Quantization made by Richard Erkhov.

llama-2-7b - GGUF

Model creator: https://huggingface.co/unsloth/
Original model: https://huggingface.co/unsloth/llama-2-7b/

Name	Quant method	Size
llama-2-7b.Q2_K.gguf	Q2_K	2.36GB
llama-2-7b.IQ3_XS.gguf	IQ3_XS	2.6GB
llama-2-7b.IQ3_S.gguf	IQ3_S	2.75GB
llama-2-7b.Q3_K_S.gguf	Q3_K_S	2.75GB
llama-2-7b.IQ3_M.gguf	IQ3_M	2.9GB
llama-2-7b.Q3_K.gguf	Q3_K	3.07GB
llama-2-7b.Q3_K_M.gguf	Q3_K_M	3.07GB
llama-2-7b.Q3_K_L.gguf	Q3_K_L	3.35GB
llama-2-7b.IQ4_XS.gguf	IQ4_XS	3.4GB
llama-2-7b.Q4_0.gguf	Q4_0	3.56GB
llama-2-7b.IQ4_NL.gguf	IQ4_NL	3.58GB
llama-2-7b.Q4_K_S.gguf	Q4_K_S	3.59GB
llama-2-7b.Q4_K.gguf	Q4_K	3.8GB
llama-2-7b.Q4_K_M.gguf	Q4_K_M	3.8GB
llama-2-7b.Q4_1.gguf	Q4_1	3.95GB
llama-2-7b.Q5_0.gguf	Q5_0	4.33GB
llama-2-7b.Q5_K_S.gguf	Q5_K_S	4.33GB
llama-2-7b.Q5_K.gguf	Q5_K	4.45GB
llama-2-7b.Q5_K_M.gguf	Q5_K_M	4.45GB
llama-2-7b.Q5_1.gguf	Q5_1	4.72GB
llama-2-7b.Q6_K.gguf	Q6_K	5.15GB
llama-2-7b.Q8_0.gguf	Q8_0	6.67GB

Original model description:

language:

en license: apache-2.0 library_name: transformers tags:
unsloth
transformers
llama
llama-2

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

Directly quantized 4bit model with bitsandbytes.

We have a Google Colab Tesla T4 notebook for Llama 7b here: https://colab.research.google.com/drive/1lBzz5KeZJKXjvivbYvmGarix9Ao6Wxe5?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
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.