impulse2000 / dolphin-2.8-experiment26

Experiment26模型的Dolphin版本（7B参数）

177 Pulls 4个月前更新

更新于 4 个月前

4 个月前

5cbd38d188b6 · 14GB

README

dolphin-2.8-experiment26-7b的Llamacpp量化

使用llama.cpp提交fa97464进行量化。

原始模型：https://hugging-face.cn/cognitivecomputations/dolphin-2.8-experiment26-7b

从下方下载文件（不是整个分支）

文件名	量化类型	文件大小	描述
dolphin-2.8-experiment26-7b-Q8_0.gguf	Q8_0	7.69GB	极其高质量，通常不需要但可用最大量化。
dolphin-2.8-experiment26-7b-Q6_K.gguf	Q6_K	5.94GB	非常高质量，接近完美，推荐。
dolphin-2.8-experiment26-7b-Q5_K_M.gguf	Q5_K_M	5.13GB	高质量，非常实用。
dolphin-2.8-experiment26-7b-Q5_K_S.gguf	Q5_K_S	4.99GB	高质量，非常实用。
dolphin-2.8-experiment26-7b-Q5_0.gguf	Q5_0	4.99GB	高质量，旧格式，通常不推荐。
dolphin-2.8-experiment26-7b-Q4_K_M.gguf	Q4_K_M	4.36GB	质量良好，与4.25 bpw相似。
dolphin-2.8-experiment26-7b-Q4_K_S.gguf	Q4_K_S	4.14GB	质量略低，但节省空间。
dolphin-2.8-experiment26-7b-Q4_0.gguf	Q4_0	4.10GB	质量尚可，旧格式，一般不推荐。
dolphin-2.8-experiment26-7b-Q3_K_L.gguf	Q3_K_L	3.82GB	质量较低但可用，适合RAM使用量低的情况。
dolphin-2.8-experiment26-7b-Q3_K_M.gguf	Q3_K_M	3.51GB	质量更低。
dolphin-2.8-experiment26-7b-Q3_K_S.gguf	Q3_K_S	3.16GB	质量低，不推荐。
dolphin-2.8-experiment26-7b-Q2_K.gguf	Q2_K	2.71GB	质量极低，不推荐。

想要支持我的工作？请访问我的ko-fi页面：[链接](https://ko-fi.com/bartowski)

## Llamacpp Quantizations of dolphin-2.8-experiment26-7b

Using <a href="https://github.com/ggerganov/llama.cpp/commit/fa974646e1a2024fc7dc9e6f27cf1f2f5d4a3763">llama.cpp commit fa97464</a> for quantization.

Original model: https://hugging-face.cn/cognitivecomputations/dolphin-2.8-experiment26-7b

Download a file (not the whole branch) from below:

| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [dolphin-2.8-experiment26-7b-Q8_0.gguf](https://hugging-face.cn/bartowski/dolphin-2.8-experiment26-7b-GGUF/blob/main/dolphin-2.8-experiment26-7b-Q8_0.gguf) | Q8_0 | 7.69GB | Extremely high quality, generally unneeded but max available quant. |
| [dolphin-2.8-experiment26-7b-Q6_K.gguf](https://hugging-face.cn/bartowski/dolphin-2.8-experiment26-7b-GGUF/blob/main/dolphin-2.8-experiment26-7b-Q6_K.gguf) | Q6_K | 5.94GB | Very high quality, near perfect, *recommended*. |
| [dolphin-2.8-experiment26-7b-Q5_K_M.gguf](https://hugging-face.cn/bartowski/dolphin-2.8-experiment26-7b-GGUF/blob/main/dolphin-2.8-experiment26-7b-Q5_K_M.gguf) | Q5_K_M | 5.13GB | High quality, very usable. |
| [dolphin-2.8-experiment26-7b-Q5_K_S.gguf](https://hugging-face.cn/bartowski/dolphin-2.8-experiment26-7b-GGUF/blob/main/dolphin-2.8-experiment26-7b-Q5_K_S.gguf) | Q5_K_S | 4.99GB | High quality, very usable. |
| [dolphin-2.8-experiment26-7b-Q5_0.gguf](https://hugging-face.cn/bartowski/dolphin-2.8-experiment26-7b-GGUF/blob/main/dolphin-2.8-experiment26-7b-Q5_0.gguf) | Q5_0 | 4.99GB | High quality, older format, generally not recommended. |
| [dolphin-2.8-experiment26-7b-Q4_K_M.gguf](https://hugging-face.cn/bartowski/dolphin-2.8-experiment26-7b-GGUF/blob/main/dolphin-2.8-experiment26-7b-Q4_K_M.gguf) | Q4_K_M | 4.36GB | Good quality, similar to 4.25 bpw. |
| [dolphin-2.8-experiment26-7b-Q4_K_S.gguf](https://hugging-face.cn/bartowski/dolphin-2.8-experiment26-7b-GGUF/blob/main/dolphin-2.8-experiment26-7b-Q4_K_S.gguf) | Q4_K_S | 4.14GB | Slightly lower quality with small space savings. |
| [dolphin-2.8-experiment26-7b-Q4_0.gguf](https://hugging-face.cn/bartowski/dolphin-2.8-experiment26-7b-GGUF/blob/main/dolphin-2.8-experiment26-7b-Q4_0.gguf) | Q4_0 | 4.10GB | Decent quality, older format, generally not recommended. |
| [dolphin-2.8-experiment26-7b-Q3_K_L.gguf](https://hugging-face.cn/bartowski/dolphin-2.8-experiment26-7b-GGUF/blob/main/dolphin-2.8-experiment26-7b-Q3_K_L.gguf) | Q3_K_L | 3.82GB | Lower quality but usable, good for low RAM availability. |
| [dolphin-2.8-experiment26-7b-Q3_K_M.gguf](https://hugging-face.cn/bartowski/dolphin-2.8-experiment26-7b-GGUF/blob/main/dolphin-2.8-experiment26-7b-Q3_K_M.gguf) | Q3_K_M | 3.51GB | Even lower quality. |
| [dolphin-2.8-experiment26-7b-Q3_K_S.gguf](https://hugging-face.cn/bartowski/dolphin-2.8-experiment26-7b-GGUF/blob/main/dolphin-2.8-experiment26-7b-Q3_K_S.gguf) | Q3_K_S | 3.16GB | Low quality, not recommended. |
| [dolphin-2.8-experiment26-7b-Q2_K.gguf](https://hugging-face.cn/bartowski/dolphin-2.8-experiment26-7b-GGUF/blob/main/dolphin-2.8-experiment26-7b-Q2_K.gguf) | Q2_K | 2.71GB | Extremely low quality, *not* recommended.

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)