models(gallery): add fireball-llama-3.11-8b-v1orpo (#3267)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-08-19 11:34:38 +02:00 committed by GitHub
parent 857443e2b5
commit f2f372b7f5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -354,6 +354,23 @@
- filename: calme-2.3-legalkit-8b.i1-Q4_K_M.gguf
sha256: b71dfea8bbd73b0fbd5793ef462b8540c24e1c52a47b1794561adb88109a9e80
uri: huggingface://mradermacher/calme-2.3-legalkit-8b-i1-GGUF/calme-2.3-legalkit-8b.i1-Q4_K_M.gguf
- !!merge <<: *llama31
name: "fireball-llama-3.11-8b-v1orpo"
icon: https://huggingface.co/EpistemeAI/Fireball-Llama-3.1-8B-v1dpo/resolve/main/fireball-llama.JPG
urls:
- https://huggingface.co/mradermacher/Fireball-Llama-3.11-8B-v1orpo-GGUF
description: |
Developed by: EpistemeAI
License: apache-2.0
Finetuned from model : unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit
Finetuned methods: DPO (Direct Preference Optimization) & ORPO (Odds Ratio Preference Optimization)
overrides:
parameters:
model: Fireball-Llama-3.11-8B-v1orpo.Q4_K_M.gguf
files:
- filename: Fireball-Llama-3.11-8B-v1orpo.Q4_K_M.gguf
sha256: c61a1f4ee4f05730ac6af754dc8dfddf34eba4486ffa320864e16620d6527731
uri: huggingface://mradermacher/Fireball-Llama-3.11-8B-v1orpo-GGUF/Fireball-Llama-3.11-8B-v1orpo.Q4_K_M.gguf
## Uncensored models
- !!merge <<: *llama31
name: "humanish-roleplay-llama-3.1-8b-i1"