---
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> |