huggingface/text-generation-inference

Pull Requests Commits

remove stream since its a separate PR

philschmid committed 2 years ago

cf435285

Update docs/source/basic_tutorials/request_parameters.md

philschmid committed 2 years ago

Verified 7b349f9b

philschmid committed 2 years ago

2c6e0739

philschmid committed 2 years ago

52cacff4

philschmid committed 2 years ago

eccb8a00

philschmid committed 2 years ago

69c3d79a

Adding Idefics multi modal model. (#842)

Narsil committed 2 years ago

Verified bce5e224

Upgrading versions of python client. (#862)

Narsil committed 2 years ago

Verified b9e33c49

"Fix" for rw-1b. (#860)

Narsil committed 2 years ago

Verified 2e68ac01

Misc improvements for InferenceClient docs (#852)

osanseviero committed 2 years ago

Verified d9bceb8e

Fixing watermark. (#851)

Narsil committed 2 years ago

Verified 2774b0ab

Update README.md (#848)

adarshxs committed 2 years ago

Verified 737d5781

Fix `tokenizers==0.13.4` . (#838)

Narsil committed 2 years ago

Verified 05dd14fd

README edit -- running the service with no GPU or CUDA support (#773)

pminervini committed 2 years ago

Verified d8f1337e

fix: LlamaTokenizerFast to AutoTokenizer at flash_llama.py (#619)

dongs0104 committed 2 years ago

Verified a072660b

Fix rope dynamic + factor (#822)

Narsil committed 2 years ago

Verified b5087c4f

Added two more features in readme.md file (#831)

sawanjr committed 2 years ago

Verified 3ffcd9d3

Have snippets in Python/JavaScript in quicktour (#809)

osanseviero committed 2 years ago

Verified d71237fc

Version 1.0.1 (#836)

Narsil committed 2 years ago

Verified 09eca642

Added streaming for InferenceClient (#821)

merveenoyan committed 2 years ago

Verified a2a913ee

Upgrade transformers (fix protobuf==3.20 issue) (#795)

Narsil committed 2 years ago

Verified cc7bb508

Added ChatUI Screenshot to Docs (#823)

merveenoyan committed 2 years ago

Verified d0e30771

[docs] Build docs only when doc files change (#812)

Mishig committed 2 years ago

Verified 5df4c7c0

Added CLI docs (#799)

merveenoyan committed 2 years ago

Verified e58ad6dd

Minor docs style fixes (#806)

osanseviero committed 2 years ago

Verified 7dbaef3f

Fix gated docs (#805)

osanseviero committed 2 years ago

Verified 04f7c2d8

Use destructuring in router arguments to avoid '.0' (#798)

ivarflakstad committed 2 years ago

Verified 8bdb16ee

Setup for doc-builder and docs for TGI (#740)

merveenoyan committed 2 years ago

Verified 647ae7a7

Llama change. (#793)

Narsil committed 2 years ago

Verified 0e8b4781

Update __init__.py (#794)

Narsil committed 2 years ago

Verified c4dac9f3

Older