Downloads · 30 days
39
1% of all-time downloads
seb-c_-_Psydestroyer-20B-gguf
RichardErkhov/seb-c_-_Psydestroyer-20B-gguf
seb-c_-_Psydestroyer-20B-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
4K
Public
Repo size
137 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf147 GB · 100%
At a glance
- Access
- Public
- Created
- Jun 6, 2024
- Updated
- Jun 7, 2024
- SHA
- b4b85562
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Psydestroyer-20B - GGUF
- Model creator: https://huggingface.co/seb-c/
- Original model: https://huggingface.co/seb-c/Psydestroyer-20B/
| Name | Quant method | Size |
|---|---|---|
| Psydestroyer-20B.Q2_K.gguf | Q2_K | 6.91GB |
| Psydestroyer-20B.IQ3_XS.gguf | IQ3_XS | 7.63GB |
| Psydestroyer-20B.IQ3_S.gguf | IQ3_S | 8.06GB |
| Psydestroyer-20B.Q3_K_S.gguf | Q3_K_S | 8.06GB |
| Psydestroyer-20B.IQ3_M.gguf | IQ3_M | 8.53GB |
| Psydestroyer-20B.Q3_K.gguf | Q3_K | 9.04GB |
| Psydestroyer-20B.Q3_K_M.gguf | Q3_K_M | 9.04GB |
| Psydestroyer-20B.Q3_K_L.gguf | Q3_K_L | 9.9GB |
| Psydestroyer-20B.IQ4_XS.gguf | IQ4_XS | 10.01GB |
| Psydestroyer-20B.Q4_0.gguf | Q4_0 | 10.52GB |
| Psydestroyer-20B.IQ4_NL.gguf | IQ4_NL | 10.57GB |
| Psydestroyer-20B.Q4_K_S.gguf | Q4_K_S | 10.59GB |
| Psydestroyer-20B.Q4_K.gguf | Q4_K | 6.58GB |
| Psydestroyer-20B.Q4_K_M.gguf | Q4_K_M | 3.59GB |
| Psydestroyer-20B.Q4_1.gguf | Q4_1 | 3.36GB |
| Psydestroyer-20B.Q5_0.gguf | Q5_0 | 3.2GB |
| Psydestroyer-20B.Q5_K_S.gguf | Q5_K_S | 2.54GB |
| Psydestroyer-20B.Q5_K.gguf | Q5_K | 1.91GB |
| Psydestroyer-20B.Q5_K_M.gguf | Q5_K_M | 1.58GB |
| Psydestroyer-20B.Q5_1.gguf | Q5_1 | 1.44GB |
| Psydestroyer-20B.Q6_K.gguf | Q6_K | 1.74GB |
| Psydestroyer-20B.Q8_0.gguf | Q8_0 | 1.65GB |
Original model description:
base_model:
- KoboldAI/LLaMA2-13B-Psyfighter2 library_name: transformers license: llama2 tags:
- mergekit
- merge
Psydestroyer 20B
I self-merged KoboldAI's Psyfighter-13B to get a 20B model, hoping to make it smarter.
GGUFs: https://huggingface.co/seb-c/Psydestroyer-20B-GGUF I have only made a Q4_K_M as that is what I tend to use when running 20Bs on my 3060 12GB, but if the demand is there I can make more.
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the passthrough merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: "KoboldAI/LLaMA2-13B-Psyfighter2"
layer_range: [0, 16]
- sources:
- model: "KoboldAI/LLaMA2-13B-Psyfighter2"
layer_range: [8, 24]
- sources:
- model: "KoboldAI/LLaMA2-13B-Psyfighter2"
layer_range: [17, 32]
- sources:
- model: "KoboldAI/LLaMA2-13B-Psyfighter2"
layer_range: [25, 40]
merge_method: passthrough
dtype: float16
- Created
- Jun 6, 2024
- Updated
- Jun 7, 2024