RichardErkhov/ehristoforu_-_SoRu-0004-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

SoRu-0004 - GGUF

• Model creator: https://huggingface.co/ehristoforu/
• Original model: https://huggingface.co/ehristoforu/SoRu-0004/

Name	Quant method	Size
SoRu-0004.Q2_K.gguf	Q2_K	0.32GB
SoRu-0004.IQ3_XS.gguf	IQ3_XS	0.32GB
SoRu-0004.IQ3_S.gguf	IQ3_S	0.32GB
SoRu-0004.Q3_K_S.gguf	Q3_K_S	0.31GB
SoRu-0004.IQ3_M.gguf	IQ3_M	0.32GB
SoRu-0004.Q3_K.gguf	Q3_K	0.33GB
SoRu-0004.Q3_K_M.gguf	Q3_K_M	0.33GB
SoRu-0004.Q3_K_L.gguf	Q3_K_L	0.34GB
SoRu-0004.IQ4_XS.gguf	IQ4_XS	0.33GB
SoRu-0004.Q4_0.gguf	Q4_0	0.33GB
SoRu-0004.IQ4_NL.gguf	IQ4_NL	0.33GB
SoRu-0004.Q4_K_S.gguf	Q4_K_S	0.36GB
SoRu-0004.Q4_K.gguf	Q4_K	0.37GB
SoRu-0004.Q4_K_M.gguf	Q4_K_M	0.37GB
SoRu-0004.Q4_1.gguf	Q4_1	0.35GB
SoRu-0004.Q5_0.gguf	Q5_0	0.37GB
SoRu-0004.Q5_K_S.gguf	Q5_K_S	0.38GB
SoRu-0004.Q5_K.gguf	Q5_K	0.39GB
SoRu-0004.Q5_K_M.gguf	Q5_K_M	0.39GB
SoRu-0004.Q5_1.gguf	Q5_1	0.39GB
SoRu-0004.Q6_K.gguf	Q6_K	0.47GB
SoRu-0004.Q8_0.gguf	Q8_0	0.49GB

Original model description:

base_model: ehristoforu/SoRu-0003 tags: - text-generation-inference - transformers - unsloth - qwen2 - trl - sft license: apache-2.0 language: - en

Uploaded model

• Developed by: ehristoforu
• License: apache-2.0
• Finetuned from model : ehristoforu/SoRu-0003

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