Downloads · 30 days
141
2% of all-time downloads
KoboldAI_-_LLaMA2-13B-Erebus-v3-gguf
RichardErkhov/KoboldAI_-_LLaMA2-13B-Erebus-v3-gguf
KoboldAI_-_LLaMA2-13B-Erebus-v3-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
6.8K
Public
Repo size
147 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.gguf171 GB · 100%
At a glance
- Access
- Public
- Created
- Aug 11, 2024
- Updated
- Aug 11, 2024
- SHA
- 7b06e666
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
LLaMA2-13B-Erebus-v3 - GGUF
- Model creator: https://huggingface.co/KoboldAI/
- Original model: https://huggingface.co/KoboldAI/LLaMA2-13B-Erebus-v3/
| Name | Quant method | Size |
|---|---|---|
| LLaMA2-13B-Erebus-v3.Q2_K.gguf | Q2_K | 4.52GB |
| LLaMA2-13B-Erebus-v3.IQ3_XS.gguf | IQ3_XS | 4.99GB |
| LLaMA2-13B-Erebus-v3.IQ3_S.gguf | IQ3_S | 5.27GB |
| LLaMA2-13B-Erebus-v3.Q3_K_S.gguf | Q3_K_S | 5.27GB |
| LLaMA2-13B-Erebus-v3.IQ3_M.gguf | IQ3_M | 5.57GB |
| LLaMA2-13B-Erebus-v3.Q3_K.gguf | Q3_K | 5.9GB |
| LLaMA2-13B-Erebus-v3.Q3_K_M.gguf | Q3_K_M | 5.9GB |
| LLaMA2-13B-Erebus-v3.Q3_K_L.gguf | Q3_K_L | 6.45GB |
| LLaMA2-13B-Erebus-v3.IQ4_XS.gguf | IQ4_XS | 6.54GB |
| LLaMA2-13B-Erebus-v3.Q4_0.gguf | Q4_0 | 6.86GB |
| LLaMA2-13B-Erebus-v3.IQ4_NL.gguf | IQ4_NL | 6.9GB |
| LLaMA2-13B-Erebus-v3.Q4_K_S.gguf | Q4_K_S | 6.91GB |
| LLaMA2-13B-Erebus-v3.Q4_K.gguf | Q4_K | 7.33GB |
| LLaMA2-13B-Erebus-v3.Q4_K_M.gguf | Q4_K_M | 7.33GB |
| LLaMA2-13B-Erebus-v3.Q4_1.gguf | Q4_1 | 7.61GB |
| LLaMA2-13B-Erebus-v3.Q5_0.gguf | Q5_0 | 8.36GB |
| LLaMA2-13B-Erebus-v3.Q5_K_S.gguf | Q5_K_S | 8.36GB |
| LLaMA2-13B-Erebus-v3.Q5_K.gguf | Q5_K | 8.6GB |
| LLaMA2-13B-Erebus-v3.Q5_K_M.gguf | Q5_K_M | 8.6GB |
| LLaMA2-13B-Erebus-v3.Q5_1.gguf | Q5_1 | 9.1GB |
| LLaMA2-13B-Erebus-v3.Q6_K.gguf | Q6_K | 9.95GB |
| LLaMA2-13B-Erebus-v3.Q8_0.gguf | Q8_0 | 12.88GB |
Original model description:
license: llama2 license_name: llama-2 license_link: LICENSE language:
- en pipeline_tag: text-generation inference: false tags:
- pytorch
- llama
- llama-2
- finetuned
- not-for-all-audiences
LLaMA2-13B-Erebus
Model description
This is the third generation of the original Shinen made by Mr. Seeker. The full dataset consists of 8 different sources, all surrounding the "Adult" theme. The name "Erebus" comes from the greek mythology, also named "darkness". This is in line with Shin'en, or "deep abyss". For inquiries, please contact the KoboldAI community. Warning: THIS model is NOT suitable for use by minors. The model will output X-rated content.
Training procedure
LLaMA2-13B-Erebus was trained on 8x A6000 Ada GPU's for a single epoch. No special frameworks have been used.
Training data
The data can be divided in 8 different datasets:
- Literotica (everything with 3.0/5 or higher)
- Sexstories (everything with 70 or higher)
- Dataset-G (private dataset of X-rated stories)
- Doc's Lab (all stories)
- Lushstories (Editor's pick)
- Swinglifestyle (all stories)
- Pike-v2 Dataset (novels with "adult" rating)
- SoFurry (collection of various animals)
The dataset uses [Genre: <comma-separated list of genres>] for tagging.
The full dataset is 2.3B tokens in size.
Limitations and biases
Based on known problems with NLP technology, potential relevant factors include bias (gender, profession, race and religion). Warning: This model has a very strong NSFW bias!
- Created
- Aug 11, 2024
- Updated
- Aug 11, 2024