File size: 750 Bytes
927ffa4 1624cbb b00487b 927ffa4 df13628 1624cbb |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 |
---
library_name: gguf
pipeline_tag: text-generation
base_model: jondurbin/bagel-dpo-34b-v0.5
license: apache-2.0
---
* GGUF importance matrix (imatrix) quants for https://huggingface.co/jondurbin/bagel-dpo-34b-v0.5
* The importance matrix was trained for 100K tokens (200 batches of 512 tokens) using wiki.train.raw.
* The [imatrix is being used on the K-quants](https://github.com/ggerganov/llama.cpp/pull/4930) as well (below Q6_K).
* Generated with llama.cpp commit `f87f7b89`
| Layers | Context | [Template](https://huggingface.co/jondurbin/bagel-dpo-34b-v0.5#prompt-formatting) |
| --- | --- | --- |
| <pre>60</pre> | <pre>200000</pre> | <pre>[INST] \<\<SYS\>\><br>{instructions}<br>\<\</SYS\>\><br><br>{prompt} [/INST]<br>{response}</pre> | |