Quantization made by Richard Erkhov.

llama3-8B-DarkIdol-1.0 - GGUF

Model creator: https://huggingface.co/aifeifei798/
Original model: https://huggingface.co/aifeifei798/llama3-8B-DarkIdol-1.0/

Name	Quant method	Size
llama3-8B-DarkIdol-1.0.Q2_K.gguf	Q2_K	2.96GB
llama3-8B-DarkIdol-1.0.IQ3_XS.gguf	IQ3_XS	3.28GB
llama3-8B-DarkIdol-1.0.IQ3_S.gguf	IQ3_S	3.43GB
llama3-8B-DarkIdol-1.0.Q3_K_S.gguf	Q3_K_S	3.41GB
llama3-8B-DarkIdol-1.0.IQ3_M.gguf	IQ3_M	3.52GB
llama3-8B-DarkIdol-1.0.Q3_K.gguf	Q3_K	3.74GB
llama3-8B-DarkIdol-1.0.Q3_K_M.gguf	Q3_K_M	3.74GB
llama3-8B-DarkIdol-1.0.Q3_K_L.gguf	Q3_K_L	4.03GB
llama3-8B-DarkIdol-1.0.IQ4_XS.gguf	IQ4_XS	4.18GB
llama3-8B-DarkIdol-1.0.Q4_0.gguf	Q4_0	4.34GB
llama3-8B-DarkIdol-1.0.IQ4_NL.gguf	IQ4_NL	4.38GB
llama3-8B-DarkIdol-1.0.Q4_K_S.gguf	Q4_K_S	4.37GB
llama3-8B-DarkIdol-1.0.Q4_K.gguf	Q4_K	4.58GB
llama3-8B-DarkIdol-1.0.Q4_K_M.gguf	Q4_K_M	4.58GB
llama3-8B-DarkIdol-1.0.Q4_1.gguf	Q4_1	4.78GB
llama3-8B-DarkIdol-1.0.Q5_0.gguf	Q5_0	5.21GB
llama3-8B-DarkIdol-1.0.Q5_K_S.gguf	Q5_K_S	5.21GB
llama3-8B-DarkIdol-1.0.Q5_K.gguf	Q5_K	5.34GB
llama3-8B-DarkIdol-1.0.Q5_K_M.gguf	Q5_K_M	5.34GB
llama3-8B-DarkIdol-1.0.Q5_1.gguf	Q5_1	5.65GB
llama3-8B-DarkIdol-1.0.Q6_K.gguf	Q6_K	6.14GB
llama3-8B-DarkIdol-1.0.Q8_0.gguf	Q8_0	7.95GB

Original model description:

license: llama3 language: - en - ja - zh tags: - roleplay - llama3 - sillytavern - idol

Special Thanks:

Lewdiculous's superb gguf version, thank you for your conscientious and responsible dedication.
https://huggingface.co/Lewdiculous/llama3-8B-DarkIdol-1.0-GGUF-IQ-Imatrix-Request

Model Description:

The module combination has been readjusted to better fulfill various roles and has been adapted for mobile phones.

DarkIdol:Roles that you can imagine and those that you cannot imagine.
Roleplay
Specialized in various role-playing scenarios
more look at test role. (https://huggingface.co/aifeifei798/llama3-8B-DarkIdol-1.0/resolve/main/DarkIdol_test_openai_api_lmstudio.py?download=true)

Model Use

Koboldcpp https://github.com/LostRuins/koboldcpp
LM Studio https://lmstudio.ai/
llama.cpp https://github.com/ggerganov/llama.cpp
Meet Layla,Layla is an AI chatbot that runs offline on your device.No internet connection required.No censorship.Complete privacy.Layla Lite https://www.layla-network.ai/
Layla Lite llama3-8B-DarkIdol-1.0-Q4_K_S-imat.gguf https://huggingface.co/Lewdiculous/llama3-8B-DarkIdol-1.0-GGUF-IQ-Imatrix-Request/blob/main/llama3-8B-DarkIdol-1.0-Q4_K_S-imat.gguf?download=true
more gguf at https://huggingface.co/Lewdiculous/llama3-8B-DarkIdol-1.0-GGUF-IQ-Imatrix-Request

character

If you want to use vision functionality:

You must use the latest versions of Koboldcpp.

To use the multimodal capabilities of this model and use vision you need to load the specified mmproj file, this can be found inside this model repo. Llava MMProj

You can load the mmproj by using the corresponding section in the interface:

Thank you:

To the authors for their hard work, which has given me more options to easily create what I want. Thank you for your efforts. - Hastagaras/Halu-8B-Llama3-Blackroot - Gryphe/Pantheon-RP-1.0-8b-Llama-3 - cgato/L3-TheSpice-8b-v0.8.3 - ChaoticNeutrals/Poppy_Porpoise-1.4-L3-8B - mergekit - merge - transformers - llama - .........

llama3-8B-DarkIdol-1.0

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Model Stock merge method using Hastagaras/Halu-8B-Llama3-Blackroot as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Gryphe/Pantheon-RP-1.0-8b-Llama-3
  - model: ChaoticNeutrals/Poppy_Porpoise-1.4-L3-8B
  - model: cgato/L3-TheSpice-8b-v0.8.3
merge_method: model_stock
base_model: Hastagaras/Halu-8B-Llama3-Blackroot
dtype: bfloat16