A 0.4B parameter draft (speculative decoding) model for use with Mistral-Large-Instruct-2411 and Mistral-Large-Instruct-2407.
See Mistral-Large-Instruct-2411-DRAFT-0.4B-v3.0 for the models in transformers format, and a detailed explanation of how the model was created.
I've included the Q4_0 quants for 3 different context lengths:
- Mistral-Large-Instruct-2411-DRAFT-0.4B-32k-Q4_0.gguf
- Mistral-Large-Instruct-2411-DRAFT-0.4B-64k-Q4_0.gguf
- Mistral-Large-Instruct-2411-DRAFT-0.4B-128k-Q4_0.gguf
NOTES:
- The 14 heads of
Qwen2.5-0.5Bdoesn't allow for any of the other 4-bit quants to be made (and experimentation has shown using more or less than 4-bits for speculative decoding is a waste of time anwyay). - Due to
llama.cppusing "static-YaRN" the scaling factor remains constant regardless of input length! Only use the longer context versions when processing long contexts is required...