v0.2.0

版本发布时间: 2023-08-19 23:49:51

xorbitsai/inference最新发布版本:v0.15.3(2024-09-30 21:42:58)

What's new in 0.2.0 (2023-08-19)

These are the changes in inference v0.2.0.

FEAT:Support Starchat-Beta and StarCoderPlus with Pytorch. by @RayJi01 in https://github.com/xorbitsai/inference/pull/333
FEAT: Support Ctransformers by @RayJi01 in https://github.com/xorbitsai/inference/pull/289
FEAT: internlm by @UranusSeven in https://github.com/xorbitsai/inference/pull/352
FEAT: Support Vicuna-v1.5 and Vicuna-v1.5-16k by @RayJi01 in https://github.com/xorbitsai/inference/pull/343
FEAT: wizardmath by @UranusSeven in https://github.com/xorbitsai/inference/pull/351
FEAT: support generate/chat/create_embedding/register/unregister/registrations method in cmdline by @pangyoki in https://github.com/xorbitsai/inference/pull/363

ENH: Use Llama 2 chat for inference in LangChain QA demo by @jiayini1119 in https://github.com/xorbitsai/inference/pull/324
ENH: cache from URI by @UranusSeven in https://github.com/xorbitsai/inference/pull/350
ENH: Update System Prompt for llama-2-chat by @Bojun-Feng in https://github.com/xorbitsai/inference/pull/359
ENH: RESTful client supports custom model APIs by @jiayini1119 in https://github.com/xorbitsai/inference/pull/360
BLD: fix readthedocs by @UranusSeven in https://github.com/xorbitsai/inference/pull/340
BLD: fix readthedocs by @UranusSeven in https://github.com/xorbitsai/inference/pull/342

BUG: Chatglm max_length doesn't work by @Bojun-Feng in https://github.com/xorbitsai/inference/pull/349
BUG: builtin stop_token_ids changes by @UranusSeven in https://github.com/xorbitsai/inference/pull/353
BUG: custom model related bugs by @UranusSeven in https://github.com/xorbitsai/inference/pull/364

FEAT : Add Model Dashboard by @Bojun-Feng in https://github.com/xorbitsai/inference/pull/334
Revert "FEAT : Add Model Dashboard" by @UranusSeven in https://github.com/xorbitsai/inference/pull/362

Full Changelog: https://github.com/xorbitsai/inference/compare/v0.1.3...v0.2.0