uploaded readme

f548727 verified 4 months ago

7.1 kB

	Quantization made by Richard Erkhov.

	[Github](https://github.com/RichardErkhov)

	[Discord](https://discord.gg/pvy7H8DZMG)

	[Request more models](https://github.com/RichardErkhov/quant_request)


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


	\| Name \| Quant method \| Size \|
	\| ---- \| ---- \| ---- \|
	\| [gemma-2-2b.Q2_K.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q2_K.gguf) \| Q2_K \| 1.15GB \|
	\| [gemma-2-2b.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.IQ3_XS.gguf) \| IQ3_XS \| 1.22GB \|
	\| [gemma-2-2b.IQ3_S.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.IQ3_S.gguf) \| IQ3_S \| 1.27GB \|
	\| [gemma-2-2b.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q3_K_S.gguf) \| Q3_K_S \| 1.27GB \|
	\| [gemma-2-2b.IQ3_M.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.IQ3_M.gguf) \| IQ3_M \| 1.3GB \|
	\| [gemma-2-2b.Q3_K.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q3_K.gguf) \| Q3_K \| 1.36GB \|
	\| [gemma-2-2b.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q3_K_M.gguf) \| Q3_K_M \| 1.36GB \|
	\| [gemma-2-2b.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q3_K_L.gguf) \| Q3_K_L \| 1.44GB \|
	\| [gemma-2-2b.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.IQ4_XS.gguf) \| IQ4_XS \| 1.47GB \|
	\| [gemma-2-2b.Q4_0.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q4_0.gguf) \| Q4_0 \| 1.52GB \|
	\| [gemma-2-2b.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.IQ4_NL.gguf) \| IQ4_NL \| 1.53GB \|
	\| [gemma-2-2b.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q4_K_S.gguf) \| Q4_K_S \| 1.53GB \|
	\| [gemma-2-2b.Q4_K.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q4_K.gguf) \| Q4_K \| 1.59GB \|
	\| [gemma-2-2b.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q4_K_M.gguf) \| Q4_K_M \| 1.59GB \|
	\| [gemma-2-2b.Q4_1.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q4_1.gguf) \| Q4_1 \| 1.64GB \|
	\| [gemma-2-2b.Q5_0.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q5_0.gguf) \| Q5_0 \| 1.75GB \|
	\| [gemma-2-2b.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q5_K_S.gguf) \| Q5_K_S \| 1.75GB \|
	\| [gemma-2-2b.Q5_K.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q5_K.gguf) \| Q5_K \| 1.79GB \|
	\| [gemma-2-2b.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q5_K_M.gguf) \| Q5_K_M \| 1.79GB \|
	\| [gemma-2-2b.Q5_1.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q5_1.gguf) \| Q5_1 \| 1.87GB \|
	\| [gemma-2-2b.Q6_K.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q6_K.gguf) \| Q6_K \| 2.0GB \|
	\| [gemma-2-2b.Q8_0.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q8_0.gguf) \| Q8_0 \| 2.59GB \|




	Original model description:
	---
	language:
	- en
	library_name: transformers
	license: gemma
	tags:
	- unsloth
	- transformers
	- gemma2
	- gemma
	---

	## Reminder to use the dev version Transformers:
	`pip install git+https://github.com/huggingface/transformers.git`

	# 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

	[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/Discord%20button.png" width="200"/>](https://discord.gg/u54VK8m8tk)
	[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/buy%20me%20a%20coffee%20button.png" width="200"/>](https://ko-fi.com/unsloth)
	[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/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 \|
	\|-----------------\|--------------------------------------------------------------------------------------------------------------------------\|-------------\|----------\|
	\| Llama 3 (8B) \| [▶️ Start on Colab](https://colab.research.google.com/drive/135ced7oHytdxu3N2DNe1Z0kqjyYIkDXp?usp=sharing) \| 2.4x faster \| 58% less \|
	\| Gemma 2 (9B) \| [▶️ Start on Colab](https://colab.research.google.com/drive/1vIrqH5uYDQwsJ4-OO3DErvuv4pBgVwk4?usp=sharing) \| 2x faster \| 63% less \|
	\| Mistral (9B) \| [▶️ Start on Colab](https://colab.research.google.com/drive/1Dyauq4kTZoLewQ1cApceUQVNcnnNTzg_?usp=sharing) \| 2.2x faster \| 62% less \|
	\| Phi 3 (mini) \| [▶️ Start on Colab](https://colab.research.google.com/drive/1lN6hPQveB_mHSnTOYifygFcrO8C1bxq4?usp=sharing) \| 2x faster \| 63% less \|
	\| TinyLlama \| [▶️ Start on Colab](https://colab.research.google.com/drive/1AZghoNBQaMDgWJpi4RbffGM1h6raLUj9?usp=sharing) \| 3.9x faster \| 74% less \|
	\| CodeLlama (34B) A100 \| [▶️ Start on Colab](https://colab.research.google.com/drive/1y7A0AxE3y8gdj4AVkl2aZX47Xu3P1wJT?usp=sharing) \| 1.9x faster \| 27% less \|
	\| Mistral (7B) 1xT4 \| [▶️ Start on Kaggle](https://www.kaggle.com/code/danielhanchen/kaggle-mistral-7b-unsloth-notebook) \| 5x faster\* \| 62% less \|
	\| DPO - Zephyr \| [▶️ Start on Colab](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) \| 1.9x faster \| 19% less \|

	- This [conversational notebook](https://colab.research.google.com/drive/1Aau3lgPzeZKQ-98h69CCu1UJcvIBLmy2?usp=sharing) is useful for ShareGPT ChatML / Vicuna templates.
	- This [text completion notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing) is for raw text. This [DPO notebook](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) replicates Zephyr.
	- \* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.

	Quantization made by Richard Erkhov.

	[Github](https://github.com/RichardErkhov)

	[Discord](https://discord.gg/pvy7H8DZMG)

	[Request more models](https://github.com/RichardErkhov/quant_request)


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


	\| Name \| Quant method \| Size \|
	\| ---- \| ---- \| ---- \|
	\| [gemma-2-2b.Q2_K.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q2_K.gguf) \| Q2_K \| 1.15GB \|
	\| [gemma-2-2b.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.IQ3_XS.gguf) \| IQ3_XS \| 1.22GB \|
	\| [gemma-2-2b.IQ3_S.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.IQ3_S.gguf) \| IQ3_S \| 1.27GB \|
	\| [gemma-2-2b.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q3_K_S.gguf) \| Q3_K_S \| 1.27GB \|
	\| [gemma-2-2b.IQ3_M.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.IQ3_M.gguf) \| IQ3_M \| 1.3GB \|
	\| [gemma-2-2b.Q3_K.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q3_K.gguf) \| Q3_K \| 1.36GB \|
	\| [gemma-2-2b.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q3_K_M.gguf) \| Q3_K_M \| 1.36GB \|
	\| [gemma-2-2b.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q3_K_L.gguf) \| Q3_K_L \| 1.44GB \|
	\| [gemma-2-2b.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.IQ4_XS.gguf) \| IQ4_XS \| 1.47GB \|
	\| [gemma-2-2b.Q4_0.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q4_0.gguf) \| Q4_0 \| 1.52GB \|
	\| [gemma-2-2b.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.IQ4_NL.gguf) \| IQ4_NL \| 1.53GB \|
	\| [gemma-2-2b.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q4_K_S.gguf) \| Q4_K_S \| 1.53GB \|
	\| [gemma-2-2b.Q4_K.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q4_K.gguf) \| Q4_K \| 1.59GB \|
	\| [gemma-2-2b.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q4_K_M.gguf) \| Q4_K_M \| 1.59GB \|
	\| [gemma-2-2b.Q4_1.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q4_1.gguf) \| Q4_1 \| 1.64GB \|
	\| [gemma-2-2b.Q5_0.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q5_0.gguf) \| Q5_0 \| 1.75GB \|
	\| [gemma-2-2b.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q5_K_S.gguf) \| Q5_K_S \| 1.75GB \|
	\| [gemma-2-2b.Q5_K.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q5_K.gguf) \| Q5_K \| 1.79GB \|
	\| [gemma-2-2b.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q5_K_M.gguf) \| Q5_K_M \| 1.79GB \|
	\| [gemma-2-2b.Q5_1.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q5_1.gguf) \| Q5_1 \| 1.87GB \|
	\| [gemma-2-2b.Q6_K.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q6_K.gguf) \| Q6_K \| 2.0GB \|
	\| [gemma-2-2b.Q8_0.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q8_0.gguf) \| Q8_0 \| 2.59GB \|




	Original model description:
	---
	language:
	- en
	library_name: transformers
	license: gemma
	tags:
	- unsloth
	- transformers
	- gemma2
	- gemma
	---

	## Reminder to use the dev version Transformers:
	`pip install git+https://github.com/huggingface/transformers.git`

	# 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

	[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/Discord%20button.png" width="200"/>](https://discord.gg/u54VK8m8tk)
	[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/buy%20me%20a%20coffee%20button.png" width="200"/>](https://ko-fi.com/unsloth)
	[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/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 \|
	\|-----------------\|--------------------------------------------------------------------------------------------------------------------------\|-------------\|----------\|
	\| Llama 3 (8B) \| [▶️ Start on Colab](https://colab.research.google.com/drive/135ced7oHytdxu3N2DNe1Z0kqjyYIkDXp?usp=sharing) \| 2.4x faster \| 58% less \|
	\| Gemma 2 (9B) \| [▶️ Start on Colab](https://colab.research.google.com/drive/1vIrqH5uYDQwsJ4-OO3DErvuv4pBgVwk4?usp=sharing) \| 2x faster \| 63% less \|
	\| Mistral (9B) \| [▶️ Start on Colab](https://colab.research.google.com/drive/1Dyauq4kTZoLewQ1cApceUQVNcnnNTzg_?usp=sharing) \| 2.2x faster \| 62% less \|
	\| Phi 3 (mini) \| [▶️ Start on Colab](https://colab.research.google.com/drive/1lN6hPQveB_mHSnTOYifygFcrO8C1bxq4?usp=sharing) \| 2x faster \| 63% less \|
	\| TinyLlama \| [▶️ Start on Colab](https://colab.research.google.com/drive/1AZghoNBQaMDgWJpi4RbffGM1h6raLUj9?usp=sharing) \| 3.9x faster \| 74% less \|
	\| CodeLlama (34B) A100 \| [▶️ Start on Colab](https://colab.research.google.com/drive/1y7A0AxE3y8gdj4AVkl2aZX47Xu3P1wJT?usp=sharing) \| 1.9x faster \| 27% less \|
	\| Mistral (7B) 1xT4 \| [▶️ Start on Kaggle](https://www.kaggle.com/code/danielhanchen/kaggle-mistral-7b-unsloth-notebook) \| 5x faster\* \| 62% less \|
	\| DPO - Zephyr \| [▶️ Start on Colab](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) \| 1.9x faster \| 19% less \|

	- This [conversational notebook](https://colab.research.google.com/drive/1Aau3lgPzeZKQ-98h69CCu1UJcvIBLmy2?usp=sharing) is useful for ShareGPT ChatML / Vicuna templates.
	- This [text completion notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing) is for raw text. This [DPO notebook](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) replicates Zephyr.
	- \* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.