WARNING
This is a model file only for evaluation. Please use the model here:
Jan banner
Model Description
This model uses the
Slerp merge method from the best models on 14th Dec on the
OpenLLM Leaderboard :
upstage/SOLAR-10.7B-Instruct-v1.0 janhq/Pandora-v1-10.7B
The yaml config file for this model is here:
1 slices :
2 - sources :
3 - model : upstage/SOLAR - 10.7B - Instruct - v1.0
4 layer_range : [ 0 , 48 ]
5 - model : janhq/Pandora - v1 - 10.7B
6 layer_range : [ 0 , 48 ]
7 merge_method : slerp
8 base_model : upstage/SOLAR - 10.7B - Instruct - v1.0
9 parameters :
10 t :
11 - filter : self_attn
12 value : [ 0 , 0.5 , 0.3 , 0.7 , 1 ]
13 - filter : mlp
14 value : [ 1 , 0.5 , 0.7 , 0.3 , 0 ]
15 - value : 0.5
16 dtype : bfloat16
Prompt template
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistantRun this model
You can run this model using
Jan 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
Please use the Solar-10.7B-SLERP-GGUF when using on Jan.
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. ? ARC (25-shot) ? HellaSwag (10-shot) ? MMLU (5-shot) ? TruthfulQA (0-shot) ? Winogrande (5-shot) ? GSM8K (5-shot) ?
Acknowlegement
