kamruzzaman-asif/mergekit-qwen_7B_instruct_base_lora_merged_0_570000

output-model-directory

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 Qwen/Qwen2.5-7B as a base.

Models Merged

The following models were included in the merge:

• kamruzzaman-asif/qwen2.5_7B_instruct_base_lora_merged_42001_57000
• Qwen/Qwen2.5-7B-Instruct
• kamruzzaman-asif/qwen2.5_7B_instruct_base_lora_merged_30001_42000
• kamruzzaman-asif/qwen2.5_7B_instruct_base_lora_merged_0_15000
• kamruzzaman-asif/qwen2.5_7B_instruct_base_lora_merged_15001_30000

Configuration

The following YAML configuration was used to produce this model:

base_model: Qwen/Qwen2.5-7B
dtype: bfloat16
merge_method: ties
models:
- model: kamruzzaman-asif/qwen2.5_7B_instruct_base_lora_merged_0_15000
  parameters:
    density: 1
    weight: 1
- model: kamruzzaman-asif/qwen2.5_7B_instruct_base_lora_merged_15001_30000
  parameters:
    density: 1
    weight: 1
- model: kamruzzaman-asif/qwen2.5_7B_instruct_base_lora_merged_30001_42000
  parameters:
    density: 1
    weight: 1
- model: kamruzzaman-asif/qwen2.5_7B_instruct_base_lora_merged_42001_57000
  parameters:
    density: 1
    weight: 1
- model: Qwen/Qwen2.5-7B-Instruct
  parameters:
    density: 1
    weight: 1
parameters:
  density: 1
  int8_mask: true
  normalize: true
  weight: 1
tokenizer_source: kamruzzaman-asif/qwen2.5_7B_instruct_base_lora_merged_0_15000