41 lines
2.9 KiB
Markdown
41 lines
2.9 KiB
Markdown
---
|
|
pipeline_tag: text-generation
|
|
tags:
|
|
- labradorite
|
|
- llama
|
|
- llama-2
|
|
- ibm
|
|
- lab
|
|
- labrador
|
|
- merlinite
|
|
license: llama2
|
|
license_link: https://ai.meta.com/llama/license/
|
|
language:
|
|
- en
|
|
quantized_by: bartowski
|
|
---
|
|
|
|
## Llamacpp Quantizations of labradorite-13b
|
|
|
|
Using <a href="https://github.com/ggerganov/llama.cpp/commit/fa974646e1a2024fc7dc9e6f27cf1f2f5d4a3763">llama.cpp commit fa97464</a> for quantization.
|
|
|
|
Original model: https://huggingface.co/ibm/labradorite-13b
|
|
|
|
Download a file (not the whole branch) from below:
|
|
|
|
| Filename | Quant type | File Size | Description |
|
|
| -------- | ---------- | --------- | ----------- |
|
|
| [labradorite-13b-Q8_0.gguf](https://huggingface.co/bartowski/labradorite-13b-GGUF/blob/main/labradorite-13b-Q8_0.gguf) | Q8_0 | 13.83GB | Extremely high quality, generally unneeded but max available quant. |
|
|
| [labradorite-13b-Q6_K.gguf](https://huggingface.co/bartowski/labradorite-13b-GGUF/blob/main/labradorite-13b-Q6_K.gguf) | Q6_K | 10.67GB | Very high quality, near perfect, *recommended*. |
|
|
| [labradorite-13b-Q5_K_M.gguf](https://huggingface.co/bartowski/labradorite-13b-GGUF/blob/main/labradorite-13b-Q5_K_M.gguf) | Q5_K_M | 9.22GB | High quality, very usable. |
|
|
| [labradorite-13b-Q5_K_S.gguf](https://huggingface.co/bartowski/labradorite-13b-GGUF/blob/main/labradorite-13b-Q5_K_S.gguf) | Q5_K_S | 8.97GB | High quality, very usable. |
|
|
| [labradorite-13b-Q5_0.gguf](https://huggingface.co/bartowski/labradorite-13b-GGUF/blob/main/labradorite-13b-Q5_0.gguf) | Q5_0 | 8.97GB | High quality, older format, generally not recommended. |
|
|
| [labradorite-13b-Q4_K_M.gguf](https://huggingface.co/bartowski/labradorite-13b-GGUF/blob/main/labradorite-13b-Q4_K_M.gguf) | Q4_K_M | 7.86GB | Good quality, similar to 4.25 bpw. |
|
|
| [labradorite-13b-Q4_K_S.gguf](https://huggingface.co/bartowski/labradorite-13b-GGUF/blob/main/labradorite-13b-Q4_K_S.gguf) | Q4_K_S | 7.42GB | Slightly lower quality with small space savings. |
|
|
| [labradorite-13b-Q4_0.gguf](https://huggingface.co/bartowski/labradorite-13b-GGUF/blob/main/labradorite-13b-Q4_0.gguf) | Q4_0 | 7.36GB | Decent quality, older format, generally not recommended. |
|
|
| [labradorite-13b-Q3_K_L.gguf](https://huggingface.co/bartowski/labradorite-13b-GGUF/blob/main/labradorite-13b-Q3_K_L.gguf) | Q3_K_L | 6.92GB | Lower quality but usable, good for low RAM availability. |
|
|
| [labradorite-13b-Q3_K_M.gguf](https://huggingface.co/bartowski/labradorite-13b-GGUF/blob/main/labradorite-13b-Q3_K_M.gguf) | Q3_K_M | 6.33GB | Even lower quality. |
|
|
| [labradorite-13b-Q3_K_S.gguf](https://huggingface.co/bartowski/labradorite-13b-GGUF/blob/main/labradorite-13b-Q3_K_S.gguf) | Q3_K_S | 5.65GB | Low quality, not recommended. |
|
|
| [labradorite-13b-Q2_K.gguf](https://huggingface.co/bartowski/labradorite-13b-GGUF/blob/main/labradorite-13b-Q2_K.gguf) | Q2_K | 4.85GB | Extremely low quality, *not* recommended.
|
|
|
|
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski |