Hjgugugjhuhjggg/mergekit-ties-dhpqgnv

merge

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 as a base.

Models Merged

The following models were included in the merge:

• autoprogrammer/Llama-3.2-1B-Instruct-MGSM8K-sft1
• meta-llama/Llama-3.2-1B-Instruct
• student-abdullah/Llama3.2-1B_Hinglish-Medicine-Dataset_Finetuning_28-09
• ank028/Llama-3.2-1B-Instruct-gsm8k
• huyhoangt2201/llama-3.2-1b-sql_finetuned_billingual_3.0_merged
• MLking2/llama-3.2-1b-medical
• unsloth/Llama-3.2-1B-Instruct-bnb-4bit
• autoprogrammer/Llama-3.2-1B-Instruct-medmcqa-zh-linear
• Alelcv27/llama3.2-1b-math-code
• ank028/Llama-3.2-1B-Instruct-medmcqa
• qzhang-2024/Llama-3.2-1B-pre-trained
• huyhoangt2201/llama-3.2-1b-chat-sql3-merged
• jayavibhav/llama3.2_1b_CoT
• ank028/Llama-3.2-1B-Instruct-commonsense_qa

Configuration

The following YAML configuration was used to produce this model:

merge_method: ties
architectures: ["transformer"]
base_model: meta-llama/Llama-3.2-1B
models:
  - model: Alelcv27/llama3.2-1b-math-code
  - model: huyhoangt2201/llama-3.2-1b-sql_finetuned_billingual_3.0_merged
  - model: autoprogrammer/Llama-3.2-1B-Instruct-MGSM8K-sft1
  - model: meta-llama/Llama-3.2-1B-Instruct
  - model: autoprogrammer/Llama-3.2-1B-Instruct-medmcqa-zh-linear
  - model: meta-llama/Llama-3.2-1B
  - model: unsloth/Llama-3.2-1B-Instruct-bnb-4bit
  - model: MLking2/llama-3.2-1b-medical
  - model: jayavibhav/llama3.2_1b_CoT
  - model: huyhoangt2201/llama-3.2-1b-chat-sql3-merged
  - model: student-abdullah/Llama3.2-1B_Hinglish-Medicine-Dataset_Finetuning_28-09
  - model: qzhang-2024/Llama-3.2-1B-pre-trained
  - model: ank028/Llama-3.2-1B-Instruct-medmcqa
  - model: ank028/Llama-3.2-1B-Instruct-gsm8k
  - model: ank028/Llama-3.2-1B-Instruct-commonsense_qa

parameters:
  density: 0.5
  weight: 1.0