A 0.6B parameter draft (speculative decoding) model for use with Kimi-K2-Instruct.
See Kimi-K2-Instruct-DRAFT-0.6B-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:
- Kimi-K2-Instruct-DRAFT-0.6B-32k-Q4_0.gguf
- Kimi-K2-Instruct-DRAFT-0.6B-64k-Q4_0.gguf
- Kimi-K2-Instruct-DRAFT-0.6B-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... - If you want to recreate these, then the
TikToken/SentencePiecetokenizer mismatch requires a small hack toconvert_hf_to_gguf.py(see main model page for details).