Yang, Bo 8a5f80bb61 Add AutoCausalLM (#5) ... Currently `BLOOMSharded` is a subclass of `CausalLM`, while it skips `CausalLM`'s constructor. This is a supprising behavior that we might want to avoid. This PR extract `CausalLM`'s constructor to `AutoCausalLM` to detect settings from `model_id`, so that we don't have to skip `CausalLM`'s constructor.		2023-08-02 09:35:40 -07:00
..
test_bloom.py	feat(server): Rework model loading (#344)	2023-06-08 14:51:52 +02:00
test_causal_lm.py	Add AutoCausalLM (#5)	2023-08-02 09:35:40 -07:00
test_model.py	fix(server): fix decode token (#334)	2023-05-16 23:23:27 +02:00
test_santacoder.py	feat(server): only compute prefill logprobs when asked (#406)	2023-06-02 17:12:30 +02:00
test_seq2seq_lm.py	feat(server): only compute prefill logprobs when asked (#406)	2023-06-02 17:12:30 +02:00