Modelpublic

RichardErkhov/Hi-Q_-_krx_qwen_2.5-7b-it_1104-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face

0likes433downloads

Model Card

Quantization made by Richard Erkhov.

Request more models

krxqwen2.5-7b-it_1104 - GGUF

—Model creator: https://huggingface.co/Hi-Q/
—Original model: https://huggingface.co/Hi-Q/krxqwen2.5-7b-it_1104/

Name	Quant method	Size
krx_qwen_2.5-7b-it_1104.Q2_K.gguf	Q2_K	2.81GB
krx_qwen_2.5-7b-it_1104.Q3_K_S.gguf	Q3KS	3.25GB
krx_qwen_2.5-7b-it_1104.Q3_K.gguf	Q3_K	3.55GB
krx_qwen_2.5-7b-it_1104.Q3_K_M.gguf	Q3KM	3.55GB
krx_qwen_2.5-7b-it_1104.Q3_K_L.gguf	Q3KL	3.81GB
krx_qwen_2.5-7b-it_1104.IQ4_XS.gguf	IQ4_XS	0.83GB
krx_qwen_2.5-7b-it_1104.Q4_0.gguf	Q4_0	4.13GB
krx_qwen_2.5-7b-it_1104.IQ4_NL.gguf	IQ4_NL	4.16GB
krx_qwen_2.5-7b-it_1104.Q4_K_S.gguf	Q4KS	4.15GB
krx_qwen_2.5-7b-it_1104.Q4_K.gguf	Q4_K	4.36GB
krx_qwen_2.5-7b-it_1104.Q4_K_M.gguf	Q4KM	4.36GB
krx_qwen_2.5-7b-it_1104.Q4_1.gguf	Q4_1	4.54GB
krx_qwen_2.5-7b-it_1104.Q5_0.gguf	Q5_0	4.95GB
krx_qwen_2.5-7b-it_1104.Q5_K_S.gguf	Q5KS	4.95GB
krx_qwen_2.5-7b-it_1104.Q5_K.gguf	Q5_K	5.07GB
krx_qwen_2.5-7b-it_1104.Q5_K_M.gguf	Q5KM	5.07GB
krx_qwen_2.5-7b-it_1104.Q5_1.gguf	Q5_1	5.36GB
krx_qwen_2.5-7b-it_1104.Q6_K.gguf	Q6_K	5.82GB
krx_qwen_2.5-7b-it_1104.Q8_0.gguf	Q8_0	7.54GB

Original model description: --- base_model: unsloth/Qwen2.5-7B-Instruct language:

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

Uploaded model

—Developed by: Hi-Q
—License: apache-2.0
—Finetuned from model : unsloth/Qwen2.5-7B-Instruct

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"/>