
        layer_range: [0, 32]
merge_method: slerp
base_model: mistralai/Mistral-7B-v0.1
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16

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:

• 💻 100% offline on your machine: Your conversations remain confidential, and visible only to you.
• 🗂️ 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

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.	72.32
ARC (25-shot)	68.94
HellaSwag (10-shot)	86.58
MMLU (5-shot)	64.93
TruthfulQA (0-shot)	60.11
Winogrande (5-shot)	81.29
GSM8K (5-shot)	72.1

Acknowlegement

• mergekit
• DARE
• SLERP
• lm-evaluation-harness

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	72.32
AI2 Reasoning Challenge (25-Shot)	68.94
HellaSwag (10-Shot)	86.58
MMLU (5-Shot)	64.93
TruthfulQA (0-shot)	60.11
Winogrande (5-shot)	81.29
GSM8k (5-shot)	72.10