Edit model card

1718719796324.png


L3-Inca-8B-v0.5

L3-Inca-8B-v0.5 is a merge of the following models:

using NurtureAI/Meta-Llama-3-8B-Instruct-32k as the base.

  • Made with RP/ERP in mind.
  • Supports a context length of 32k.
  • Strong at instruction following.
  • Fully uncensored.

Recommend Preset Settings:

Top K: 40
Top P: 0.95
Min P: 0.075
Rep Pen: 1.05
Rep Pen Range: 2048
Frequency Pen: 0.50
Presence Pen: 0.15

GGUF

mradermacher: L3-Inca-8B-v0.5-GGUF

Downloads last month
1
Safetensors
Model size
8.03B params
Tensor type
BF16
·
Inference API
Input a message to start chatting with Ppoyaa/L3-Inca-8B-v0.5.
Model is too large to load in Inference API (serverless). To try the model, launch it on Inference Endpoints (dedicated) instead.