QuantFactory/HALU-8B-LLAMA3-BRSLURP-GGUF

This is quantized version of Hastagaras/HALU-8B-LLAMA3-BRSLURP created suing llama.cpp

Model Description

You can see the Halu 0.35 model details in HERE

So two different models with different base models...a fusion of OpenAI and MetaAI, truthful QA gonna be tough.

After some testing, I think this super duper easy merge that I did while I was half asleep is actually pretty decent.

After another testing...the Blackroot influence is way smoother than the Anjir, probably because the base models are different, so...no duplicate layers, I guess.

Works better with around 0.95-1.1 temp.

EDIT: I think this is too safe, I don't like it...

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: Hastagaras/Halu-8B-Llama3-v0.35
        layer_range: [0,32]
      - model: Hastagaras/Halu-8B-Llama3-Blackroot
        layer_range: [0,32]
merge_method: slerp
base_model: Hastagaras/Halu-8B-Llama3-v0.35
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.5, 0.5, 1]
    - filter: mlp
      value: [1, 0.5, 0.5, 0.5, 0]
    - value: 0.5
dtype: bfloat16