Commit
•
bcc636d
1
Parent(s):
b34e2c6
auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -14,7 +14,6 @@ quantized_by: mradermacher
|
|
| 14 |
<!-- ### vocab_type: -->
|
| 15 |
weighted/imatrix quants of https://huggingface.co/ResplendentAI/SOVL_Llama3_8B
|
| 16 |
|
| 17 |
-
|
| 18 |
<!-- provided-files -->
|
| 19 |
static quants are available at https://huggingface.co/mradermacher/SOVL_Llama3_8B-GGUF
|
| 20 |
## Usage
|
|
@@ -51,7 +50,6 @@ more details, including on how to concatenate multi-part files.
|
|
| 51 |
| [GGUF](https://huggingface.co/mradermacher/SOVL_Llama3_8B-i1-GGUF/resolve/main/SOVL_Llama3_8B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | |
|
| 52 |
| [GGUF](https://huggingface.co/mradermacher/SOVL_Llama3_8B-i1-GGUF/resolve/main/SOVL_Llama3_8B.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K |
|
| 53 |
|
| 54 |
-
|
| 55 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 56 |
types (lower is better):
|
| 57 |
|
|
|
|
| 14 |
<!-- ### vocab_type: -->
|
| 15 |
weighted/imatrix quants of https://huggingface.co/ResplendentAI/SOVL_Llama3_8B
|
| 16 |
|
|
|
|
| 17 |
<!-- provided-files -->
|
| 18 |
static quants are available at https://huggingface.co/mradermacher/SOVL_Llama3_8B-GGUF
|
| 19 |
## Usage
|
|
|
|
| 50 |
| [GGUF](https://huggingface.co/mradermacher/SOVL_Llama3_8B-i1-GGUF/resolve/main/SOVL_Llama3_8B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | |
|
| 51 |
| [GGUF](https://huggingface.co/mradermacher/SOVL_Llama3_8B-i1-GGUF/resolve/main/SOVL_Llama3_8B.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K |
|
| 52 |
|
|
|
|
| 53 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 54 |
types (lower is better):
|
| 55 |
|