Commit
•
5752ba8
1
Parent(s):
bbea9a2
auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -16,7 +16,6 @@ quantized_by: mradermacher
|
|
| 16 |
<!-- ### vocab_type: -->
|
| 17 |
static quants of https://huggingface.co/deepseek-ai/deepseek-llm-67b-base
|
| 18 |
|
| 19 |
-
|
| 20 |
<!-- provided-files -->
|
| 21 |
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.
|
| 22 |
## Usage
|
|
@@ -32,6 +31,7 @@ more details, including on how to concatenate multi-part files.
|
|
| 32 |
| Link | Type | Size/GB | Notes |
|
| 33 |
|:-----|:-----|--------:|:------|
|
| 34 |
| [GGUF](https://huggingface.co/mradermacher/deepseek-llm-67b-base-GGUF/resolve/main/deepseek-llm-67b-base.IQ3_S.gguf) | IQ3_S | 29.5 | beats Q3_K* |
|
|
|
|
| 35 |
| [PART 1](https://huggingface.co/mradermacher/deepseek-llm-67b-base-GGUF/resolve/main/deepseek-llm-67b-base.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/deepseek-llm-67b-base-GGUF/resolve/main/deepseek-llm-67b-base.Q8_0.gguf.part2of2) | Q8_0 | 71.7 | fast, best quality |
|
| 36 |
|
| 37 |
|
|
|
|
| 16 |
<!-- ### vocab_type: -->
|
| 17 |
static quants of https://huggingface.co/deepseek-ai/deepseek-llm-67b-base
|
| 18 |
|
|
|
|
| 19 |
<!-- provided-files -->
|
| 20 |
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.
|
| 21 |
## Usage
|
|
|
|
| 31 |
| Link | Type | Size/GB | Notes |
|
| 32 |
|:-----|:-----|--------:|:------|
|
| 33 |
| [GGUF](https://huggingface.co/mradermacher/deepseek-llm-67b-base-GGUF/resolve/main/deepseek-llm-67b-base.IQ3_S.gguf) | IQ3_S | 29.5 | beats Q3_K* |
|
| 34 |
+
| [GGUF](https://huggingface.co/mradermacher/deepseek-llm-67b-base-GGUF/resolve/main/deepseek-llm-67b-base.Q4_K_S.gguf) | Q4_K_S | 38.5 | fast, recommended |
|
| 35 |
| [PART 1](https://huggingface.co/mradermacher/deepseek-llm-67b-base-GGUF/resolve/main/deepseek-llm-67b-base.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/deepseek-llm-67b-base-GGUF/resolve/main/deepseek-llm-67b-base.Q8_0.gguf.part2of2) | Q8_0 | 71.7 | fast, best quality |
|
| 36 |
|
| 37 |
|