Downloads · 30 days
26
5% of all-time downloads
athirdpath_-_CleverMommy-mix-20b-gguf
RichardErkhov/athirdpath_-_CleverMommy-mix-20b-gguf
athirdpath_-_CleverMommy-mix-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
499
Public
Repo size
226 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf262 GB · 100%
At a glance
- Access
- Public
- Created
- Jun 2, 2024
- Updated
- Jun 2, 2024
- SHA
- 13a6369a
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
CleverMommy-mix-20b - GGUF
- Model creator: https://huggingface.co/athirdpath/
- Original model: https://huggingface.co/athirdpath/CleverMommy-mix-20b/
| Name | Quant method | Size |
|---|---|---|
| CleverMommy-mix-20b.Q2_K.gguf | Q2_K | 6.91GB |
| CleverMommy-mix-20b.IQ3_XS.gguf | IQ3_XS | 7.63GB |
| CleverMommy-mix-20b.IQ3_S.gguf | IQ3_S | 8.06GB |
| CleverMommy-mix-20b.Q3_K_S.gguf | Q3_K_S | 8.06GB |
| CleverMommy-mix-20b.IQ3_M.gguf | IQ3_M | 8.53GB |
| CleverMommy-mix-20b.Q3_K.gguf | Q3_K | 9.04GB |
| CleverMommy-mix-20b.Q3_K_M.gguf | Q3_K_M | 9.04GB |
| CleverMommy-mix-20b.Q3_K_L.gguf | Q3_K_L | 9.9GB |
| CleverMommy-mix-20b.IQ4_XS.gguf | IQ4_XS | 10.01GB |
| CleverMommy-mix-20b.Q4_0.gguf | Q4_0 | 10.52GB |
| CleverMommy-mix-20b.IQ4_NL.gguf | IQ4_NL | 10.57GB |
| CleverMommy-mix-20b.Q4_K_S.gguf | Q4_K_S | 10.59GB |
| CleverMommy-mix-20b.Q4_K.gguf | Q4_K | 11.22GB |
| CleverMommy-mix-20b.Q4_K_M.gguf | Q4_K_M | 11.22GB |
| CleverMommy-mix-20b.Q4_1.gguf | Q4_1 | 11.67GB |
| CleverMommy-mix-20b.Q5_0.gguf | Q5_0 | 12.83GB |
| CleverMommy-mix-20b.Q5_K_S.gguf | Q5_K_S | 12.83GB |
| CleverMommy-mix-20b.Q5_K.gguf | Q5_K | 13.18GB |
| CleverMommy-mix-20b.Q5_K_M.gguf | Q5_K_M | 13.18GB |
| CleverMommy-mix-20b.Q5_1.gguf | Q5_1 | 13.98GB |
| CleverMommy-mix-20b.Q6_K.gguf | Q6_K | 15.28GB |
| CleverMommy-mix-20b.Q8_0.gguf | Q8_0 | 19.79GB |
Original model description:
license: cc-by-nc-4.0
An extended part of my effort to create Eileithyia-20B. This model is made by following the recipe below, inverting it, then SLERPing the models back together at 0.5, hopefully fusing the models into one block for use with Harmonia.
slices:
- sources:
- model: microsoft/Orca-2-13b
- layer_range: [0, 16]
- sources:
- model: athirdpath/Eileithyia-13B
- layer_range: [8, 24]
- sources:
- model: microsoft/Orca-2-13b
- layer_range: [17, 32]
- sources:
- model: athirdpath/Eileithyia-13B
- layer_range: [25, 40]
merge_method: passthrough
dtype: float16
Thanks to Undi95 for pioneering the recipe.
- Created
- Jun 2, 2024
- Updated
- Jun 2, 2024