Open Assistant: v0.0.1-beta57 Release

What's Changed

• added markdown tooltip by @Anantha-Kandrapu in https://github.com/LAION-AI/Open-Assistant/pull/2064
• duplex communication in inference by @yk in https://github.com/LAION-AI/Open-Assistant/pull/2098
• Fix passing parallelism var to worker in Ansible playbook by @olliestanley in https://github.com/LAION-AI/Open-Assistant/pull/2092
• Add XP progress by @AbdBarho in https://github.com/LAION-AI/Open-Assistant/pull/2093
• Update Chat UI to latest inference changes by @AbdBarho in https://github.com/LAION-AI/Open-Assistant/pull/2105
• Inference-deploy by @yk in https://github.com/LAION-AI/Open-Assistant/pull/2109
• Inference-comma-separated-list-configs by @yk in https://github.com/LAION-AI/Open-Assistant/pull/2110
• added create_at and parent_id to inference MessageRead by @yk in https://github.com/LAION-AI/Open-Assistant/pull/2111
• Improve FAQ by @olliestanley in https://github.com/LAION-AI/Open-Assistant/pull/2114
• Add GitHub OAuth support to inference server by @olliestanley in https://github.com/LAION-AI/Open-Assistant/pull/2097
• Clean up chat UI by @AbdBarho in https://github.com/LAION-AI/Open-Assistant/pull/2108
• Add Team page by @AbdBarho in https://github.com/LAION-AI/Open-Assistant/pull/2103
• Added James Mete (JMete) to team page. by @Jmete in https://github.com/LAION-AI/Open-Assistant/pull/2117
• Update team.json by @melvinebenezer in https://github.com/LAION-AI/Open-Assistant/pull/2116
• Minor update on team.json by @melvinebenezer in https://github.com/LAION-AI/Open-Assistant/pull/2118
• Some changes in teams by @0x22almostEvil in https://github.com/LAION-AI/Open-Assistant/pull/2120
• Reward Model Training by @dvruette in https://github.com/LAION-AI/Open-Assistant/pull/2071
• You in teams and more by @0x22almostEvil in https://github.com/LAION-AI/Open-Assistant/pull/2123
• Add minimath support by @johnflux in https://github.com/LAION-AI/Open-Assistant/pull/2094
• Add ~Zy~ to /website/src/data/team.json by @Zyphre in https://github.com/LAION-AI/Open-Assistant/pull/2125
• Fix GitHub auth flow on inference server by @olliestanley in https://github.com/LAION-AI/Open-Assistant/pull/2121
• Add tlcv2.0_oa by @wannaphong in https://github.com/LAION-AI/Open-Assistant/pull/1965
• Basic-hf-server by @yk in https://github.com/LAION-AI/Open-Assistant/pull/2130
• feature: Using Celery for APIs and periodic tasks by @melvinebenezer in https://github.com/LAION-AI/Open-Assistant/pull/1754
• enable chat via environment variable instead of flag by @yk in https://github.com/LAION-AI/Open-Assistant/pull/2128
• Boilerplate OAuth website <=> inference by @AbdBarho in https://github.com/LAION-AI/Open-Assistant/pull/2127
• Add Joak to team by @notmd in https://github.com/LAION-AI/Open-Assistant/pull/2134
• Evaluation datasets for Reward Model by @shahules786 in https://github.com/LAION-AI/Open-Assistant/pull/2112
• fix team description by @notmd in https://github.com/LAION-AI/Open-Assistant/pull/2135
• Add me to team.json by @johnflux in https://github.com/LAION-AI/Open-Assistant/pull/2132
• Update team.json by @kenhktsui in https://github.com/LAION-AI/Open-Assistant/pull/2139
• Simplify celery worker use by @andreaskoepf in https://github.com/LAION-AI/Open-Assistant/pull/2131
• added HF, W&B, and Redmond to sponsors by @yk in https://github.com/LAION-AI/Open-Assistant/pull/2142
• Display message tree state admin by @Rulios in https://github.com/LAION-AI/Open-Assistant/pull/2133
• Add multi-turn conversation dataset format by @Vechtomov in https://github.com/LAION-AI/Open-Assistant/pull/2113
• [#2077] Possbility to revert message deletion by @Shadowner in https://github.com/LAION-AI/Open-Assistant/pull/2079
• Added ENABLE_CHAT to chat id page and docker-compose by @yk in https://github.com/LAION-AI/Open-Assistant/pull/2137
• Llama inference by @yk in https://github.com/LAION-AI/Open-Assistant/pull/2144
• hotfix for max_new_tokens parameter being None by @yk in https://github.com/LAION-AI/Open-Assistant/pull/2146
• Implemented ability to press ctrl+enter (or cmd+enter) to Review/Subm… by @cooperaustinj in https://github.com/LAION-AI/Open-Assistant/pull/1237
• Cancelling pending chat messages of user on submission of a new message by @yk in https://github.com/LAION-AI/Open-Assistant/pull/2141
• Added a timeout for inference messages by @yk in https://github.com/LAION-AI/Open-Assistant/pull/2147
• Added various people to codeowners for backend and inference by @yk in https://github.com/LAION-AI/Open-Assistant/pull/2150
• Remove invalid badge from README by @olliestanley in https://github.com/LAION-AI/Open-Assistant/pull/2149
• Add refresh tokens to inference server auth by @olliestanley in https://github.com/LAION-AI/Open-Assistant/pull/2129
• Robustification: Specific message type for protocol upgrade, everything else will re-connect by @yk in https://github.com/LAION-AI/Open-Assistant/pull/2152
• Fixes auth TokenPair change bug (also fix for null logprob from inference server) by @yk in https://github.com/LAION-AI/Open-Assistant/pull/2155
• Fixes changed access token model for website. Does not handle refresh yet by @yk in https://github.com/LAION-AI/Open-Assistant/pull/2157
• Updated team page to fit visually more the the rest of the pages, added a button to the call-to-action section which links to the team page. by @theopfr in https://github.com/LAION-AI/Open-Assistant/pull/2126
• Fix stacking of pos/neg logits for RM compute_metrics by @andreaskoepf in https://github.com/LAION-AI/Open-Assistant/pull/2138
• building separate llama image for inference by @yk in https://github.com/LAION-AI/Open-Assistant/pull/2161
• Changed worker config into worker info and unified model input and total lengths by @yk in https://github.com/LAION-AI/Open-Assistant/pull/2160
• Added hardware info dependencies to oasst-shared to make api tests pass by @yk in https://github.com/LAION-AI/Open-Assistant/pull/2162
• Derive RewardModel from PreTrainedModel by @andreaskoepf in https://github.com/LAION-AI/Open-Assistant/pull/2158
• check per_digit_tokens exists by @HuangLK in https://github.com/LAION-AI/Open-Assistant/pull/2166
• Only allow prompter answers to complete parent message by @yk in https://github.com/LAION-AI/Open-Assistant/pull/2164
• Add first RM training run params by @andreaskoepf in https://github.com/LAION-AI/Open-Assistant/pull/2167
• Diabling stop sequences in inference, since we are using eos_tokens in most models by @yk in https://github.com/LAION-AI/Open-Assistant/pull/2168
• Added param configs from eval to pass to the frontend by @yk in https://github.com/LAION-AI/Open-Assistant/pull/2163
• Fix: Correctly sending error to waiting client on message abort by @yk in https://github.com/LAION-AI/Open-Assistant/pull/2169
• Chat config UI by @notmd in https://github.com/LAION-AI/Open-Assistant/pull/2115
• Update pythia 6b RM training config by @andreaskoepf in https://github.com/LAION-AI/Open-Assistant/pull/2187
• Add @dvruette, @andreaskoepf & @yk as codeowners of /model/ by @andreaskoepf in https://github.com/LAION-AI/Open-Assistant/pull/2186
• Fix inconsistent sources of max token length by @yk in https://github.com/LAION-AI/Open-Assistant/pull/2178
• Add GPTNeoXRewardModel by @andreaskoepf in https://github.com/LAION-AI/Open-Assistant/pull/2182
• Add llama training support by @andreaskoepf in https://github.com/LAION-AI/Open-Assistant/pull/2055
• Fix output of RankingDataCollator when max_length is None by @andreaskoepf in https://github.com/LAION-AI/Open-Assistant/pull/2185
• Update website's dockerfile by @AbdBarho in https://github.com/LAION-AI/Open-Assistant/pull/2189
• Login to inference through website by @AbdBarho in https://github.com/LAION-AI/Open-Assistant/pull/2176
• rework layout by @notmd in https://github.com/LAION-AI/Open-Assistant/pull/2172
• Evaluate sampling report using RM by @shahules786 in https://github.com/LAION-AI/Open-Assistant/pull/2190

New Contributors

• @Anantha-Kandrapu made their first contribution in https://github.com/LAION-AI/Open-Assistant/pull/2064
• @Zyphre made their first contribution in https://github.com/LAION-AI/Open-Assistant/pull/2125
• @Rulios made their first contribution in https://github.com/LAION-AI/Open-Assistant/pull/2133
• @cooperaustinj made their first contribution in https://github.com/LAION-AI/Open-Assistant/pull/1237
• @HuangLK made their first contribution in https://github.com/LAION-AI/Open-Assistant/pull/2166

Full Changelog: https://github.com/LAION-AI/Open-Assistant/compare/v0.0.1-beta56...v0.0.1-beta57