metadata
base_model:
- huyhoangt2201/llama-3.2-1b-sql_finetuned_billingual_3.0_merged
- jayavibhav/llama3.2_1b_CoT
- huyhoangt2201/llama-3.2-1b-chat-sql3-merged
- autoprogrammer/Llama-3.2-1B-Instruct-MGSM8K-sft1
- Alelcv27/llama3.2-1b-math-code
- unsloth/Llama-3.2-1B-Instruct-bnb-4bit
- meta-llama/Llama-3.2-1B
- student-abdullah/Llama3.2-1B_Hinglish-Medicine-Dataset_Finetuning_28-09
- meta-llama/Llama-3.2-1B-Instruct
- MLking2/llama-3.2-1b-medical
- autoprogrammer/Llama-3.2-1B-Instruct-medmcqa-zh-linear
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 TIES merge method using meta-llama/Llama-3.2-1B-Instruct as a base.
Models Merged
The following models were included in the merge:
- huyhoangt2201/llama-3.2-1b-sql_finetuned_billingual_3.0_merged
- jayavibhav/llama3.2_1b_CoT
- huyhoangt2201/llama-3.2-1b-chat-sql3-merged
- autoprogrammer/Llama-3.2-1B-Instruct-MGSM8K-sft1
- Alelcv27/llama3.2-1b-math-code
- unsloth/Llama-3.2-1B-Instruct-bnb-4bit
- meta-llama/Llama-3.2-1B
- student-abdullah/Llama3.2-1B_Hinglish-Medicine-Dataset_Finetuning_28-09
- MLking2/llama-3.2-1b-medical
- autoprogrammer/Llama-3.2-1B-Instruct-medmcqa-zh-linear
Configuration
The following YAML configuration was used to produce this model:
merge_method: ties
architectures: ["transformer"]
base_model: meta-llama/Llama-3.2-1B-Instruct
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
parameters:
density: 0.5
weight: 1.0
int8_mask: true
normalize: true