RichardErkhov/ChaoticNeutrals_-_Hathor_RP-v.01-L3-8B-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Hathor_RP-v.01-L3-8B - GGUF

• Model creator: https://huggingface.co/ChaoticNeutrals/
• Original model: https://huggingface.co/ChaoticNeutrals/Hathor_RP-v.01-L3-8B/

Name	Quant method	Size
Hathor_RP-v.01-L3-8B.Q2_K.gguf	Q2_K	2.96GB
Hathor_RP-v.01-L3-8B.IQ3_XS.gguf	IQ3_XS	3.28GB
Hathor_RP-v.01-L3-8B.IQ3_S.gguf	IQ3_S	3.43GB
Hathor_RP-v.01-L3-8B.Q3_K_S.gguf	Q3_K_S	3.41GB
Hathor_RP-v.01-L3-8B.IQ3_M.gguf	IQ3_M	3.52GB
Hathor_RP-v.01-L3-8B.Q3_K.gguf	Q3_K	3.74GB
Hathor_RP-v.01-L3-8B.Q3_K_M.gguf	Q3_K_M	3.74GB
Hathor_RP-v.01-L3-8B.Q3_K_L.gguf	Q3_K_L	4.03GB
Hathor_RP-v.01-L3-8B.IQ4_XS.gguf	IQ4_XS	4.18GB
Hathor_RP-v.01-L3-8B.Q4_0.gguf	Q4_0	4.34GB
Hathor_RP-v.01-L3-8B.IQ4_NL.gguf	IQ4_NL	4.38GB
Hathor_RP-v.01-L3-8B.Q4_K_S.gguf	Q4_K_S	4.37GB
Hathor_RP-v.01-L3-8B.Q4_K.gguf	Q4_K	4.58GB
Hathor_RP-v.01-L3-8B.Q4_K_M.gguf	Q4_K_M	4.58GB
Hathor_RP-v.01-L3-8B.Q4_1.gguf	Q4_1	4.78GB
Hathor_RP-v.01-L3-8B.Q5_0.gguf	Q5_0	5.21GB
Hathor_RP-v.01-L3-8B.Q5_K_S.gguf	Q5_K_S	5.21GB
Hathor_RP-v.01-L3-8B.Q5_K.gguf	Q5_K	5.34GB
Hathor_RP-v.01-L3-8B.Q5_K_M.gguf	Q5_K_M	5.34GB
Hathor_RP-v.01-L3-8B.Q5_1.gguf	Q5_1	5.65GB
Hathor_RP-v.01-L3-8B.Q6_K.gguf	Q6_K	6.14GB
Hathor_RP-v.01-L3-8B.Q8_0.gguf	Q8_0	7.95GB

Original model description:

license: other language: - en

"Hathor-v0.1 is a model based on the LLaMA 3 architecture: Designed to seamlessly integrate the qualities of creativity, intelligence, and robust performance. Making it an ideal tool for a wide range of applications; such as creative writing, educational support and human/computer interaction."

Recomended ST Presets: Hathor Presets

Quants: From the boy Lewdiculus: https://huggingface.co/Lewdiculous/Hathor-L3-8B-v.01-GGUF-IQ-Imatrix

Quants: From Nitral-Ai: https://huggingface.co/Nitral-AI/Hathor-L3-8B-v.01-5bpw-exl2

Notes: Hathor is trained on 3 epochs of private rp data, synthetic opus instructons, a mix of light/classical novel data. (Heavily wip)