Downloads · 30 days
30
4% of all-time downloads
RichardErkhov/sakaltcommunity_-_slerpQwen-0002-gguf
sakaltcommunity_-_slerpQwen-0002-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
30
4% of all-time downloads
All-time downloads
703
Public
Repo size
21.1 GB
Likes
0
Public
Click a slice to open those files.
.gguf24.5 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
slerpQwen-0002 - GGUF
| Name | Quant method | Size |
|---|---|---|
| slerpQwen-0002.Q2_K.gguf | Q2_K | 0.7GB |
| slerpQwen-0002.IQ3_XS.gguf | IQ3_XS | 0.77GB |
| slerpQwen-0002.IQ3_S.gguf | IQ3_S | 0.8GB |
| slerpQwen-0002.Q3_K_S.gguf | Q3_K_S | 0.8GB |
| slerpQwen-0002.IQ3_M.gguf | IQ3_M | 0.82GB |
| slerpQwen-0002.Q3_K.gguf | Q3_K | 0.86GB |
| slerpQwen-0002.Q3_K_M.gguf | Q3_K_M | 0.86GB |
| slerpQwen-0002.Q3_K_L.gguf | Q3_K_L | 0.91GB |
| slerpQwen-0002.IQ4_XS.gguf | IQ4_XS | 0.96GB |
| slerpQwen-0002.Q4_0.gguf | Q4_0 | 0.99GB |
| slerpQwen-0002.IQ4_NL.gguf | IQ4_NL | 1.0GB |
| slerpQwen-0002.Q4_K_S.gguf | Q4_K_S | 1.0GB |
| slerpQwen-0002.Q4_K.gguf | Q4_K | 1.04GB |
| slerpQwen-0002.Q4_K_M.gguf | Q4_K_M | 1.04GB |
| slerpQwen-0002.Q4_1.gguf | Q4_1 | 1.08GB |
| slerpQwen-0002.Q5_0.gguf | Q5_0 | 1.17GB |
| slerpQwen-0002.Q5_K_S.gguf | Q5_K_S | 1.17GB |
| slerpQwen-0002.Q5_K.gguf | Q5_K | 1.2GB |
| slerpQwen-0002.Q5_K_M.gguf | Q5_K_M | 1.2GB |
| slerpQwen-0002.Q5_1.gguf | Q5_1 | 1.26GB |
| slerpQwen-0002.Q6_K.gguf | Q6_K | 1.36GB |
| slerpQwen-0002.Q8_0.gguf | Q8_0 | 1.76GB |
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:
slices:
- sources:
- model: Sakalti/Saba1.5-Pro
layer_range: [0, 28]
merge_method: slerp
base_model: Sakalti/Saba1.5-Pro
parameters:
t:
- value: 0.4
dtype: float16