Quantization made by Richard Erkhov.
Copium-Cola-9B - GGUF
- Model creator: https://huggingface.co/Nitral-AI/
- Original model: https://huggingface.co/Nitral-AI/Copium-Cola-9B/
Name | Quant method | Size |
---|---|---|
Copium-Cola-9B.Q2_K.gguf | Q2_K | 3.13GB |
Copium-Cola-9B.IQ3_XS.gguf | IQ3_XS | 3.48GB |
Copium-Cola-9B.IQ3_S.gguf | IQ3_S | 3.67GB |
Copium-Cola-9B.Q3_K_S.gguf | Q3_K_S | 3.65GB |
Copium-Cola-9B.IQ3_M.gguf | IQ3_M | 3.79GB |
Copium-Cola-9B.Q3_K.gguf | Q3_K | 4.05GB |
Copium-Cola-9B.Q3_K_M.gguf | Q3_K_M | 4.05GB |
Copium-Cola-9B.Q3_K_L.gguf | Q3_K_L | 4.41GB |
Copium-Cola-9B.IQ4_XS.gguf | IQ4_XS | 4.55GB |
Copium-Cola-9B.Q4_0.gguf | Q4_0 | 4.74GB |
Copium-Cola-9B.IQ4_NL.gguf | IQ4_NL | 4.79GB |
Copium-Cola-9B.Q4_K_S.gguf | Q4_K_S | 4.78GB |
Copium-Cola-9B.Q4_K.gguf | Q4_K | 5.04GB |
Copium-Cola-9B.Q4_K_M.gguf | Q4_K_M | 5.04GB |
Copium-Cola-9B.Q4_1.gguf | Q4_1 | 5.26GB |
Copium-Cola-9B.Q5_0.gguf | Q5_0 | 5.77GB |
Copium-Cola-9B.Q5_K_S.gguf | Q5_K_S | 5.77GB |
Copium-Cola-9B.Q5_K.gguf | Q5_K | 5.93GB |
Copium-Cola-9B.Q5_K_M.gguf | Q5_K_M | 5.93GB |
Copium-Cola-9B.Q5_1.gguf | Q5_1 | 6.29GB |
Copium-Cola-9B.Q6_K.gguf | Q6_K | 6.87GB |
Copium-Cola-9B.Q8_0.gguf | Q8_0 | 8.89GB |
Original model description:
base_model: - ChaoticNeutrals/Eris_7B library_name: transformers tags: - mergekit - merge license: other
This model was merged using the passthrough merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: ChaoticNeutrals/Eris_7B
layer_range: [0, 20]
- sources:
- model: ChaoticNeutrals/Eris_7B
layer_range: [12, 32]
merge_method: passthrough
dtype: float16