Modelpublic

RichardErkhov/OneAndOnly1_-_krx_qwen2.5_7b_it_v3-gguf

sourceHugging Faceupdated 1y agoView on Hugging Face

0likes298downloads

Model Card

Quantization made by Richard Erkhov.

Request more models

krxqwen2.57bitv3 - GGUF

—Model creator: https://huggingface.co/OneAndOnly1/
—Original model: https://huggingface.co/OneAndOnly1/krxqwen2.57bitv3/

Name	Quant method	Size
krx_qwen2.5_7b_it_v3.Q2_K.gguf	Q2_K	2.81GB
krx_qwen2.5_7b_it_v3.IQ3_XS.gguf	IQ3_XS	3.12GB
krx_qwen2.5_7b_it_v3.IQ3_S.gguf	IQ3_S	3.26GB
krx_qwen2.5_7b_it_v3.Q3_K_S.gguf	Q3KS	3.25GB
krx_qwen2.5_7b_it_v3.IQ3_M.gguf	IQ3_M	3.33GB
krx_qwen2.5_7b_it_v3.Q3_K.gguf	Q3_K	3.55GB
krx_qwen2.5_7b_it_v3.Q3_K_M.gguf	Q3KM	3.55GB
krx_qwen2.5_7b_it_v3.Q3_K_L.gguf	Q3KL	3.81GB
krx_qwen2.5_7b_it_v3.IQ4_XS.gguf	IQ4_XS	3.96GB
krx_qwen2.5_7b_it_v3.Q4_0.gguf	Q4_0	4.13GB
krx_qwen2.5_7b_it_v3.IQ4_NL.gguf	IQ4_NL	4.16GB
krx_qwen2.5_7b_it_v3.Q4_K_S.gguf	Q4KS	4.15GB
krx_qwen2.5_7b_it_v3.Q4_K.gguf	Q4_K	4.36GB
krx_qwen2.5_7b_it_v3.Q4_K_M.gguf	Q4KM	4.36GB
krx_qwen2.5_7b_it_v3.Q4_1.gguf	Q4_1	4.54GB
krx_qwen2.5_7b_it_v3.Q5_0.gguf	Q5_0	4.95GB
krx_qwen2.5_7b_it_v3.Q5_K_S.gguf	Q5KS	4.95GB
krx_qwen2.5_7b_it_v3.Q5_K.gguf	Q5_K	5.07GB
krx_qwen2.5_7b_it_v3.Q5_K_M.gguf	Q5KM	5.07GB
krx_qwen2.5_7b_it_v3.Q5_1.gguf	Q5_1	5.36GB
krx_qwen2.5_7b_it_v3.Q6_K.gguf	Q6_K	5.82GB
krx_qwen2.5_7b_it_v3.Q8_0.gguf	Q8_0	7.54GB

Original model description: --- base_model: unsloth/qwen2.5-7b-instruct-bnb-4bit language:

—en license: apache-2.0 tags:
—text-generation-inference
—transformers
—unsloth
—qwen2
—trl
—Krx
—krx ---

Uploaded model

—Developed by: OneAndOnly1
—License: apache-2.0
—Finetuned from model : unsloth/qwen2.5-7b-instruct-bnb-4bit

This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.

<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>