Commit
•
a240d82
1
Parent(s):
007bf8b
auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -18,7 +18,6 @@ quantized_by: mradermacher
|
|
| 18 |
<!-- ### vocab_type: -->
|
| 19 |
weighted/imatrix quants of https://huggingface.co/ICBU-NPU/FashionGPT-70B-V1
|
| 20 |
|
| 21 |
-
|
| 22 |
<!-- provided-files -->
|
| 23 |
static quants are available at https://huggingface.co/mradermacher/FashionGPT-70B-V1-GGUF
|
| 24 |
## Usage
|
|
@@ -39,6 +38,7 @@ more details, including on how to concatenate multi-part files.
|
|
| 39 |
| [GGUF](https://huggingface.co/mradermacher/FashionGPT-70B-V1-i1-GGUF/resolve/main/FashionGPT-70B-V1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 33.4 | IQ3_S probably better |
|
| 40 |
| [GGUF](https://huggingface.co/mradermacher/FashionGPT-70B-V1-i1-GGUF/resolve/main/FashionGPT-70B-V1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 39.3 | optimal size/speed/quality |
|
| 41 |
| [GGUF](https://huggingface.co/mradermacher/FashionGPT-70B-V1-i1-GGUF/resolve/main/FashionGPT-70B-V1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 41.5 | fast, recommended |
|
|
|
|
| 42 |
|
| 43 |
|
| 44 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
|
| 18 |
<!-- ### vocab_type: -->
|
| 19 |
weighted/imatrix quants of https://huggingface.co/ICBU-NPU/FashionGPT-70B-V1
|
| 20 |
|
|
|
|
| 21 |
<!-- provided-files -->
|
| 22 |
static quants are available at https://huggingface.co/mradermacher/FashionGPT-70B-V1-GGUF
|
| 23 |
## Usage
|
|
|
|
| 38 |
| [GGUF](https://huggingface.co/mradermacher/FashionGPT-70B-V1-i1-GGUF/resolve/main/FashionGPT-70B-V1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 33.4 | IQ3_S probably better |
|
| 39 |
| [GGUF](https://huggingface.co/mradermacher/FashionGPT-70B-V1-i1-GGUF/resolve/main/FashionGPT-70B-V1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 39.3 | optimal size/speed/quality |
|
| 40 |
| [GGUF](https://huggingface.co/mradermacher/FashionGPT-70B-V1-i1-GGUF/resolve/main/FashionGPT-70B-V1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 41.5 | fast, recommended |
|
| 41 |
+
| [PART 1](https://huggingface.co/mradermacher/FashionGPT-70B-V1-i1-GGUF/resolve/main/FashionGPT-70B-V1.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/FashionGPT-70B-V1-i1-GGUF/resolve/main/FashionGPT-70B-V1.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 56.7 | practically like static Q6_K |
|
| 42 |
|
| 43 |
|
| 44 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|