auto-patch README.md
Browse files
README.md
CHANGED
@@ -20,7 +20,7 @@ tags:
|
|
20 |
static quants of https://huggingface.co/wnma3mz/Janus-Pro-7B-LM
|
21 |
|
22 |
<!-- provided-files -->
|
23 |
-
weighted/imatrix quants
|
24 |
## Usage
|
25 |
|
26 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
@@ -43,6 +43,7 @@ more details, including on how to concatenate multi-part files.
|
|
43 |
| [GGUF](https://huggingface.co/mradermacher/Janus-Pro-7B-LM-GGUF/resolve/main/Janus-Pro-7B-LM.Q5_K_S.gguf) | Q5_K_S | 4.9 | |
|
44 |
| [GGUF](https://huggingface.co/mradermacher/Janus-Pro-7B-LM-GGUF/resolve/main/Janus-Pro-7B-LM.Q5_K_M.gguf) | Q5_K_M | 5.0 | |
|
45 |
| [GGUF](https://huggingface.co/mradermacher/Janus-Pro-7B-LM-GGUF/resolve/main/Janus-Pro-7B-LM.Q6_K.gguf) | Q6_K | 5.8 | very good quality |
|
|
|
46 |
| [GGUF](https://huggingface.co/mradermacher/Janus-Pro-7B-LM-GGUF/resolve/main/Janus-Pro-7B-LM.f16.gguf) | f16 | 13.9 | 16 bpw, overkill |
|
47 |
|
48 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
20 |
static quants of https://huggingface.co/wnma3mz/Janus-Pro-7B-LM
|
21 |
|
22 |
<!-- provided-files -->
|
23 |
+
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Janus-Pro-7B-LM-i1-GGUF
|
24 |
## Usage
|
25 |
|
26 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
43 |
| [GGUF](https://huggingface.co/mradermacher/Janus-Pro-7B-LM-GGUF/resolve/main/Janus-Pro-7B-LM.Q5_K_S.gguf) | Q5_K_S | 4.9 | |
|
44 |
| [GGUF](https://huggingface.co/mradermacher/Janus-Pro-7B-LM-GGUF/resolve/main/Janus-Pro-7B-LM.Q5_K_M.gguf) | Q5_K_M | 5.0 | |
|
45 |
| [GGUF](https://huggingface.co/mradermacher/Janus-Pro-7B-LM-GGUF/resolve/main/Janus-Pro-7B-LM.Q6_K.gguf) | Q6_K | 5.8 | very good quality |
|
46 |
+
| [GGUF](https://huggingface.co/mradermacher/Janus-Pro-7B-LM-GGUF/resolve/main/Janus-Pro-7B-LM.Q8_0.gguf) | Q8_0 | 7.4 | fast, best quality |
|
47 |
| [GGUF](https://huggingface.co/mradermacher/Janus-Pro-7B-LM-GGUF/resolve/main/Janus-Pro-7B-LM.f16.gguf) | f16 | 13.9 | 16 bpw, overkill |
|
48 |
|
49 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|