Hugging Face's logo

bartowski
/
MN-12B-Lyra-v1-GGUF

Text Generation
GGUF
English
Inference Endpoints
Model card Files Community
3
bartowski commited on
Commit
fbe6ac4
·
verified ·
1 Parent(s): 3f10325

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -1
README.md CHANGED
@@ -30,7 +30,6 @@ Adding ARM quants
30
  | Filename | Quant type | File Size | Split | Description |
31
  | -------- | ---------- | --------- | ----- | ----------- |
32
  | [MN-12B-Lyra-v1-f32.gguf](https://huggingface.co/bartowski/MN-12B-Lyra-v1-GGUF/blob/main/MN-12B-Lyra-v1-f32.gguf) | f32 | 49.00GB | false | Full F32 weights. |
33
- | [MN-12B-Lyra-v1-f32.gguf](https://huggingface.co/bartowski/MN-12B-Lyra-v1-GGUF/blob/main/MN-12B-Lyra-v1-f32.gguf) | f32 | 49.00GB | false | Full F32 weights. |
34
  | [MN-12B-Lyra-v1-Q8_0.gguf](https://huggingface.co/bartowski/MN-12B-Lyra-v1-GGUF/blob/main/MN-12B-Lyra-v1-Q8_0.gguf) | Q8_0 | 13.02GB | false | Extremely high quality, generally unneeded but max available quant. |
35
  | [MN-12B-Lyra-v1-Q6_K_L.gguf](https://huggingface.co/bartowski/MN-12B-Lyra-v1-GGUF/blob/main/MN-12B-Lyra-v1-Q6_K_L.gguf) | Q6_K_L | 10.38GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
36
  | [MN-12B-Lyra-v1-Q6_K.gguf](https://huggingface.co/bartowski/MN-12B-Lyra-v1-GGUF/blob/main/MN-12B-Lyra-v1-Q6_K.gguf) | Q6_K | 10.06GB | false | Very high quality, near perfect, *recommended*. |
 
30
  | Filename | Quant type | File Size | Split | Description |
31
  | -------- | ---------- | --------- | ----- | ----------- |
32
  | [MN-12B-Lyra-v1-f32.gguf](https://huggingface.co/bartowski/MN-12B-Lyra-v1-GGUF/blob/main/MN-12B-Lyra-v1-f32.gguf) | f32 | 49.00GB | false | Full F32 weights. |
 
33
  | [MN-12B-Lyra-v1-Q8_0.gguf](https://huggingface.co/bartowski/MN-12B-Lyra-v1-GGUF/blob/main/MN-12B-Lyra-v1-Q8_0.gguf) | Q8_0 | 13.02GB | false | Extremely high quality, generally unneeded but max available quant. |
34
  | [MN-12B-Lyra-v1-Q6_K_L.gguf](https://huggingface.co/bartowski/MN-12B-Lyra-v1-GGUF/blob/main/MN-12B-Lyra-v1-Q6_K_L.gguf) | Q6_K_L | 10.38GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
35
  | [MN-12B-Lyra-v1-Q6_K.gguf](https://huggingface.co/bartowski/MN-12B-Lyra-v1-GGUF/blob/main/MN-12B-Lyra-v1-Q6_K.gguf) | Q6_K | 10.06GB | false | Very high quality, near perfect, *recommended*. |