Commit
•
465c186
1
Parent(s):
d6c8daa
auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -14,7 +14,6 @@ quantized_by: mradermacher
|
|
| 14 |
<!-- ### vocab_type: -->
|
| 15 |
static quants of https://huggingface.co/ICBU-NPU/FashionGPT-70B-V1.2
|
| 16 |
|
| 17 |
-
|
| 18 |
<!-- provided-files -->
|
| 19 |
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
|
| 20 |
## Usage
|
|
@@ -30,11 +29,13 @@ more details, including on how to concatenate multi-part files.
|
|
| 30 |
| Link | Type | Size/GB | Notes |
|
| 31 |
|:-----|:-----|--------:|:------|
|
| 32 |
| [GGUF](https://huggingface.co/mradermacher/FashionGPT-70B-V1.2-GGUF/resolve/main/FashionGPT-70B-V1.2.Q2_K.gguf) | Q2_K | 25.6 | |
|
|
|
|
| 33 |
| [GGUF](https://huggingface.co/mradermacher/FashionGPT-70B-V1.2-GGUF/resolve/main/FashionGPT-70B-V1.2.IQ3_S.gguf) | IQ3_S | 30.0 | beats Q3_K* |
|
| 34 |
| [GGUF](https://huggingface.co/mradermacher/FashionGPT-70B-V1.2-GGUF/resolve/main/FashionGPT-70B-V1.2.Q3_K_S.gguf) | Q3_K_S | 30.0 | |
|
| 35 |
| [GGUF](https://huggingface.co/mradermacher/FashionGPT-70B-V1.2-GGUF/resolve/main/FashionGPT-70B-V1.2.IQ3_M.gguf) | IQ3_M | 31.0 | |
|
| 36 |
| [GGUF](https://huggingface.co/mradermacher/FashionGPT-70B-V1.2-GGUF/resolve/main/FashionGPT-70B-V1.2.Q3_K_M.gguf) | Q3_K_M | 33.4 | lower quality |
|
| 37 |
| [GGUF](https://huggingface.co/mradermacher/FashionGPT-70B-V1.2-GGUF/resolve/main/FashionGPT-70B-V1.2.Q3_K_L.gguf) | Q3_K_L | 36.2 | |
|
|
|
|
| 38 |
| [GGUF](https://huggingface.co/mradermacher/FashionGPT-70B-V1.2-GGUF/resolve/main/FashionGPT-70B-V1.2.Q4_K_S.gguf) | Q4_K_S | 39.3 | fast, recommended |
|
| 39 |
| [GGUF](https://huggingface.co/mradermacher/FashionGPT-70B-V1.2-GGUF/resolve/main/FashionGPT-70B-V1.2.Q4_K_M.gguf) | Q4_K_M | 41.5 | fast, recommended |
|
| 40 |
| [GGUF](https://huggingface.co/mradermacher/FashionGPT-70B-V1.2-GGUF/resolve/main/FashionGPT-70B-V1.2.Q5_K_S.gguf) | Q5_K_S | 47.6 | |
|
|
|
|
| 14 |
<!-- ### vocab_type: -->
|
| 15 |
static quants of https://huggingface.co/ICBU-NPU/FashionGPT-70B-V1.2
|
| 16 |
|
|
|
|
| 17 |
<!-- provided-files -->
|
| 18 |
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
|
| 19 |
## Usage
|
|
|
|
| 29 |
| Link | Type | Size/GB | Notes |
|
| 30 |
|:-----|:-----|--------:|:------|
|
| 31 |
| [GGUF](https://huggingface.co/mradermacher/FashionGPT-70B-V1.2-GGUF/resolve/main/FashionGPT-70B-V1.2.Q2_K.gguf) | Q2_K | 25.6 | |
|
| 32 |
+
| [GGUF](https://huggingface.co/mradermacher/FashionGPT-70B-V1.2-GGUF/resolve/main/FashionGPT-70B-V1.2.IQ3_XS.gguf) | IQ3_XS | 28.4 | |
|
| 33 |
| [GGUF](https://huggingface.co/mradermacher/FashionGPT-70B-V1.2-GGUF/resolve/main/FashionGPT-70B-V1.2.IQ3_S.gguf) | IQ3_S | 30.0 | beats Q3_K* |
|
| 34 |
| [GGUF](https://huggingface.co/mradermacher/FashionGPT-70B-V1.2-GGUF/resolve/main/FashionGPT-70B-V1.2.Q3_K_S.gguf) | Q3_K_S | 30.0 | |
|
| 35 |
| [GGUF](https://huggingface.co/mradermacher/FashionGPT-70B-V1.2-GGUF/resolve/main/FashionGPT-70B-V1.2.IQ3_M.gguf) | IQ3_M | 31.0 | |
|
| 36 |
| [GGUF](https://huggingface.co/mradermacher/FashionGPT-70B-V1.2-GGUF/resolve/main/FashionGPT-70B-V1.2.Q3_K_M.gguf) | Q3_K_M | 33.4 | lower quality |
|
| 37 |
| [GGUF](https://huggingface.co/mradermacher/FashionGPT-70B-V1.2-GGUF/resolve/main/FashionGPT-70B-V1.2.Q3_K_L.gguf) | Q3_K_L | 36.2 | |
|
| 38 |
+
| [GGUF](https://huggingface.co/mradermacher/FashionGPT-70B-V1.2-GGUF/resolve/main/FashionGPT-70B-V1.2.IQ4_XS.gguf) | IQ4_XS | 37.3 | |
|
| 39 |
| [GGUF](https://huggingface.co/mradermacher/FashionGPT-70B-V1.2-GGUF/resolve/main/FashionGPT-70B-V1.2.Q4_K_S.gguf) | Q4_K_S | 39.3 | fast, recommended |
|
| 40 |
| [GGUF](https://huggingface.co/mradermacher/FashionGPT-70B-V1.2-GGUF/resolve/main/FashionGPT-70B-V1.2.Q4_K_M.gguf) | Q4_K_M | 41.5 | fast, recommended |
|
| 41 |
| [GGUF](https://huggingface.co/mradermacher/FashionGPT-70B-V1.2-GGUF/resolve/main/FashionGPT-70B-V1.2.Q5_K_S.gguf) | Q5_K_S | 47.6 | |
|