Downloads · 30 days
107
3% of all-time downloads
RichardErkhov/SzilviaB_-_Daring-Mythalion-13B-gguf
SzilviaB_-_Daring-Mythalion-13B-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.
Downloads · 30 days
107
3% of all-time downloads
All-time downloads
3.1K
Public
Repo size
116 GB
Likes
0
Public
Click a slice to open those files.
.gguf133 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Daring-Mythalion-13B - GGUF
| Name | Quant method | Size |
|---|---|---|
| Daring-Mythalion-13B.Q2_K.gguf | Q2_K | 4.52GB |
| Daring-Mythalion-13B.Q3_K_S.gguf | Q3_K_S | 3.03GB |
| Daring-Mythalion-13B.Q3_K.gguf | Q3_K | 0.56GB |
| Daring-Mythalion-13B.Q3_K_M.gguf | Q3_K_M | 1.2GB |
| Daring-Mythalion-13B.Q3_K_L.gguf | Q3_K_L | 6.45GB |
| Daring-Mythalion-13B.IQ4_XS.gguf | IQ4_XS | 3.59GB |
| Daring-Mythalion-13B.Q4_0.gguf | Q4_0 | 6.86GB |
| Daring-Mythalion-13B.IQ4_NL.gguf | IQ4_NL | 5.55GB |
| Daring-Mythalion-13B.Q4_K_S.gguf | Q4_K_S | 3.68GB |
| Daring-Mythalion-13B.Q4_K.gguf | Q4_K | 7.33GB |
| Daring-Mythalion-13B.Q4_K_M.gguf | Q4_K_M | 7.33GB |
| Daring-Mythalion-13B.Q4_1.gguf | Q4_1 | 7.61GB |
| Daring-Mythalion-13B.Q5_0.gguf | Q5_0 | 8.36GB |
| Daring-Mythalion-13B.Q5_K_S.gguf | Q5_K_S | 8.36GB |
| Daring-Mythalion-13B.Q5_K.gguf | Q5_K | 8.6GB |
| Daring-Mythalion-13B.Q5_K_M.gguf | Q5_K_M | 8.6GB |
| Daring-Mythalion-13B.Q5_1.gguf | Q5_1 | 9.1GB |
| Daring-Mythalion-13B.Q6_K.gguf | Q6_K | 9.95GB |
| Daring-Mythalion-13B.Q8_0.gguf | Q8_0 | 12.88GB |
base_model:
This is a merge of pre-trained language models created using mergekit.
This model was merged using the SLERP merge method.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: Kooten/DaringMaid-13B
- model: PygmalionAI/mythalion-13b
merge_method: slerp
base_model: Kooten/DaringMaid-13B
dtype: bfloat16
parameters:
t: [0, 0.5, 1, 0.5, 0] # V shaped curve: Hermes for input & output, WizardMath in the middle layers