Quantization made by Richard Erkhov.
Sina-Loki-7b-Merge - GGUF
- Model creator: https://huggingface.co/Azazelle/
- Original model: https://huggingface.co/Azazelle/Sina-Loki-7b-Merge/
| Name | Quant method | Size |
|---|---|---|
| Sina-Loki-7b-Merge.Q2_K.gguf | Q2_K | 2.53GB |
| Sina-Loki-7b-Merge.IQ3_XS.gguf | IQ3_XS | 2.81GB |
| Sina-Loki-7b-Merge.IQ3_S.gguf | IQ3_S | 2.96GB |
| Sina-Loki-7b-Merge.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| Sina-Loki-7b-Merge.IQ3_M.gguf | IQ3_M | 3.06GB |
| Sina-Loki-7b-Merge.Q3_K.gguf | Q3_K | 3.28GB |
| Sina-Loki-7b-Merge.Q3_K_M.gguf | Q3_K_M | 3.28GB |
| Sina-Loki-7b-Merge.Q3_K_L.gguf | Q3_K_L | 3.56GB |
| Sina-Loki-7b-Merge.IQ4_XS.gguf | IQ4_XS | 3.67GB |
| Sina-Loki-7b-Merge.Q4_0.gguf | Q4_0 | 3.83GB |
| Sina-Loki-7b-Merge.IQ4_NL.gguf | IQ4_NL | 3.87GB |
| Sina-Loki-7b-Merge.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| Sina-Loki-7b-Merge.Q4_K.gguf | Q4_K | 4.07GB |
| Sina-Loki-7b-Merge.Q4_K_M.gguf | Q4_K_M | 4.07GB |
| Sina-Loki-7b-Merge.Q4_1.gguf | Q4_1 | 4.24GB |
| Sina-Loki-7b-Merge.Q5_0.gguf | Q5_0 | 4.65GB |
| Sina-Loki-7b-Merge.Q5_K_S.gguf | Q5_K_S | 4.65GB |
| Sina-Loki-7b-Merge.Q5_K.gguf | Q5_K | 4.78GB |
| Sina-Loki-7b-Merge.Q5_K_M.gguf | Q5_K_M | 4.78GB |
| Sina-Loki-7b-Merge.Q5_1.gguf | Q5_1 | 5.07GB |
| Sina-Loki-7b-Merge.Q6_K.gguf | Q6_K | 5.53GB |
| Sina-Loki-7b-Merge.Q8_0.gguf | Q8_0 | 7.17GB |
Original model description:
pipeline_tag: text-generation tags: - mistral - merge license: cc-by-4.0
Model Card for Sina-Loki-7b-Merge
Part of a series of experimental DARE merges.
.yaml file for mergekit
models:
- model: RatanRohith/SRBOSGPT-7B-slerp
# no parameters necessary for base model
- model: rishiraj/smol-7b #75
parameters:
weight: 0.2
density: 0.41
- model: SanjiWatsuki/openchat-3.5-1210-starling-slerp #125
parameters:
weight: 0.33
density: 0.54
- model: Azazelle/Dumb-Maidlet #200
parameters:
weight: 0.53
density: 0.71
merge_method: dare_ties
base_model: RatanRohith/SRBOSGPT-7B-slerp
parameters:
int8_mask: true
dtype: bfloat16