Add F16 and I2_S GGUF conversion for bitnet-embeddings 0.6B and 270M models#584

Merged

tsong-ms merged 8 commits into

microsoft:mainfrom

isHuangXin:release-bitnet-embedding-0.6b-270m

Jul 16, 2026

Commits on Jul 12, 2026

Add bitnet-embeddings-0.6b model adaptation with F16 and I2_S GGUF conversion
isHuangXin
committed

Commits on Jul 13, 2026

feat: add I2_S GGUF conversion for bitnet-b1.58-2B-4T and refactor T-MAC LUT path
isHuangXin
committed

Commits on Jul 16, 2026

Fix vocab encoding by disabling add_special_tokens in tokenizer.encode
isHuangXin
committed
Enable LLAMA_BUILD_COMMON and LLAMA_BUILD_SERVER to build llama-cli
isHuangXin
committed