auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -16,7 +16,7 @@ quantized_by: mradermacher
|
|
| 16 |
static quants of https://huggingface.co/alpindale/WizardLM-2-8x22B
|
| 17 |
|
| 18 |
<!-- provided-files -->
|
| 19 |
-
weighted/imatrix quants
|
| 20 |
## Usage
|
| 21 |
|
| 22 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
@@ -36,6 +36,7 @@ more details, including on how to concatenate multi-part files.
|
|
| 36 |
| [PART 1](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.IQ3_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.IQ3_M.gguf.part2of2) | IQ3_M | 64.6 | |
|
| 37 |
| [PART 1](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q3_K_M.gguf.part2of2) | Q3_K_M | 67.9 | lower quality |
|
| 38 |
| [PART 1](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q3_K_L.gguf.part2of2) | Q3_K_L | 72.7 | |
|
|
|
|
| 39 |
| [PART 1](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q4_K_S.gguf.part2of2) | Q4_K_S | 80.6 | fast, recommended |
|
| 40 |
| [PART 1](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q4_K_M.gguf.part2of2) | Q4_K_M | 85.7 | fast, recommended |
|
| 41 |
| [PART 1](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q5_K_S.gguf.part2of2) | Q5_K_S | 97.1 | |
|
|
|
|
| 16 |
static quants of https://huggingface.co/alpindale/WizardLM-2-8x22B
|
| 17 |
|
| 18 |
<!-- provided-files -->
|
| 19 |
+
weighted/imatrix quants are available at https://huggingface.co/mradermacher/WizardLM-2-8x22B-i1-GGUF
|
| 20 |
## Usage
|
| 21 |
|
| 22 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
|
| 36 |
| [PART 1](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.IQ3_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.IQ3_M.gguf.part2of2) | IQ3_M | 64.6 | |
|
| 37 |
| [PART 1](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q3_K_M.gguf.part2of2) | Q3_K_M | 67.9 | lower quality |
|
| 38 |
| [PART 1](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q3_K_L.gguf.part2of2) | Q3_K_L | 72.7 | |
|
| 39 |
+
| [PART 1](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.IQ4_XS.gguf.part2of2) | IQ4_XS | 76.5 | |
|
| 40 |
| [PART 1](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q4_K_S.gguf.part2of2) | Q4_K_S | 80.6 | fast, recommended |
|
| 41 |
| [PART 1](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q4_K_M.gguf.part2of2) | Q4_K_M | 85.7 | fast, recommended |
|
| 42 |
| [PART 1](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q5_K_S.gguf.part2of2) | Q5_K_S | 97.1 | |
|