kukulemon-32K-7B-GGUF

kukulemon-32K-7B-GGUF

These are GGUF quants of a proof of concept a merge capable of functional 32K context length while being derived from kukulemon-7B. The functioning 32K context window has been folded in via a merger of Mistral 7B v0.2 models. SLERP merge appears to be viable, but DARE-TIES merge risks producing a damaged model and is therefore not recommended.

Although the resulting model natively supports Alpaca prompt, I've tested with ChatML prompts successfuly. Medium temperature (around 1) with low minP (e.g., 0.01) works with ChatML prompts in my most recent testing.

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

• Full weights: grimjim/kukulemon-32K-7B

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• grimjim/Mistral-7B-Instruct-demi-merge-v0.2-7B
• grimjim/kukulemon-7B

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: grimjim/kukulemon-7B
        layer_range: [0, 32]
      - model: grimjim/Mistral-7B-Instruct-demi-merge-v0.2-7B
        layer_range: [0, 32]
# or, the equivalent models: syntax:
# models:
merge_method: slerp
base_model: grimjim/kukulemon-7B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5 # fallback for rest of tensors
dtype: bfloat16