text-generation-inference/server/text_generation_server
Nicolas Patry e943a294bc
fix(server): harden the weights choice to save on disk. (#561)
- Look at `transformers` base class to check for
  `_key_to_ignore_on_load_missing` or `_tied_weights` which are the
  standard attributes to select the keys to NOT save on disk (since they
  are ignored)

- Modified safetensors code (to be reflected in safetensors even if it's
  an internal function).
  
- Will not work for trust_remote_code=True repos (like santacoder).

Should help with :
https://github.com/huggingface/text-generation-inference/issues/555
and : https://github.com/huggingface/text-generation-inference/pull/501
and https://github.com/huggingface/text-generation-inference/issues/556
and
https://github.com/huggingface/text-generation-inference/issues/482#issuecomment-1623713593
2023-07-07 14:50:12 +02:00
..
models fix(server): decrease memory fragmentation (#557) 2023-07-06 14:28:33 +02:00
pb feat(server): clear cache on error (#143) 2023-03-28 11:29:35 +02:00
utils fix(server): harden the weights choice to save on disk. (#561) 2023-07-07 14:50:12 +02:00
__init__.py feat(clients): Python client (#103) 2023-03-07 18:52:22 +01:00
cache.py fix(server): decrease memory fragmentation (#557) 2023-07-06 14:28:33 +02:00
cli.py fix(server): harden the weights choice to save on disk. (#561) 2023-07-07 14:50:12 +02:00
interceptor.py feat(clients): Python client (#103) 2023-03-07 18:52:22 +01:00
server.py feat: Add the option to force another dtype than f16. (#513) 2023-06-30 20:30:09 +02:00
tracing.py feat(clients): Python client (#103) 2023-03-07 18:52:22 +01:00