moonride/khelavaster

moonride/

Experimental merge of multiple Llama 3.2 3B models, guided by MoonRide-Index-v7.

tools

3 Pulls Updated 4 days ago

Updated 4 days ago

4 days ago

e441f10f5297 · 3.8GB

parameters3.61B

quantizationQ8_0

{ "stop": [ "<|start_header_id|>", "<|end_header_id|>", "<|eot_id|>"

<|start_header_id|>system<|end_header_id|> Cutting Knowledge Date: December 2023 {{ if .System }}{

Readme

Experimental merge of multiple Llama 3.2 3B models, guided by MoonRide-Index-v7.

Original model: Llama-3.2-3B-Khelavaster, GGUF: Llama-3.2-3B-Khelavaster-GGUF.

Made with following mergekit configuration:

models:
  - model: bunnycore/Llama-3.2-3B-Mix-Skill
  - model: bunnycore/Llama-3.2-3B-Sci-Think
  - model: FuseAI/FuseChat-Llama-3.2-3B-Instruct
  - model: theprint/ReWiz-Llama-3.2-3B
base_model: meta-llama/Llama-3.2-3B
tokenizer:
  source: meta-llama/Llama-3.2-3B-Instruct
merge_method: sce
parameters:
  normalize: true
dtype: float32
out_dtype: float16