RichardErkhov/paraschopra_-_llama-31-8b-instruct-regenerated-100-cot-no-system-prompt_MERGED_SLERP-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama-31-8b-instruct-regenerated-100-cot-no-system-promptMERGEDSLERP - GGUF

• —Model creator: https://huggingface.co/paraschopra/
• —Original model: https://huggingface.co/paraschopra/llama-31-8b-instruct-regenerated-100-cot-no-system-promptMERGEDSLERP/

Original model description: --- base_model:

• —paraschopra/llama-31-8b-instruct-regenerated-100-cot-no-system-prompt
• —meta-llama/meta-llama-3.1-8b-instruct library_name: transformers tags:
• —mergekit
• —merge

merge

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• —paraschopra/llama-31-8b-instruct-regenerated-100-cot-no-system-prompt
• —meta-llama/meta-llama-3.1-8b-instruct

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: paraschopra/llama-31-8b-instruct-regenerated-100-cot-no-system-prompt
        layer_range: [0, 32]
      - model: meta-llama/meta-llama-3.1-8b-instruct
        layer_range: [0, 32]
merge_method: slerp
base_model: meta-llama/meta-llama-3.1-8b-instruct
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
dtype: bfloat16
tokenizer_source: meta-llama/meta-llama-3.1-8b-instruct