supermario-slerp-v3/README.md

language, license, model-index

language	license	model-index
en	apache-2.0	name results supermario-slerp-v3 task dataset metrics source type name text-generation Text Generation name type config split args AI2 Reasoning Challenge (25-Shot) ai2_arc ARC-Challenge test num_few_shot 25 type value name acc_norm 69.28 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jan-hq/supermario-slerp-v3 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type split args HellaSwag (10-Shot) hellaswag validation num_few_shot 10 type value name acc_norm 86.71 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jan-hq/supermario-slerp-v3 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args MMLU (5-Shot) cais/mmlu all test num_few_shot 5 type value name acc 65.11 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jan-hq/supermario-slerp-v3 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args TruthfulQA (0-shot) truthful_qa multiple_choice validation num_few_shot 0 type value mc2 61.77 url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jan-hq/supermario-slerp-v3 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args Winogrande (5-shot) winogrande winogrande_xl validation num_few_shot 5 type value name acc 80.51 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jan-hq/supermario-slerp-v3 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args GSM8k (5-shot) gsm8k main test num_few_shot 5 type value name acc 69.98 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jan-hq/supermario-slerp-v3 Open LLM Leaderboard

Jan - Discord

Model Description

This model uses the Slerp merge method from our 2 best models in 12th Dec:

1. supermario-slerp-v2
2. supermario-v2

• base model: supermario-slerp-v2

The yaml config file for this model is here:

slices:
  - sources:
      - model: janhq/supermario-slerp-v2
        layer_range: [0, 32]
      - model: janhq/supermario-v2
        layer_range: [0, 32]
merge_method: slerp
base_model: janhq/supermario-slerp-v2
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.	?
ARC (25-shot)	?
HellaSwag (10-shot)	?
MMLU (5-shot)	?
TruthfulQA (0-shot)	?
Winogrande (5-shot)	?
GSM8K (5-shot)	?

Acknowlegement

• mergekit
• DARE

SLERP

• lm-evaluation-harness

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	72.22
AI2 Reasoning Challenge (25-Shot)	69.28
HellaSwag (10-Shot)	86.71
MMLU (5-Shot)	65.11
TruthfulQA (0-shot)	61.77
Winogrande (5-shot)	80.51
GSM8k (5-shot)	69.98