unsloth_-_gemma-7b-it-gguf

RichardErkhov/unsloth_-_gemma-7b-it-gguf

unsloth_-_gemma-7b-it-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

299

10% of all-time downloads

All-time downloads

Public

Repo size

70.7 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.gguf81.9 GB · 100%

At a glance

Access: Public
Created: Sep 8, 2024
Updated: Sep 8, 2024
SHA: e7ffc08a

Model card

From the Hugging Face model README

Quantization made by Richard Erkhov.

Github

Discord

Request more models

gemma-7b-it - GGUF

Model creator: https://huggingface.co/unsloth/
Original model: https://huggingface.co/unsloth/gemma-7b-it/

Name	Quant method	Size
gemma-7b-it.Q2_K.gguf	Q2_K	2.36GB
gemma-7b-it.IQ3_XS.gguf	IQ3_XS	2.55GB
gemma-7b-it.IQ3_S.gguf	IQ3_S	2.68GB
gemma-7b-it.Q3_K_S.gguf	Q3_K_S	2.68GB
gemma-7b-it.IQ3_M.gguf	IQ3_M	2.76GB
gemma-7b-it.Q3_K.gguf	Q3_K	2.91GB
gemma-7b-it.Q3_K_M.gguf	Q3_K_M	2.91GB
gemma-7b-it.Q3_K_L.gguf	Q3_K_L	3.11GB
gemma-7b-it.IQ4_XS.gguf	IQ4_XS	3.2GB
gemma-7b-it.Q4_0.gguf	Q4_0	3.32GB
gemma-7b-it.IQ4_NL.gguf	IQ4_NL	3.34GB
gemma-7b-it.Q4_K_S.gguf	Q4_K_S	3.35GB
gemma-7b-it.Q4_K.gguf	Q4_K	3.49GB
gemma-7b-it.Q4_K_M.gguf	Q4_K_M	3.49GB
gemma-7b-it.Q4_1.gguf	Q4_1	3.62GB
gemma-7b-it.Q5_0.gguf	Q5_0	3.92GB
gemma-7b-it.Q5_K_S.gguf	Q5_K_S	3.92GB
gemma-7b-it.Q5_K.gguf	Q5_K	4.01GB
gemma-7b-it.Q5_K_M.gguf	Q5_K_M	4.01GB
gemma-7b-it.Q5_1.gguf	Q5_1	4.22GB
gemma-7b-it.Q6_K.gguf	Q6_K	4.56GB
gemma-7b-it.Q8_0.gguf	Q8_0	5.9GB

Original model description:

language:

en library_name: transformers license: apache-2.0 tags:
unsloth
transformers
gemma
gemma-7b

Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!

✨ Finetune for Free

All notebooks are beginner friendly! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face.

Unsloth supports	Free Notebooks	Performance	Memory use
Gemma 7b	▶️ Start on Colab	2.4x faster	58% less
Mistral 7b	▶️ Start on Colab	2.2x faster	62% less
Llama-2 7b	▶️ Start on Colab	2.2x faster	43% less
TinyLlama	▶️ Start on Colab	3.9x faster	74% less
CodeLlama 34b A100	▶️ Start on Colab	1.9x faster	27% less
Mistral 7b 1xT4	▶️ Start on Kaggle	5x faster*	62% less
DPO - Zephyr	▶️ Start on Colab	1.9x faster	19% less

This conversational notebook is useful for ShareGPT ChatML / Vicuna templates.
This text completion notebook is for raw text. This DPO notebook replicates Zephyr.
* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.

Created: Sep 8, 2024
Updated: Sep 8, 2024