nbeerbower_-_phi3.5-gutenberg-4B-gguf

RichardErkhov/nbeerbower_-_phi3.5-gutenberg-4B-gguf

nbeerbower_-_phi3.5-gutenberg-4B-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

Downloads · 30 days

238

10% of all-time downloads

All-time downloads

2.3K

Public

Repo size

43.9 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.gguf51.1 GB · 100%

At a glance

Access: Public
Created: Oct 3, 2024
Updated: Oct 3, 2024
SHA: 199b6159

Model card

From the Hugging Face model README

Quantization made by Richard Erkhov.

Github

Discord

Request more models

phi3.5-gutenberg-4B - GGUF

Model creator: https://huggingface.co/nbeerbower/
Original model: https://huggingface.co/nbeerbower/phi3.5-gutenberg-4B/

Name	Quant method	Size
phi3.5-gutenberg-4B.Q2_K.gguf	Q2_K	1.32GB
phi3.5-gutenberg-4B.IQ3_XS.gguf	IQ3_XS	1.51GB
phi3.5-gutenberg-4B.IQ3_S.gguf	IQ3_S	1.57GB
phi3.5-gutenberg-4B.Q3_K_S.gguf	Q3_K_S	1.57GB
phi3.5-gutenberg-4B.IQ3_M.gguf	IQ3_M	1.73GB
phi3.5-gutenberg-4B.Q3_K.gguf	Q3_K	1.82GB
phi3.5-gutenberg-4B.Q3_K_M.gguf	Q3_K_M	1.82GB
phi3.5-gutenberg-4B.Q3_K_L.gguf	Q3_K_L	1.94GB
phi3.5-gutenberg-4B.IQ4_XS.gguf	IQ4_XS	1.93GB
phi3.5-gutenberg-4B.Q4_0.gguf	Q4_0	2.03GB
phi3.5-gutenberg-4B.IQ4_NL.gguf	IQ4_NL	2.04GB
phi3.5-gutenberg-4B.Q4_K_S.gguf	Q4_K_S	2.04GB
phi3.5-gutenberg-4B.Q4_K.gguf	Q4_K	2.23GB
phi3.5-gutenberg-4B.Q4_K_M.gguf	Q4_K_M	2.23GB
phi3.5-gutenberg-4B.Q4_1.gguf	Q4_1	2.24GB
phi3.5-gutenberg-4B.Q5_0.gguf	Q5_0	2.46GB
phi3.5-gutenberg-4B.Q5_K_S.gguf	Q5_K_S	2.46GB
phi3.5-gutenberg-4B.Q5_K.gguf	Q5_K	2.62GB
phi3.5-gutenberg-4B.Q5_K_M.gguf	Q5_K_M	2.62GB
phi3.5-gutenberg-4B.Q5_1.gguf	Q5_1	2.68GB
phi3.5-gutenberg-4B.Q6_K.gguf	Q6_K	2.92GB
phi3.5-gutenberg-4B.Q8_0.gguf	Q8_0	3.78GB

Original model description:

library_name: transformers base_model:

microsoft/Phi-3.5-mini-instruct datasets:
jondurbin/gutenberg-dpo-v0.1 license: mit

phi3.5-gutenberg-4B

microsoft/Phi-3.5-mini-instruct finetuned on jondurbin/gutenberg-dpo-v0.1.

Method

Finetuned using 2x RTX 4060 Ti for 3 epochs.

Fine-tune Llama 3 with ORPO

Created: Oct 3, 2024
Updated: Oct 3, 2024