---
pipeline_tag: text-generation
library_name: gguf
license: apache-2.0
---
GGUF importance matrix (imatrix) quants for https://huggingface.co/jondurbin/bagel-34b-v0.4  
The importance matrix was trained for ~50K tokens (105 batches of 512 tokens) using a [general purpose imatrix calibration dataset](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384).

Prompt strategies: https://huggingface.co/jondurbin/bagel-34b-v0.4#prompting-strategies

Feb. 21, 2024: Updating quants from [latest commit](https://huggingface.co/jondurbin/bagel-34b-v0.4/commit/94054270c89880c5fbc7e8d9d7b7540fcfdcbbeb).

| Layers | Context | [Template](https://huggingface.co/jondurbin/bagel-34b-v0.4#prompt-formatting) |
| --- | --- | --- |
| <pre>60</pre> | <pre>200000</pre> | <pre>[INST] \<\<SYS\>\><br>{instructions}<br>\<\</SYS\>\><br><br>{prompt} [/INST]<br>{response}</pre> |