metadata
license: other
license_name: deepseek
license_link: https://huggingface.co./deepseek-ai/deepseek-coder-33b-base/blob/main/LICENSE
quantized_by: bartowski
pipeline_tag: text-generation
Llamacpp Quantizations of WhiteRabbitNeo-7B-v1.5a
Using llama.cpp release b2354 for quantization.
Original model: https://huggingface.co./WhiteRabbitNeo/WhiteRabbitNeo-7B-v1.5a
Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| WhiteRabbitNeo-7B-v1.5a-Q8_0.gguf | Q8_0 | 7.16GB | Extremely high quality, generally unneeded but max available quant. |
| WhiteRabbitNeo-7B-v1.5a-Q6_K.gguf | Q6_K | 5.53GB | Very high quality, near perfect, recommended. |
| WhiteRabbitNeo-7B-v1.5a-Q5_K_M.gguf | Q5_K_M | 4.78GB | High quality, very usable. |
| WhiteRabbitNeo-7B-v1.5a-Q5_K_S.gguf | Q5_K_S | 4.65GB | High quality, very usable. |
| WhiteRabbitNeo-7B-v1.5a-Q5_0.gguf | Q5_0 | 4.65GB | High quality, older format, generally not recommended. |
| WhiteRabbitNeo-7B-v1.5a-Q4_K_M.gguf | Q4_K_M | 4.08GB | Good quality, similar to 4.25 bpw. |
| WhiteRabbitNeo-7B-v1.5a-Q4_K_S.gguf | Q4_K_S | 3.85GB | Slightly lower quality with small space savings. |
| WhiteRabbitNeo-7B-v1.5a-Q4_0.gguf | Q4_0 | 3.82GB | Decent quality, older format, generally not recommended. |
| WhiteRabbitNeo-7B-v1.5a-Q3_K_L.gguf | Q3_K_L | 3.59GB | Lower quality but usable, good for low RAM availability. |
| WhiteRabbitNeo-7B-v1.5a-Q3_K_M.gguf | Q3_K_M | 3.29GB | Even lower quality. |
| WhiteRabbitNeo-7B-v1.5a-Q3_K_S.gguf | Q3_K_S | 2.94GB | Low quality, not recommended. |
| WhiteRabbitNeo-7B-v1.5a-Q2_K.gguf | Q2_K | 2.53GB | Extremely low quality, not recommended. |
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski