Quantization made by Richard Erkhov.

Opus-Samantha-Llama-3-8B - GGUF

Model creator: https://huggingface.co/macadeliccc/
Original model: https://huggingface.co/macadeliccc/Opus-Samantha-Llama-3-8B/

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

Original model description:

license: apache-2.0 datasets: - macadeliccc/opus_samantha

Opus-Samantha-Llama-3-8B

Trained on 1xA100

5/11/24: Model has been updated and performs much better

Process

Original Model: meta-llama/Meta-Llama-3-8B
Datatset: macadeliccc/opus_samantha

💻 Usage

!pip install -qU transformers torch

import transformers
import torch

model_id = "macadeliccc/Opus-Samantha-Llama-3-8B"

pipeline = transformers.pipeline(
pipeline("Hey how are you doing today?")