Modelpublic

StopTryharding/DareBeagel-2x7B-GGUF

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face

4likes138downloads

Model Card

This is a repository of GGUF Quants for DareBeagel-2x7B ---

Original Model Available Here: https://huggingface.co/shadowml/DareBeagel-2x7B

Available Quants

—Q8_0
—Q6_K
—Q5KM
—Q5KS
—Q4KM
—Q4KS
—Q3KM
—Q3KS
—Q2_K

Beyonder-2x7B-v2

Beyonder-2x7B-v2 is a Mixure of Experts (MoE) made with the following models using LazyMergekit:

—mlabonne/NeuralBeagle14-7B
—mlabonne/NeuralDaredevil-7B

🧩 Configuration

yaml

base_model: mlabonne/NeuralBeagle14-7B
gate_mode: random
experts:
  - source_model: mlabonne/NeuralBeagle14-7B
    positive_prompts: [""]
  - source_model: mlabonne/NeuralDaredevil-7B
    positive_prompts: [""]

💻 Usage

Load in Kobold.cpp or whatever.
I found Alpaca (and Alpaca-ish) prompts worked well.
Settings that worked good for me are:

Min P - 0.1
Dynamic Temperature Min 0 Max 3
Rep Pen 1.03
Rep Pen Range 1000