Quantization made by Richard Erkhov.

Qwen-2.5-3b-Evol-CoT-V3 - GGUF

Model creator: https://huggingface.co/bunnycore/
Original model: https://huggingface.co/bunnycore/Qwen-2.5-3b-Evol-CoT-V3/

Name	Quant method	Size
Qwen-2.5-3b-Evol-CoT-V3.Q2_K.gguf	Q2_K	1.28GB
Qwen-2.5-3b-Evol-CoT-V3.IQ3_XS.gguf	IQ3_XS	1.42GB
Qwen-2.5-3b-Evol-CoT-V3.IQ3_S.gguf	IQ3_S	1.48GB
Qwen-2.5-3b-Evol-CoT-V3.Q3_K_S.gguf	Q3_K_S	1.48GB
Qwen-2.5-3b-Evol-CoT-V3.IQ3_M.gguf	IQ3_M	1.51GB
Qwen-2.5-3b-Evol-CoT-V3.Q3_K.gguf	Q3_K	1.61GB
Qwen-2.5-3b-Evol-CoT-V3.Q3_K_M.gguf	Q3_K_M	1.61GB
Qwen-2.5-3b-Evol-CoT-V3.Q3_K_L.gguf	Q3_K_L	1.71GB
Qwen-2.5-3b-Evol-CoT-V3.IQ4_XS.gguf	IQ4_XS	1.79GB
Qwen-2.5-3b-Evol-CoT-V3.Q4_0.gguf	Q4_0	1.86GB
Qwen-2.5-3b-Evol-CoT-V3.IQ4_NL.gguf	IQ4_NL	1.87GB
Qwen-2.5-3b-Evol-CoT-V3.Q4_K_S.gguf	Q4_K_S	1.87GB
Qwen-2.5-3b-Evol-CoT-V3.Q4_K.gguf	Q4_K	1.96GB
Qwen-2.5-3b-Evol-CoT-V3.Q4_K_M.gguf	Q4_K_M	1.96GB
Qwen-2.5-3b-Evol-CoT-V3.Q4_1.gguf	Q4_1	2.04GB
Qwen-2.5-3b-Evol-CoT-V3.Q5_0.gguf	Q5_0	2.22GB
Qwen-2.5-3b-Evol-CoT-V3.Q5_K_S.gguf	Q5_K_S	2.22GB
Qwen-2.5-3b-Evol-CoT-V3.Q5_K.gguf	Q5_K	2.27GB
Qwen-2.5-3b-Evol-CoT-V3.Q5_K_M.gguf	Q5_K_M	2.27GB
Qwen-2.5-3b-Evol-CoT-V3.Q5_1.gguf	Q5_1	2.4GB
Qwen-2.5-3b-Evol-CoT-V3.Q6_K.gguf	Q6_K	2.6GB
Qwen-2.5-3b-Evol-CoT-V3.Q8_0.gguf	Q8_0	3.37GB

Original model description:

base_model:

bunnycore/Qwen-2.5-3b-Evol-CoT
bunnycore/qwen-2.5-3b-lora_model
Qwen/Qwen2.5-3B
bunnycore/qwen-2.5-3b-lora_model
bunnycore/Qwen-2.5-3b-RP
bunnycore/Qwen-2.5-3b-Evol-CoT-v2
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 Model Stock merge method using Qwen/Qwen2.5-3B + bunnycore/qwen-2.5-3b-lora_model 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: bunnycore/Qwen-2.5-3b-Evol-CoT+bunnycore/qwen-2.5-3b-lora_model
  - model: bunnycore/Qwen-2.5-3b-RP
  - model: bunnycore/Qwen-2.5-3b-Evol-CoT-v2+bunnycore/Qwen-2.5-3b-Mix-Data-lora
merge_method: model_stock
base_model: Qwen/Qwen2.5-3B+bunnycore/qwen-2.5-3b-lora_model
parameters:
  normalize: false
  int8_mask: true
dtype: float16

Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more quants, at much higher speed, than I would otherwise be able to.