mirror of
https://github.com/mudler/LocalAI.git
synced 2025-01-29 15:44:17 +00:00
models(gallery): add nymph_8b-i1 (#2742)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
parent
bdfebfe0f4
commit
deb5311373
@ -2490,6 +2490,24 @@
|
||||
- filename: L3-Uncen-Merger-Omelette-RP-v0.2-8B-Q4_K_M-imat.gguf
|
||||
sha256: 6bbc42a4c3b25f2b854d76a6e32746b9b3b21dd8856f8f2bc1a5b1269aa8fca1
|
||||
uri: huggingface://LWDCLS/L3-Uncen-Merger-Omelette-RP-v0.2-8B-GGUF-IQ-Imatrix-Request/L3-Uncen-Merger-Omelette-RP-v0.2-8B-Q4_K_M-imat.gguf
|
||||
- !!merge <<: *llama3
|
||||
name: "nymph_8b-i1"
|
||||
icon: https://cdn-uploads.huggingface.co/production/uploads/626dfb8786671a29c715f8a9/9U_eJCDzLJ8nxb6qfuICc.jpeg
|
||||
urls:
|
||||
- https://huggingface.co/ResplendentAI/Nymph_8B
|
||||
- https://huggingface.co/mradermacher/Nymph_8B-i1-GGUF?not-for-all-audiences=true
|
||||
description: |
|
||||
Model card:
|
||||
Nymph is the culmination of everything I have learned with the T-series project. This model aims to be a unique and full featured RP juggernaut.
|
||||
|
||||
The finetune incorporates 1.6 Million tokens of RP data sourced from Bluemoon, FreedomRP, Aesir-Preview, and Claude Opus logs. I made sure to use the multi-turn sharegpt datasets this time instead of alpaca conversions. I have also included three of my personal datasets. The final touch is an ORPO based upon Openhermes Roleplay preferences.
|
||||
overrides:
|
||||
parameters:
|
||||
model: Nymph_8B.i1-Q4_K_M.gguf
|
||||
files:
|
||||
- filename: Nymph_8B.i1-Q4_K_M.gguf
|
||||
sha256: 5b35794539d9cd262720f47a54f59dbffd5bf6c601950359b5c68d13f1ce13a0
|
||||
uri: huggingface://mradermacher/Nymph_8B-i1-GGUF/Nymph_8B.i1-Q4_K_M.gguf
|
||||
- &chatml
|
||||
### ChatML
|
||||
url: "github:mudler/LocalAI/gallery/chatml.yaml@master"
|
||||
|
Loading…
x
Reference in New Issue
Block a user