File size: 874 Bytes
9a7155c 14ace87 9a7155c 14ace87 9c3a8a1 8547739 14ace87 9dead2c |
1 2 3 4 5 6 7 8 9 10 11 12 |
---
license: apache-2.0
pipeline_tag: text-generation
library_name: gguf
---
GGUF importance matrix (imatrix) quants for https://huggingface.co/abacusai/Smaug-Mixtral-v0.1
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).
**NOTE**: The new IQ3_M/IQ3_S/Q3_K_XS quants are currently causing a segfault during quantization, so I'll upload them once llama.cpp gets fixed. The [imatrix is being used on the K-quants](https://github.com/ggerganov/llama.cpp/pull/4930) as well.
| Layers | Context | [Template](https://huggingface.co/abacusai/Smaug-Mixtral-v0.1/blob/main/tokenizer_config.json#L32) |
| --- | --- | --- |
| <pre>32</pre> | <pre>32768</pre> | <pre>\<s\>[INST] {prompt} [/INST]<br>{response}</pre> | |