You can deploy this model and start earning money today!

RichardErkhov/
kamruzzaman-asif_-_mergekit-qwen_3B_instruct_base_lora_merged_0_6500-gguf

Name: kamruzzaman-asif_-_mergekit-qwen_3B_instruct_base_lora_merged_0_6500-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

mergekit-qwen_3B_instruct_base_lora_merged_0_6500 - GGUF

Model creator: https://huggingface.co/kamruzzaman-asif/
Original model: https://huggingface.co/kamruzzaman-asif/mergekit-qwen_3B_instruct_base_lora_merged_0_6500/

Name	Quant method	Size
mergekit-qwen_3B_instruct_base_lora_merged_0_6500.Q2_K.gguf	Q2_K	1.28GB
mergekit-qwen_3B_instruct_base_lora_merged_0_6500.IQ3_XS.gguf	IQ3_XS	1.42GB
mergekit-qwen_3B_instruct_base_lora_merged_0_6500.IQ3_S.gguf	IQ3_S	1.48GB
mergekit-qwen_3B_instruct_base_lora_merged_0_6500.Q3_K_S.gguf	Q3_K_S	1.48GB
mergekit-qwen_3B_instruct_base_lora_merged_0_6500.IQ3_M.gguf	IQ3_M	1.51GB
mergekit-qwen_3B_instruct_base_lora_merged_0_6500.Q3_K.gguf	Q3_K	1.61GB
mergekit-qwen_3B_instruct_base_lora_merged_0_6500.Q3_K_M.gguf	Q3_K_M	1.61GB
mergekit-qwen_3B_instruct_base_lora_merged_0_6500.Q3_K_L.gguf	Q3_K_L	1.71GB
mergekit-qwen_3B_instruct_base_lora_merged_0_6500.IQ4_XS.gguf	IQ4_XS	1.79GB
mergekit-qwen_3B_instruct_base_lora_merged_0_6500.Q4_0.gguf	Q4_0	1.86GB
mergekit-qwen_3B_instruct_base_lora_merged_0_6500.IQ4_NL.gguf	IQ4_NL	1.87GB
mergekit-qwen_3B_instruct_base_lora_merged_0_6500.Q4_K_S.gguf	Q4_K_S	1.87GB
mergekit-qwen_3B_instruct_base_lora_merged_0_6500.Q4_K.gguf	Q4_K	1.96GB
mergekit-qwen_3B_instruct_base_lora_merged_0_6500.Q4_K_M.gguf	Q4_K_M	1.96GB
mergekit-qwen_3B_instruct_base_lora_merged_0_6500.Q4_1.gguf	Q4_1	2.04GB
mergekit-qwen_3B_instruct_base_lora_merged_0_6500.Q5_0.gguf	Q5_0	2.22GB
mergekit-qwen_3B_instruct_base_lora_merged_0_6500.Q5_K_S.gguf	Q5_K_S	2.22GB
mergekit-qwen_3B_instruct_base_lora_merged_0_6500.Q5_K.gguf	Q5_K	2.27GB
mergekit-qwen_3B_instruct_base_lora_merged_0_6500.Q5_K_M.gguf	Q5_K_M	2.27GB
mergekit-qwen_3B_instruct_base_lora_merged_0_6500.Q5_1.gguf	Q5_1	2.4GB
mergekit-qwen_3B_instruct_base_lora_merged_0_6500.Q6_K.gguf	Q6_K	2.6GB
mergekit-qwen_3B_instruct_base_lora_merged_0_6500.Q8_0.gguf	Q8_0	3.37GB

Original model description:

base_model:

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

Configuration

The following YAML configuration was used to produce this model:

yaml

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

RichardErkhov/kamruzzaman-asif_-_mergekit-qwen_3B_instruct_base_lora_merged_0_6500-gguf