nbeerbower_-_gemma2-gutenberg-27B-gguf

RichardErkhov/nbeerbower_-_gemma2-gutenberg-27B-gguf

nbeerbower_-_gemma2-gutenberg-27B-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

354

9% of all-time downloads

All-time downloads

4.1K

Public

Repo size

312 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.gguf361 GB · 100%

At a glance

Access: Public
Created: Sep 19, 2024
Updated: Sep 20, 2024
SHA: cf9d2315

Model card

From the Hugging Face model README

Quantization made by Richard Erkhov.

Github

Discord

Request more models

gemma2-gutenberg-27B - GGUF

Model creator: https://huggingface.co/nbeerbower/
Original model: https://huggingface.co/nbeerbower/gemma2-gutenberg-27B/

Name	Quant method	Size
gemma2-gutenberg-27B.Q2_K.gguf	Q2_K	9.73GB
gemma2-gutenberg-27B.IQ3_XS.gguf	IQ3_XS	10.76GB
gemma2-gutenberg-27B.IQ3_S.gguf	IQ3_S	11.33GB
gemma2-gutenberg-27B.Q3_K_S.gguf	Q3_K_S	11.33GB
gemma2-gutenberg-27B.IQ3_M.gguf	IQ3_M	11.6GB
gemma2-gutenberg-27B.Q3_K.gguf	Q3_K	12.5GB
gemma2-gutenberg-27B.Q3_K_M.gguf	Q3_K_M	12.5GB
gemma2-gutenberg-27B.Q3_K_L.gguf	Q3_K_L	13.52GB
gemma2-gutenberg-27B.IQ4_XS.gguf	IQ4_XS	13.92GB
gemma2-gutenberg-27B.Q4_0.gguf	Q4_0	14.56GB
gemma2-gutenberg-27B.IQ4_NL.gguf	IQ4_NL	14.65GB
gemma2-gutenberg-27B.Q4_K_S.gguf	Q4_K_S	14.66GB
gemma2-gutenberg-27B.Q4_K.gguf	Q4_K	15.5GB
gemma2-gutenberg-27B.Q4_K_M.gguf	Q4_K_M	15.5GB
gemma2-gutenberg-27B.Q4_1.gguf	Q4_1	16.07GB
gemma2-gutenberg-27B.Q5_0.gguf	Q5_0	17.59GB
gemma2-gutenberg-27B.Q5_K_S.gguf	Q5_K_S	17.59GB
gemma2-gutenberg-27B.Q5_K.gguf	Q5_K	18.08GB
gemma2-gutenberg-27B.Q5_K_M.gguf	Q5_K_M	18.08GB
gemma2-gutenberg-27B.Q5_1.gguf	Q5_1	19.1GB
gemma2-gutenberg-27B.Q6_K.gguf	Q6_K	20.81GB
gemma2-gutenberg-27B.Q8_0.gguf	Q8_0	26.95GB

Original model description:

license: gemma library_name: transformers base_model:

google/gemma-2-27b-it datasets:
jondurbin/gutenberg-dpo-v0.1

gemma2-gutenberg-27B

google/gemma-2-27b-it finetuned on jondurbin/gutenberg-dpo-v0.1.

Method

ORPO tuned with an 80GB A100 on RunPod (plz sponsor me) for 3 epochs.

Fine-tune Llama 3 with ORPO

Created: Sep 19, 2024
Updated: Sep 20, 2024