bartowski commited on
Commit
9c5b946
1 Parent(s): 36016eb

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -30,7 +30,7 @@ All quants made using imatrix option with dataset from [here](https://gist.githu
30
  | -------- | ---------- | --------- | ----------- |
31
  | [MadWizard-SFT-v2-Mistral-7b-v0.3-Q8_1.gguf](https://huggingface.co/bartowski/MadWizard-SFT-v2-Mistral-7b-v0.3-GGUF/blob/main/MadWizard-SFT-v2-Mistral-7b-v0.3-Q8_1.gguf) | Q8_1 | 7.95GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Extremely high quality, generally unneeded but max available quant. |
32
  | [MadWizard-SFT-v2-Mistral-7b-v0.3-Q8_0.gguf](https://huggingface.co/bartowski/MadWizard-SFT-v2-Mistral-7b-v0.3-GGUF/blob/main/MadWizard-SFT-v2-Mistral-7b-v0.3-Q8_0.gguf) | Q8_0 | 7.70GB | Extremely high quality, generally unneeded but max available quant. |
33
- | [MadWizard-SFT-v2-Mistral-7b-v0.3-Q6_K_L.gguf](https://huggingface.co/bartowski/MadWizard-SFT-v2-Mistral-7b-v0.3-GGUF//main/MadWizard-SFT-v2-Mistral-7b-v0.3-Q6_K_L.gguf) | Q6_K_L | 6.26GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Very high quality, near perfect, *recommended*. |
34
  | [MadWizard-SFT-v2-Mistral-7b-v0.3-Q6_K.gguf](https://huggingface.co/bartowski/MadWizard-SFT-v2-Mistral-7b-v0.3-GGUF/blob/main/MadWizard-SFT-v2-Mistral-7b-v0.3-Q6_K.gguf) | Q6_K | 5.94GB | Very high quality, near perfect, *recommended*. |
35
  | [MadWizard-SFT-v2-Mistral-7b-v0.3-Q5_K_L.gguf](https://huggingface.co/bartowski/MadWizard-SFT-v2-Mistral-7b-v0.3-GGUF/blob/main/MadWizard-SFT-v2-Mistral-7b-v0.3-Q5_K_L.gguf) | Q5_K_L | 5.47GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. High quality, *recommended*. |
36
  | [MadWizard-SFT-v2-Mistral-7b-v0.3-Q5_K_M.gguf](https://huggingface.co/bartowski/MadWizard-SFT-v2-Mistral-7b-v0.3-GGUF/blob/main/MadWizard-SFT-v2-Mistral-7b-v0.3-Q5_K_M.gguf) | Q5_K_M | 5.13GB | High quality, *recommended*. |
 
30
  | -------- | ---------- | --------- | ----------- |
31
  | [MadWizard-SFT-v2-Mistral-7b-v0.3-Q8_1.gguf](https://huggingface.co/bartowski/MadWizard-SFT-v2-Mistral-7b-v0.3-GGUF/blob/main/MadWizard-SFT-v2-Mistral-7b-v0.3-Q8_1.gguf) | Q8_1 | 7.95GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Extremely high quality, generally unneeded but max available quant. |
32
  | [MadWizard-SFT-v2-Mistral-7b-v0.3-Q8_0.gguf](https://huggingface.co/bartowski/MadWizard-SFT-v2-Mistral-7b-v0.3-GGUF/blob/main/MadWizard-SFT-v2-Mistral-7b-v0.3-Q8_0.gguf) | Q8_0 | 7.70GB | Extremely high quality, generally unneeded but max available quant. |
33
+ | [MadWizard-SFT-v2-Mistral-7b-v0.3-Q6_K_L.gguf](https://huggingface.co/bartowski/MadWizard-SFT-v2-Mistral-7b-v0.3-GGUF/blob/main/MadWizard-SFT-v2-Mistral-7b-v0.3-Q6_K_L.gguf) | Q6_K_L | 6.26GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Very high quality, near perfect, *recommended*. |
34
  | [MadWizard-SFT-v2-Mistral-7b-v0.3-Q6_K.gguf](https://huggingface.co/bartowski/MadWizard-SFT-v2-Mistral-7b-v0.3-GGUF/blob/main/MadWizard-SFT-v2-Mistral-7b-v0.3-Q6_K.gguf) | Q6_K | 5.94GB | Very high quality, near perfect, *recommended*. |
35
  | [MadWizard-SFT-v2-Mistral-7b-v0.3-Q5_K_L.gguf](https://huggingface.co/bartowski/MadWizard-SFT-v2-Mistral-7b-v0.3-GGUF/blob/main/MadWizard-SFT-v2-Mistral-7b-v0.3-Q5_K_L.gguf) | Q5_K_L | 5.47GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. High quality, *recommended*. |
36
  | [MadWizard-SFT-v2-Mistral-7b-v0.3-Q5_K_M.gguf](https://huggingface.co/bartowski/MadWizard-SFT-v2-Mistral-7b-v0.3-GGUF/blob/main/MadWizard-SFT-v2-Mistral-7b-v0.3-Q5_K_M.gguf) | Q5_K_M | 5.13GB | High quality, *recommended*. |