RichardErkhov/kamruzzaman-asif_-_mergekit-qwen_3B_instruct_base_lora_merged_0_6500-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

mergekit-qwen3Binstructbaseloramerged0_6500 - GGUF

• —Model creator: https://huggingface.co/kamruzzaman-asif/
• —Original model: https://huggingface.co/kamruzzaman-asif/mergekit-qwen3Binstructbaseloramerged0_6500/

Original model description: --- base_model:

• —Qwen/Qwen2.5-3B-Instruct
• —kamruzzaman-asif/qwen-3Binstructbaseloramerged06500
• —Qwen/Qwen2.5-3B library_name: transformers tags:
• —mergekit
• —merge

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/Qwen2.5-3B as a base.

Models Merged

The following models were included in the merge:

• —Qwen/Qwen2.5-3B-Instruct
• —kamruzzaman-asif/qwen-3B_instruct_base_lora_merged_0_6500

Configuration

The following YAML configuration was used to produce this model:

base_model: Qwen/Qwen2.5-3B
dtype: bfloat16
merge_method: ties
models:
- model: kamruzzaman-asif/qwen-3B_instruct_base_lora_merged_0_6500
  parameters:
    density: 1
    weight: 1
- model: Qwen/Qwen2.5-3B-Instruct
  parameters:
    density: 1
    weight: 1
parameters:
  density: 1
  int8_mask: true
  normalize: true
  weight: 1
tokenizer_source: kamruzzaman-asif/qwen-3B_instruct_base_lora_merged_0_6500