Downloads · 30 days
61
9% of all-time downloads
CorticalStack_-_shadow-clown-7B-dare-gguf
RichardErkhov/CorticalStack_-_shadow-clown-7B-dare-gguf
CorticalStack_-_shadow-clown-7B-dare-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
701
Public
Repo size
82.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf95.2 GB · 100%
At a glance
- Access
- Public
- Created
- Sep 10, 2024
- Updated
- Sep 10, 2024
- SHA
- 42f77ba0
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
shadow-clown-7B-dare - GGUF
- Model creator: https://huggingface.co/CorticalStack/
- Original model: https://huggingface.co/CorticalStack/shadow-clown-7B-dare/
| Name | Quant method | Size |
|---|---|---|
| shadow-clown-7B-dare.Q2_K.gguf | Q2_K | 2.53GB |
| shadow-clown-7B-dare.IQ3_XS.gguf | IQ3_XS | 2.81GB |
| shadow-clown-7B-dare.IQ3_S.gguf | IQ3_S | 2.96GB |
| shadow-clown-7B-dare.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| shadow-clown-7B-dare.IQ3_M.gguf | IQ3_M | 3.06GB |
| shadow-clown-7B-dare.Q3_K.gguf | Q3_K | 3.28GB |
| shadow-clown-7B-dare.Q3_K_M.gguf | Q3_K_M | 3.28GB |
| shadow-clown-7B-dare.Q3_K_L.gguf | Q3_K_L | 3.56GB |
| shadow-clown-7B-dare.IQ4_XS.gguf | IQ4_XS | 3.67GB |
| shadow-clown-7B-dare.Q4_0.gguf | Q4_0 | 3.83GB |
| shadow-clown-7B-dare.IQ4_NL.gguf | IQ4_NL | 3.87GB |
| shadow-clown-7B-dare.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| shadow-clown-7B-dare.Q4_K.gguf | Q4_K | 4.07GB |
| shadow-clown-7B-dare.Q4_K_M.gguf | Q4_K_M | 4.07GB |
| shadow-clown-7B-dare.Q4_1.gguf | Q4_1 | 4.24GB |
| shadow-clown-7B-dare.Q5_0.gguf | Q5_0 | 4.65GB |
| shadow-clown-7B-dare.Q5_K_S.gguf | Q5_K_S | 4.65GB |
| shadow-clown-7B-dare.Q5_K.gguf | Q5_K | 4.78GB |
| shadow-clown-7B-dare.Q5_K_M.gguf | Q5_K_M | 4.78GB |
| shadow-clown-7B-dare.Q5_1.gguf | Q5_1 | 5.07GB |
| shadow-clown-7B-dare.Q6_K.gguf | Q6_K | 5.53GB |
| shadow-clown-7B-dare.Q8_0.gguf | Q8_0 | 7.17GB |
Original model description:
license: apache-2.0 tags:
- merge
- mergekit
- CorticalStack/pastiche-crown-clown-7b-dare-dpo
- CultriX/NeuralTrix-7B-dpo
- CorticalStack/neurotic-crown-clown-7b-ties
<img src="shadow_clown.png" alt="Shadow clown logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
shadow-clown-7B-dare
shadow-clown-7B-dare is a DARE merge of the following models using mergekit:
- CorticalStack/pastiche-crown-clown-7b-dare-dpo
- CultriX/NeuralTrix-7B-dpo
- CorticalStack/neurotic-crown-clown-7b-ties
See the paper Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch for more on the method.
🧩 Configuration
models:
- model: yam-peleg/Experiment26-7B
- model: CorticalStack/pastiche-crown-clown-7b-dare-dpo
parameters:
density: 0.52
weight: 0.4
- model: CultriX/NeuralTrix-7B-dpo
parameters:
density: 0.52
weight: 0.2
- model: CorticalStack/neurotic-crown-clown-7b-ties
parameters:
density: 0.52
weight: 0.3
merge_method: dare_ties
base_model: yam-peleg/Experiment26-7B
parameters:
int8_mask: true
dtype: bfloat16
- Created
- Sep 10, 2024
- Updated
- Sep 10, 2024