Why choose?

The full model name is "Llama-3-8B-Poppy-Sunspice"

RP Model, pretty creative.

v000000/L3-8B-Poppy-Sunspice-Q8_0-GGUF

This model was converted to GGUF format from v000000/L3-8B-Poppy-Sunspice using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

Update/Notice:

This has a tendency for endless generations. It likes a bit of penalty parameters if this occurs.

merge

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

Merge Details

Merge Method

This model was merged using the linear merge method.

Models Merged

The following models were included in the merge:

• Sao10K/L3-8B-Stheno-v3.1
• Nitral-Archive/Poppy_Porpoise-Biomix
• Hastagaras/HALU-8B-LLAMA3-BRSLURP
• crestf411/L3-8B-sunfall-abliterated-v0.1
• cgato/L3-TheSpice-8b-v0.8.3
• Nitral-AI/Poppy_Porpoise-0.72-L3-8B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: crestf411/L3-8B-sunfall-abliterated-v0.1
    parameters:
      weight: 0.1
  - model: Nitral-AI/Poppy_Porpoise-0.72-L3-8B
    parameters:
      weight: 0.3
  - model: Nitral-Archive/Poppy_Porpoise-Biomix
    parameters:
      weight: 0.1
  - model: Sao10K/L3-8B-Stheno-v3.1
    parameters:
      weight: 0.2
  - model: Hastagaras/HALU-8B-LLAMA3-BRSLURP
    parameters:
      weight: 0.1
  - model: cgato/L3-TheSpice-8b-v0.8.3
    parameters:
      weight: 0.2
merge_method: linear
dtype: float16

Prompt Template:

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>

{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

{output}<|eot_id|>