This is a Llama-3 land now, cowboys!

GGUF-IQ-Imatrix quants for NLPark/Test0_SLIDE. Presets here.

Use the latest version of KoboldCpp. Use the provided presets.
This is all still highly experimental, let the authors know how it performs for you, feedback is more important than ever now.

Original model information:

image/png

Shi-Ci Language Identify & Decode Expositor

8B, Ruozhiba...

Chinese Released as an early preview of our v3 LLMs. The v3 series covers the "Shi-Ci", "AnFeng" and "Cecilia" LLM products. The sizes are labelled from small to large "Nano" "Leap" "Pattern" "Avocet "Robin" "Kestrel"

Downloads last month
23
GGUF
Model size
8.03B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference API
Unable to determine this model's library. Check the docs .