RichardErkhov/NeuralNovel_-_Llama-3-NeuralPaca-8b-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Llama-3-NeuralPaca-8b - GGUF

• Model creator: https://huggingface.co/NeuralNovel/
• Original model: https://huggingface.co/NeuralNovel/Llama-3-NeuralPaca-8b/

Name	Quant method	Size
Llama-3-NeuralPaca-8b.Q2_K.gguf	Q2_K	2.96GB
Llama-3-NeuralPaca-8b.IQ3_XS.gguf	IQ3_XS	3.28GB
Llama-3-NeuralPaca-8b.IQ3_S.gguf	IQ3_S	3.43GB
Llama-3-NeuralPaca-8b.Q3_K_S.gguf	Q3_K_S	3.41GB
Llama-3-NeuralPaca-8b.IQ3_M.gguf	IQ3_M	3.52GB
Llama-3-NeuralPaca-8b.Q3_K.gguf	Q3_K	3.74GB
Llama-3-NeuralPaca-8b.Q3_K_M.gguf	Q3_K_M	3.74GB
Llama-3-NeuralPaca-8b.Q3_K_L.gguf	Q3_K_L	4.03GB
Llama-3-NeuralPaca-8b.IQ4_XS.gguf	IQ4_XS	4.18GB
Llama-3-NeuralPaca-8b.Q4_0.gguf	Q4_0	4.34GB
Llama-3-NeuralPaca-8b.IQ4_NL.gguf	IQ4_NL	4.38GB
Llama-3-NeuralPaca-8b.Q4_K_S.gguf	Q4_K_S	4.37GB
Llama-3-NeuralPaca-8b.Q4_K.gguf	Q4_K	4.58GB
Llama-3-NeuralPaca-8b.Q4_K_M.gguf	Q4_K_M	4.58GB
Llama-3-NeuralPaca-8b.Q4_1.gguf	Q4_1	4.78GB
Llama-3-NeuralPaca-8b.Q5_0.gguf	Q5_0	5.21GB
Llama-3-NeuralPaca-8b.Q5_K_S.gguf	Q5_K_S	5.21GB
Llama-3-NeuralPaca-8b.Q5_K.gguf	Q5_K	5.34GB
Llama-3-NeuralPaca-8b.Q5_K_M.gguf	Q5_K_M	5.34GB
Llama-3-NeuralPaca-8b.Q5_1.gguf	Q5_1	5.65GB
Llama-3-NeuralPaca-8b.Q6_K.gguf	Q6_K	6.14GB
Llama-3-NeuralPaca-8b.Q8_0.gguf	Q8_0	7.95GB

Original model description:

thumbnail: "https://cdn-uploads.huggingface.co/production/uploads/645cfe4603fc86c46b3e46d1/njn9I-gHjyq0lMyjF0lZF.jpeg"

language: - en tags: - text-generation-inference - transformers - unsloth - llama - trl base_model: unsloth/llama-3-8b-bnb-4bit datasets: - tatsu-lab/alpaca

Llama-3-NeuralPaca-8b

In the light of a new dawn

• Developed by: NeuralNovel
• License: Llama-3
• Finetuned from model : unsloth/llama-3-8b-bnb-4bit
• Built with Meta LLAMA-3 :

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.