Quantization made by Richard Erkhov.

Qwen-2.5-3b-Evol-CoT - GGUF

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

Name	Quant method	Size
Qwen-2.5-3b-Evol-CoT.Q2_K.gguf	Q2_K	1.28GB
Qwen-2.5-3b-Evol-CoT.IQ3_XS.gguf	IQ3_XS	1.42GB
Qwen-2.5-3b-Evol-CoT.IQ3_S.gguf	IQ3_S	1.48GB
Qwen-2.5-3b-Evol-CoT.Q3_K_S.gguf	Q3_K_S	1.48GB
Qwen-2.5-3b-Evol-CoT.IQ3_M.gguf	IQ3_M	1.51GB
Qwen-2.5-3b-Evol-CoT.Q3_K.gguf	Q3_K	1.61GB
Qwen-2.5-3b-Evol-CoT.Q3_K_M.gguf	Q3_K_M	1.61GB
Qwen-2.5-3b-Evol-CoT.Q3_K_L.gguf	Q3_K_L	1.71GB
Qwen-2.5-3b-Evol-CoT.IQ4_XS.gguf	IQ4_XS	1.79GB
Qwen-2.5-3b-Evol-CoT.Q4_0.gguf	Q4_0	1.86GB
Qwen-2.5-3b-Evol-CoT.IQ4_NL.gguf	IQ4_NL	1.87GB
Qwen-2.5-3b-Evol-CoT.Q4_K_S.gguf	Q4_K_S	1.87GB
Qwen-2.5-3b-Evol-CoT.Q4_K.gguf	Q4_K	1.96GB
Qwen-2.5-3b-Evol-CoT.Q4_K_M.gguf	Q4_K_M	1.96GB
Qwen-2.5-3b-Evol-CoT.Q4_1.gguf	Q4_1	2.04GB
Qwen-2.5-3b-Evol-CoT.Q5_0.gguf	Q5_0	2.22GB
Qwen-2.5-3b-Evol-CoT.Q5_K_S.gguf	Q5_K_S	2.22GB
Qwen-2.5-3b-Evol-CoT.Q5_K.gguf	Q5_K	2.27GB
Qwen-2.5-3b-Evol-CoT.Q5_K_M.gguf	Q5_K_M	2.27GB
Qwen-2.5-3b-Evol-CoT.Q5_1.gguf	Q5_1	2.4GB
Qwen-2.5-3b-Evol-CoT.Q6_K.gguf	Q6_K	2.6GB
Qwen-2.5-3b-Evol-CoT.Q8_0.gguf	Q8_0	3.37GB

Original model description:

base_model:

bunnycore/Qwen-2.5-3b-RP
Replete-AI/Replete-LLM-V2.5-Qwen-3b
bunnycore/Qwen-2.5-3b-Mix-Data-lora
bunnycore/Qwen-2.5-3b-RP
bunnycore/Qwen-2.5-3b-Mix-Data-lora 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 bunnycore/Qwen-2.5-3b-RP as a base.

Models Merged

The following models were included in the merge:

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-Mix-Data-lora
    parameters:
      density: 0.5
      weight: 0.5
  - model: bunnycore/Qwen-2.5-3b-RP+bunnycore/Qwen-2.5-3b-Mix-Data-lora
    parameters:
      density: 0.5
      weight: 0.5

merge_method: dare_ties
base_model: bunnycore/Qwen-2.5-3b-RP
parameters:
  normalize: false
  int8_mask: true
dtype: float16