Downloads · 30 days
16
7% of all-time downloads
Astris/Llama-3-AnySelfMerge
Llama-3-AnySelfMerge is a text generation model from Astris. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as llama3.
To use this model, make sure to enable trustremotecode. To tweak the layer order, go into config.json and change the layerexecplan. Normally (for llama 8b) it would be [0...31] but you can change this to be any combin…
Downloads · 30 days
16
7% of all-time downloads
All-time downloads
215
Public
Parameters
8B
16.1 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors16.1 GB · 100%
From the Hugging Face model README
To use this model, make sure to enable trust_remote_code. To tweak the layer order, go into config.json and change the layer_exec_plan. Normally (for llama 8b) it would be [0...31] but you can change this to be any combination of layers you want (including repetitions).