|
--- |
|
license: other |
|
license_name: deepseek |
|
library_name: gguf |
|
license_link: >- |
|
https://huggingface.co/deepseek-ai/deepseek-coder-33b-instruct/blob/main/LICENSE |
|
pipeline_tag: text-generation |
|
--- |
|
GGUF importance matrix (imatrix) quants for https://huggingface.co/deepseek-ai/deepseek-coder-33b-instruct |
|
The importance matrix was trained for 100K tokens (200 batches of 512 tokens) using wiki.train.raw. |
|
|
|
**2024-03-13**: Updated IQ1_S using latest commit `19885d20`. More info [here](https://github.com/ggerganov/llama.cpp/pull/5999) and [here](https://github.com/ggerganov/llama.cpp/pull/5999#issuecomment-1991587536). |
|
|
|
| Layers | Context | Template | |
|
| --- | --- | --- | |
|
| <pre>62</pre> | <pre>16384</pre> | <pre>{instructions}<br>### Instruction:<br>{prompt}<br>### Response:<br>{response}</pre> | |
