mirror of
https://github.com/ml-explore/mlx-examples.git
synced 2025-07-24 21:21:16 +08:00
f5b80c95fb
* Draft of tiny llama from gguf * Transpose all * No transposition with new layout * Read config from gguf * Create tokenizer from gguf * move gguf and update to be similar to hf_llm * change model to HF style + updates to REAMDE * nits in REAMDE * nit readme * only use mlx for metadata * fix eos/bos tokenizer * fix tokenization * quantization runs * 8-bit works * tokenizer fix * bump mlx version --------- Co-authored-by: Juarez Bochi <juarez.bochi@grammarly.com> Co-authored-by: Awni Hannun <awni@apple.com>
5 lines
49 B
Plaintext
5 lines
49 B
Plaintext
mlx>=0.0.11
|
|
numpy
|
|
protobuf==3.20.0
|
|
sentencepiece
|