You can deploy this model and start earning money today!

RichardErkhov/
unsloth_-_gemma-2-2b-it-exl2

Name: unsloth_-_gemma-2-2b-it-exl2
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

gemma-2-2b-it - EXL2

Model creator: https://huggingface.co/unsloth/
Original model: https://huggingface.co/unsloth/gemma-2-2b-it/

Available sizes

Branch	Bits	Description
8_0	8.0	Maximum quality that ExLlamaV2 can produce, near unquantized performance.
6_5	6.5	Very similar to 8.0, good tradeoff of size vs performance, recommended.
5_0	5.0	Slightly lower quality vs 6.5, but usable
4_25	4.25	GPTQ equivalent bits per weight, slightly higher quality.
3_5	3.5	Lower quality, only use if you have to.

Download instructions

With git:

git clone --single-branch --branch 6_5 https://huggingface.co/unsloth_-_gemma-2-2b-it-exl2 gemma-2-2b-it-6_5

With huggingface hub:

pip3 install huggingface-hub

To download a specific branch, use the --revision parameter. For example, to download the 6.5 bpw branch: Linux:

huggingface-cli download unsloth_-_gemma-2-2b-it-exl2 --revision 6_5 --local-dir gemma-2-2b-it-6_5 --local-dir-use-symlinks False

Windows (which apparently doesn't like _ in folders sometimes?):

huggingface-cli download unsloth_-_gemma-2-2b-it-exl2 --revision 6_5 --local-dir gemma-2-2b-it-6.5 --local-dir-use-symlinks False

Original model description:

language:

en library_name: transformers license: gemma tags:
unsloth
transformers
gemma2
gemma

Finetune Gemma 2, Llama 3.1, Mistral 2-5x faster with 70% less memory via Unsloth!

Directly quantized 4bit model with bitsandbytes.

We have a Google Colab Tesla T4 notebook for Gemma 2 (2B) here: https://colab.research.google.com/drive/1weTpKOjBZxZJ5PQ-Ql8i6ptAY2x-FWVA?usp=sharing

We have a Google Colab Tesla T4 notebook for Gemma 2 (9B) here: https://colab.research.google.com/drive/1vIrqH5uYDQwsJ4-OO3DErvuv4pBgVwk4?usp=sharing

✨ 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
Llama 3 (8B)	▶️ Start on Colab	2.4x faster	58% less
Gemma 2 (9B)	▶️ Start on Colab	2x faster	63% less
Mistral (9B)	▶️ Start on Colab	2.2x faster	62% less
Phi 3 (mini)	▶️ Start on Colab	2x faster	63% 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.

RichardErkhov/unsloth_-_gemma-2-2b-it-exl2