File size: 348 Bytes
d91f9b1 1009e69 |
1 2 3 4 |
---
license: apache-2.0
---
The Qwen authors highlight in their blogpost that qwen 2 7b can handle sequences up to 128k, but the GGUF meta-data is set to 32k. This is a version with 131k max context length, Using the llama.cpp script, and this command: `python gguf-set-metadata.py qwen2-7b-instruct-q5_k_m.gguf qwen2.context_length 131072 --force` |