v000000/L3-8B-UGI-DontPlanToEnd-test-GGUF

This model was converted to GGUF format from v000000/L3-8B-UGI-DontPlanToEnd-test using llama.cpp Refer to the original model card for more details on the model.'

List of quants in repo:

• Q8_0 imatrix
• FP16 in .GGUF format for llama.cpp inference.

test-test-test-test request

num_battles: 40982
num_wins: 23536
celo_rating: 1214.08
safety_score: 0.96
propriety_score: 0.7065322049358942
propriety_total_count: 19733.0

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using tannedbum/L3-Nymeria-8B as a base.

Models Merged

The following models were included in the merge:

• PJMixers/LLaMa-3-CursedStock-v1.8-8B
• bluuwhale/L3-SthenoMaidBlackroot-8B-V1
• v000000/L3-8B-Poppy-Sunspice
• Nitral-AI/Hathor_RP-v.01-L3-8B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: PJMixers/LLaMa-3-CursedStock-v1.8-8B
    parameters:
      weight: 0.15
      density: 0.57
  - model: v000000/L3-8B-Poppy-Sunspice
    parameters:
      weight: 0.20
      density: 0.69
  - model: Nitral-AI/Hathor_RP-v.01-L3-8B
    parameters:
      weight: 0.30
      density: 0.8
  - model: bluuwhale/L3-SthenoMaidBlackroot-8B-V1
    parameters:
      weight: 0.35
      density: 0.85
merge_method: dare_ties
base_model: tannedbum/L3-Nymeria-8B
parameters:
  int8_mask: true
dtype: bfloat16