38 lines
841 B
Markdown
38 lines
841 B
Markdown
---
|
|
license: apache-2.0
|
|
---
|
|
|
|
Frankenmerge 11b between teknium/OpenHermes-2.5-Mistral-7B and Intel/neural-chat-7b-v3-1
|
|
|
|
|
|
GGUF: https://huggingface.co/TheBloke/Open-Hermes-2.5-neural-chat-3.1-frankenmerge-11b-GGUF
|
|
|
|
Merge with the following conditions
|
|
|
|
|
|
- model: teknium/OpenHermes-2.5-Mistral-7B
|
|
layer_range: [0, 8]
|
|
|
|
- model: Intel/neural-chat-7b-v3-1
|
|
layer_range: [4, 12]
|
|
|
|
- model: teknium/OpenHermes-2.5-Mistral-7B
|
|
layer_range: [9, 16]
|
|
|
|
- model: Intel/neural-chat-7b-v3-1
|
|
layer_range: [13, 20]
|
|
|
|
- model: teknium/OpenHermes-2.5-Mistral-7B
|
|
layer_range: [17, 24]
|
|
|
|
- model: Intel/neural-chat-7b-v3-1
|
|
layer_range: [21, 28]
|
|
|
|
- model: teknium/OpenHermes-2.5-Mistral-7B
|
|
layer_range: [25, 32]
|
|
merge_method: passthrough
|
|
|
|
|
|
|
|
Benchmarks are coming soon...
|