metadata
license: apache-2.0
language:
- en
Model Description
This model uses the DARE_TIES merge method from 3 models:
- base model: Mistral-7B-v0.1
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
- Alpaca
{system_message}
### Instruction:
{prompt}
### Response:
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 |