README.md

Quantization made by Richard Erkhov.

Github

Discord

Request more models

PHI3-Medium-NLI-16bit - GGUF

• Model creator: https://huggingface.co/1-800-SHARED-TASKS/
• Original model: https://huggingface.co/1-800-SHARED-TASKS/PHI3-Medium-NLI-16bit/

Name	Quant method	Size
PHI3-Medium-NLI-16bit.Q2_K.gguf	Q2_K	4.85GB
PHI3-Medium-NLI-16bit.IQ3_XS.gguf	IQ3_XS	5.38GB
PHI3-Medium-NLI-16bit.IQ3_S.gguf	IQ3_S	5.68GB
PHI3-Medium-NLI-16bit.Q3_K_S.gguf	Q3_K_S	5.65GB
PHI3-Medium-NLI-16bit.IQ3_M.gguf	IQ3_M	5.87GB
PHI3-Medium-NLI-16bit.Q3_K.gguf	Q3_K	6.29GB
PHI3-Medium-NLI-16bit.Q3_K_M.gguf	Q3_K_M	6.29GB
PHI3-Medium-NLI-16bit.Q3_K_L.gguf	Q3_K_L	6.84GB
PHI3-Medium-NLI-16bit.IQ4_XS.gguf	IQ4_XS	7.06GB
PHI3-Medium-NLI-16bit.Q4_0.gguf	Q4_0	7.35GB
PHI3-Medium-NLI-16bit.IQ4_NL.gguf	IQ4_NL	7.44GB
PHI3-Medium-NLI-16bit.Q4_K_S.gguf	Q4_K_S	7.41GB
PHI3-Medium-NLI-16bit.Q4_K.gguf	Q4_K	7.83GB
PHI3-Medium-NLI-16bit.Q4_K_M.gguf	Q4_K_M	7.83GB
PHI3-Medium-NLI-16bit.Q4_1.gguf	Q4_1	8.16GB
PHI3-Medium-NLI-16bit.Q5_0.gguf	Q5_0	8.96GB
PHI3-Medium-NLI-16bit.Q5_K_S.gguf	Q5_K_S	8.96GB
PHI3-Medium-NLI-16bit.Q5_K.gguf	Q5_K	9.2GB
PHI3-Medium-NLI-16bit.Q5_K_M.gguf	Q5_K_M	9.2GB
PHI3-Medium-NLI-16bit.Q5_1.gguf	Q5_1	9.76GB
PHI3-Medium-NLI-16bit.Q6_K.gguf	Q6_K	10.67GB
PHI3-Medium-NLI-16bit.Q8_0.gguf	Q8_0	13.82GB

Original model description:

base_model: unsloth/phi-3-medium-4k-instruct-bnb-4bit language: - en license: apache-2.0 tags: - text-generation-inference - transformers - unsloth - mistral - trl - sft

Uploaded model

• Developed by: 1024m
• License: apache-2.0
• Finetuned from model : unsloth/phi-3-medium-4k-instruct-bnb-4bit

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