RichardErkhov/bunnycore_-_Qwen-2.5-3b-RP-awq

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Qwen-2.5-3b-RP - AWQ

• Model creator: https://huggingface.co/bunnycore/
• Original model: https://huggingface.co/bunnycore/Qwen-2.5-3b-RP/

Original model description:

base_model:

• Replete-AI/Replete-LLM-V2.5-Qwen-3b
• bunnycore/qwen-2.5-3b-lora_model
• unsloth/Qwen2.5-3B-Instruct
• bunnycore/qwen-2.5-3b-lora_model
• Replete-AI/Replete-LLM-V2.5-Qwen-3b 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 DARE TIES merge method using Replete-AI/Replete-LLM-V2.5-Qwen-3b as a base.

Models Merged

The following models were included in the merge:

• Replete-AI/Replete-LLM-V2.5-Qwen-3b + bunnycore/qwen-2.5-3b-lora_model
• unsloth/Qwen2.5-3B-Instruct + bunnycore/qwen-2.5-3b-lora_model

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Replete-AI/Replete-LLM-V2.5-Qwen-3b+bunnycore/qwen-2.5-3b-lora_model
    parameters:
      density: 0.5
      weight: 0.5
  - model: unsloth/Qwen2.5-3B-Instruct+bunnycore/qwen-2.5-3b-lora_model
    parameters:
      density: 0.5
      weight: 0.5

merge_method: dare_ties
base_model: Replete-AI/Replete-LLM-V2.5-Qwen-3b
parameters:
  normalize: false
  int8_mask: true
dtype: float16