models(gallery): add l3-aethora-15b (#2546)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-06-11 18:31:13 +02:00 committed by GitHub
parent 3c50abffdd
commit 7b12300f15
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -527,6 +527,21 @@
- filename: halu-8b-llama3-blackroot-q4_k_m.gguf
uri: huggingface://mudler/Halu-8B-Llama3-Blackroot-Q4_K_M-GGUF/halu-8b-llama3-blackroot-q4_k_m.gguf
sha256: 6304c7abadb9c5197485e8b4373b7ed22d9838d5081cd134c4fee823f88ac403
- !!merge <<: *llama3
name: "l3-aethora-15b"
urls:
- https://huggingface.co/Steelskull/L3-Aethora-15B
- https://huggingface.co/SteelQuants/L3-Aethora-15B-Q4_K_M-GGUF
icon: https://cdn-uploads.huggingface.co/production/uploads/64545af5ec40bbbd01242ca6/W0qzZK_V1Zt1GdgCIsnrP.png
description: |
L3-Aethora-15B was crafted through using the abilteration method to adjust model responses. The model's refusal is inhibited, focusing on yielding more compliant and facilitative dialogue interactions. It then underwent a modified DUS (Depth Up Scale) merge (originally used by @Elinas) by using passthrough merge to create a 15b model, with specific adjustments (zeroing) to 'o_proj' and 'down_proj', enhancing its efficiency and reducing perplexity. This created AbL3In-15b.
overrides:
parameters:
model: l3-aethora-15b-q4_k_m.gguf
files:
- filename: l3-aethora-15b-q4_k_m.gguf
uri: huggingface://SteelQuants/L3-Aethora-15B-Q4_K_M-GGUF/l3-aethora-15b-q4_k_m.gguf
sha256: 968f77a3187f4865458bfffc51a10bcf49c11263fdd389f13215a704b25947b6
- !!merge <<: *llama3
name: "jsl-medllama-3-8b-v2.0"
license: cc-by-nc-nd-4.0