Hugging Face's logo

bartowski
/
L3-Zodiac-8B-ORPO-Base-GGUF

Text Generation
Transformers
GGUF
English
text-generation-inference
unsloth
llama
trl
Inference Endpoints
Model card Files Community
bartowski commited on
Commit
f41731a
•
1 Parent(s): c0cddbc

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -38,7 +38,7 @@ No chat template specified so default is used. This may be incorrect, check orig
38
 
39
  | Filename | Quant type | File Size | Description |
40
  | -------- | ---------- | --------- | ----------- |
41
- | [L3-Zodiac-8B-ORPO-Base-Q8_1.gguf](https://huggingface.co/bartowski/L3-Zodiac-8B-ORPO-Base-GGUF//main/L3-Zodiac-8B-ORPO-Base-Q8_1.gguf) | Q8_1 | | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Extremely high quality, generally unneeded but max available quant. |
42
  | [L3-Zodiac-8B-ORPO-Base-Q8_0.gguf](https://huggingface.co/bartowski/L3-Zodiac-8B-ORPO-Base-GGUF/blob/main/L3-Zodiac-8B-ORPO-Base-Q8_0.gguf) | Q8_0 | 8.54GB | Extremely high quality, generally unneeded but max available quant. |
43
  | [L3-Zodiac-8B-ORPO-Base-Q6_K_L.gguf](https://huggingface.co/bartowski/L3-Zodiac-8B-ORPO-Base-GGUF/blob/main/L3-Zodiac-8B-ORPO-Base-Q6_K_L.gguf) | Q6_K_L | 7.83GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Very high quality, near perfect, *recommended*. |
44
  | [L3-Zodiac-8B-ORPO-Base-Q6_K.gguf](https://huggingface.co/bartowski/L3-Zodiac-8B-ORPO-Base-GGUF/blob/main/L3-Zodiac-8B-ORPO-Base-Q6_K.gguf) | Q6_K | 6.59GB | Very high quality, near perfect, *recommended*. |
 
38
 
39
  | Filename | Quant type | File Size | Description |
40
  | -------- | ---------- | --------- | ----------- |
41
+ | [L3-Zodiac-8B-ORPO-Base-Q8_0_L.gguf](https://huggingface.co/bartowski/L3-Zodiac-8B-ORPO-Base-GGUF/blob/main/L3-Zodiac-8B-ORPO-Base-Q8_0_L.gguf) | Q8_0_L | 9.53GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Extremely high quality, generally unneeded but max available quant. |
42
  | [L3-Zodiac-8B-ORPO-Base-Q8_0.gguf](https://huggingface.co/bartowski/L3-Zodiac-8B-ORPO-Base-GGUF/blob/main/L3-Zodiac-8B-ORPO-Base-Q8_0.gguf) | Q8_0 | 8.54GB | Extremely high quality, generally unneeded but max available quant. |
43
  | [L3-Zodiac-8B-ORPO-Base-Q6_K_L.gguf](https://huggingface.co/bartowski/L3-Zodiac-8B-ORPO-Base-GGUF/blob/main/L3-Zodiac-8B-ORPO-Base-Q6_K_L.gguf) | Q6_K_L | 7.83GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Very high quality, near perfect, *recommended*. |
44
  | [L3-Zodiac-8B-ORPO-Base-Q6_K.gguf](https://huggingface.co/bartowski/L3-Zodiac-8B-ORPO-Base-GGUF/blob/main/L3-Zodiac-8B-ORPO-Base-Q6_K.gguf) | Q6_K | 6.59GB | Very high quality, near perfect, *recommended*. |