RichardErkhov/ank028_-_Llama-3.2-1B-Instruct-commonsense_qa-MGSM8K-sft1-ties-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Llama-3.2-1B-Instruct-commonsense_qa-MGSM8K-sft1-ties - GGUF

• —Model creator: https://huggingface.co/ank028/
• —Original model: https://huggingface.co/ank028/Llama-3.2-1B-Instruct-commonsense_qa-MGSM8K-sft1-ties/

Original model description: --- base_model:

• —ank028/Llama-3.2-1B-Instruct-commonsense_qa
• —autoprogrammer/Llama-3.2-1B-Instruct-MGSM8K-sft1
• —meta-llama/Llama-3.2-1B-Instruct library_name: transformers tags:
• —mergekit
• —merge

c_l

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

Merge Details

Merge Method

This model was merged using the TIES merge method using meta-llama/Llama-3.2-1B-Instruct as a base.

Models Merged

The following models were included in the merge:

• —ank028/Llama-3.2-1B-Instruct-commonsense_qa
• —autoprogrammer/Llama-3.2-1B-Instruct-MGSM8K-sft1

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: ank028/Llama-3.2-1B-Instruct-commonsense_qa
    parameters:
      density: 0.5 # density gradient
      weight: 1.0
  - model: autoprogrammer/Llama-3.2-1B-Instruct-MGSM8K-sft1
    parameters:
      density: 0.5
      weight: 0.5 # weight gradient
merge_method: ties
base_model: meta-llama/Llama-3.2-1B-Instruct
parameters:
  normalize: true
  int8_mask: false
dtype: float16
name: Llama-3.2-1B-Instruct-commonsense_qa-MGSM8K-sft1-ties