models(gallery): add llama-3.1-supernova-lite-reflection-v1.0-i1 ()

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-09-20 17:19:53 +02:00 committed by GitHub
parent 38cad0b8dc
commit c4cecba07f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

@ -601,6 +601,22 @@
- filename: Reflection-Llama-3.1-70B-q4_k_m.gguf
sha256: 16064e07037883a750cfeae9a7be41143aa857dbac81c2e93c68e2f941dee7b2
uri: huggingface://senseable/Reflection-Llama-3.1-70B-gguf/Reflection-Llama-3.1-70B-q4_k_m.gguf
- !!merge <<: *llama31
name: "llama-3.1-supernova-lite-reflection-v1.0-i1"
url: "github:mudler/LocalAI/gallery/llama3.1-reflective.yaml@master"
icon: https://i.ibb.co/r072p7j/eopi-ZVu-SQ0-G-Cav78-Byq-Tg.png
urls:
- https://huggingface.co/SE6446/Llama-3.1-SuperNova-Lite-Reflection-V1.0
- https://huggingface.co/mradermacher/Llama-3.1-SuperNova-Lite-Reflection-V1.0-i1-GGUF
description: |
This model is a LoRA adaptation of arcee-ai/Llama-3.1-SuperNova-Lite on thesven/Reflective-MAGLLAMA-v0.1.1. This has been a simple experiment into reflection and the model appears to perform adequately, though I am unsure if it is a large improvement.
overrides:
parameters:
model: Llama-3.1-SuperNova-Lite-Reflection-V1.0.i1-Q4_K_M.gguf
files:
- filename: Llama-3.1-SuperNova-Lite-Reflection-V1.0.i1-Q4_K_M.gguf
sha256: 0c4531fe553d00142808e1bc7348ae92d400794c5b64d2db1a974718324dfe9a
uri: huggingface://mradermacher/Llama-3.1-SuperNova-Lite-Reflection-V1.0-i1-GGUF/Llama-3.1-SuperNova-Lite-Reflection-V1.0.i1-Q4_K_M.gguf
## Uncensored models
- !!merge <<: *llama31
name: "humanish-roleplay-llama-3.1-8b-i1"