Downloads · 30 days
210
13% of all-time downloads
RichardErkhov/jpechg_-_Sour-Marcoro-12.5B-gguf
jpechg_-_Sour-Marcoro-12.5B-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
210
13% of all-time downloads
All-time downloads
1.6K
Public
Repo size
138 GB
Likes
0
Public
Click a slice to open those files.
.gguf160 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Sour-Marcoro-12.5B - GGUF
| Name | Quant method | Size |
|---|---|---|
| Sour-Marcoro-12.5B.Q2_K.gguf | Q2_K | 4.33GB |
| Sour-Marcoro-12.5B.IQ3_XS.gguf | IQ3_XS | 4.81GB |
| Sour-Marcoro-12.5B.IQ3_S.gguf | IQ3_S | 1.98GB |
| Sour-Marcoro-12.5B.Q3_K_S.gguf | Q3_K_S | 5.04GB |
| Sour-Marcoro-12.5B.IQ3_M.gguf | IQ3_M | 5.24GB |
| Sour-Marcoro-12.5B.Q3_K.gguf | Q3_K | 5.62GB |
| Sour-Marcoro-12.5B.Q3_K_M.gguf | Q3_K_M | 5.62GB |
| Sour-Marcoro-12.5B.Q3_K_L.gguf | Q3_K_L | 6.11GB |
| Sour-Marcoro-12.5B.IQ4_XS.gguf | IQ4_XS | 6.3GB |
| Sour-Marcoro-12.5B.Q4_0.gguf | Q4_0 | 6.57GB |
| Sour-Marcoro-12.5B.IQ4_NL.gguf | IQ4_NL | 6.64GB |
| Sour-Marcoro-12.5B.Q4_K_S.gguf | Q4_K_S | 6.62GB |
| Sour-Marcoro-12.5B.Q4_K.gguf | Q4_K | 6.99GB |
| Sour-Marcoro-12.5B.Q4_K_M.gguf | Q4_K_M | 6.99GB |
| Sour-Marcoro-12.5B.Q4_1.gguf | Q4_1 | 7.29GB |
| Sour-Marcoro-12.5B.Q5_0.gguf | Q5_0 | 8.01GB |
| Sour-Marcoro-12.5B.Q5_K_S.gguf | Q5_K_S | 8.01GB |
| Sour-Marcoro-12.5B.Q5_K.gguf | Q5_K | 8.22GB |
| Sour-Marcoro-12.5B.Q5_K_M.gguf | Q5_K_M | 8.22GB |
| Sour-Marcoro-12.5B.Q5_1.gguf | Q5_1 | 8.73GB |
| Sour-Marcoro-12.5B.Q6_K.gguf | Q6_K | 9.53GB |
| Sour-Marcoro-12.5B.Q8_0.gguf | Q8_0 | 12.35GB |
base_model:
This is a merge of pre-trained language models created using mergekit.
This model was merged using the passthrough merge method.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: Weyaxi/SauerkrautLM-UNA-SOLAR-Instruct
layer_range: [0, 32]
- sources:
- model: mlabonne/Marcoro14-7B-slerp
layer_range: [8, 32]
merge_method: passthrough
dtype: float16