models(gallery): add l3.1-etherealrainbow-v1.0-rc1-8b (#3856)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-10-17 10:03:08 +02:00 committed by GitHub
parent 98dfa363db
commit 5927f9e43e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -1713,6 +1713,25 @@
- filename: Llama-3.1-Nemotron-70B-Instruct-HF.Q4_K_M.gguf
sha256: b6b80001b849e3c59c39b09508c018b35b491a5c7bbafafa23f2fc04243f3e30
uri: huggingface://mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF/Llama-3.1-Nemotron-70B-Instruct-HF.Q4_K_M.gguf
- !!merge <<: *llama31
name: "l3.1-etherealrainbow-v1.0-rc1-8b"
icon: https://huggingface.co/invisietch/L3.1-EtherealRainbow-v1.0-rc1-8B/resolve/main/header.png
urls:
- https://huggingface.co/invisietch/L3.1-EtherealRainbow-v1.0-rc1-8B
- https://huggingface.co/mradermacher/L3.1-EtherealRainbow-v1.0-rc1-8B-GGUF
description: |
Ethereal Rainbow v1.0 is the sequel to the popular Llama 3 8B merge, EtherealRainbow v0.3. Instead of a straight merge of other peoples' models, v1.0 is a finetune on the Instruct model, using 245 million tokens of training data (approx 177 million of these tokens are my own novel datasets).
This model is designed to be suitable for creative writing and roleplay, and to push the boundaries of what's possible with an 8B model. This RC is not a finished product, but your feedback will drive the creation of better models.
This is a release candidate model. It has some known issues and probably some unknown ones too, because the purpose of these early releases is to seek feedback.
overrides:
parameters:
model: L3.1-EtherealRainbow-v1.0-rc1-8B.Q4_K_M.gguf
files:
- filename: L3.1-EtherealRainbow-v1.0-rc1-8B.Q4_K_M.gguf
sha256: c5556b2563112e512acca171415783f0988545b02c1834696c1cc35952def72c
uri: huggingface://mradermacher/L3.1-EtherealRainbow-v1.0-rc1-8B-GGUF/L3.1-EtherealRainbow-v1.0-rc1-8B.Q4_K_M.gguf
- &deepseek
## Deepseek
url: "github:mudler/LocalAI/gallery/deepseek.yaml@master"