Releases: LAION-AI/Open-Assistant
Releases · LAION-AI/Open-Assistant
v0.0.2-alpha1: press enter to submit chat prompt (#2537)
v0.0.1
What's Changed
- Adds default to hidden to fix bugs by @yk in #2524
- Add default to user deleted column by @olliestanley in #2526
- Added playbook variables for google auth by @yk in #2529
- Added model config for sft-6 llama 30b by @yk in #2530
- Hide chats in the frontend by @yk in #2525
- Hotfix for non-updating chat list (#2527) by @yk in #2531
- Add delete account page by @AbdBarho in #2523
- Downgrade
react-simple-icons
by @AbdBarho in #2533
Full Changelog: v0.0.1-beta65...v0.0.1
v0.0.1-beta65
What's Changed
- [fix] rephrase weird chinese translation by @theblackcat102 in #2418
- Add self to data code owners by @olliestanley in #2424
- update docusaurus to latest + add models yt video as blogpost by @andrewm4894 in #2373
- add oa_leet10k instruction dataset by @ehartford in #2407
- Fix 'ConfigError: Attempted to change value of key "val_max_length" ...' and remove val_max_len variable by @jordiclive in #2425
- Small fixes for Greek translation by @stevestavropoulos in #2431
- Clear unused Images from node by @AbdBarho in #2338
- Added docker image for standalone worker by @yk in #2300
- Improvements to the HF worker container by @yk in #2339
- Add max_replies parameter for trainer_rm by @andreaskoepf in #2433
- Capitalized Chats by @jweaver3 in #2413
- Greek translation fixes for the stats page by @stevestavropoulos in #2434
- Add Graverman to contributors by @olliestanley in #2440
- move chat to top of sidebar by @andrewm4894 in #2429
- Fix export_model script by @andreaskoepf in #2426
- Allow google login to backend by @AbdBarho in #2390
- Fix for Webgpt NaN loss by @shahules786 in #2438
- fix list index out of range error for soda dataset by @CloseChoice in #2326
- Update team.json by @DamascusGit in #2427
- ua-UK translation improvements by @nmeln in #2442
- Add Links to sponsors by @AbdBarho in #2444
- fix extraction locales: "Sign In" on a main page by @vivekpabari in #2443
- remove openai references from datasets by @CloseChoice in #2445
- update team page by @jordiclive in #2366
- add Logic Inference Dataset by @kkie02 in #2337
- Added biostars_qa dataset and pre-processing scripts by @cannin in #2353
- remove prints by @CloseChoice in #2446
- Missing translations + improvements for EO by @stefangrotz in #2465
- Greek translation fixes by @stevestavropoulos in #2473
- fix vicuna dataset by @CloseChoice in #2476
- Implement new chat UI by @notmd in #2436
- Avoid chat flash render by @notmd in #2483
- Add gh vars config for rewiew/ranking counts by @andreaskoepf in #2479
- Add sedthh to data code owners by @olliestanley in #2487
- Add Databricks Dolly 15k converted to OA data format by @olliestanley in #2481
- Rename type by @AbdBarho in #2489
- Make readme neater and make more sense by @sryu1 in #2333
- fix custom preset selection by @notmd in #2493
- inference: allow user change chat title by @notmd in #2496
- basque lang fix by @ZiTAL in #2498
- Add safety server to inference by @olliestanley in #2449
- add conversion script for oa_leet10k by @ehartford in #2494
- Added llama 30b sft-5 to model configs by @yk in #2503
- Implement chat threading UI by @notmd in #2484
- Don't refresh the page after each message by @AbdBarho in #2491
- Fix #2354, introduce line-buffering + yield multiple objects from list in chat_stream.ts by @kpoeppel in #2458
- fix double emoji in
MessageTableEntry
component by @notmd in #2513 - Google auth website by @AbdBarho in #2391
- add databricks dolly dataset by @CloseChoice in #2499
- implement update chat title UI by @notmd in #2507
- fix custom preset selection by @notmd in #2511
- Data analysis suite by @MattAlexMiracle in #2159
- Add option to find missing strings in only some locales by @Psychpsyo in #2356
- Discord bot(js) with inference system by @MrlolDev in #2359
- PII Detector added by @Simon1V in #2380
- Update ChatConfigDrawer.tsx by @rain-1 in #2482
- Feature/remove reward instructor by @CloseChoice in #2289
- Add support for user deletion by @olliestanley in #2486
- Safety level control by @shahules786 in #2516
- Fix for existing inference user rows with deleted column by @olliestanley in #2521
- Add ability to hide (soft delete) chats to inference backend by @olliestanley in #2512
New Contributors
- @ehartford made their first contribution in #2407
- @jweaver3 made their first contribution in #2413
- @DamascusGit made their first contribution in #2427
- @vivekpabari made their first contribution in #2443
- @kkie02 made their first contribution in #2337
- @cannin made their first contribution in #2353
- @stefangrotz made their first contribution in #2465
- @Simon1V made their first contribution in #2380
- @rain-1 made their first contribution in #2482
Full Changelog: v0.0.1-beta64...v0.0.1-beta65
v0.0.1-beta64
What's Changed
- Update web container to include migrations by @AbdBarho in #2234
- fix types for prompt dataset by @CloseChoice in #2377
- Yet Another Russian Tranlsation by @0x22almostEvil in #2381
- Greek language addition with translations by @stevestavropoulos in #2386
- Add vicuna dataset by @CloseChoice in #2364
- Add alpaca reverse augmentation possibility by @CloseChoice in #2342
- Add chat deletion functionality by @AbdBarho in #2350
- Update documentation to reflect state of project by @olliestanley in #2379
- add chat cta in docs nav bar by @andrewm4894 in #2395
- add documentation to
team.json
and add andrewm4894 by @andrewm4894 in #2393 - Improve Chinese translation of 'Is it a bad reply, as an answer to th… by @lone-wolf-akela in #2396
- Added stability, and added sponsors to inference interface by @yk in #2383
- Add option to export trlx checkpoints by @andreaskoepf in #2409
- Reduced max tokens of llama 30b to 1792 because of OOMs at 2048 by @yk in #2411
- Add more German translations by @Psychpsyo in #2352
New Contributors
- @stevestavropoulos made their first contribution in #2386
- @lone-wolf-akela made their first contribution in #2396
Full Changelog: v0.0.1-beta63...v0.0.1-beta64
v0.0.1-beta63
What's Changed
- Update team page by @dvruette in #2361
- Add HFSummaryPairs class & fix AnthropicRLHF parsing by @andreaskoepf in #2362
- Update GPT4All dataset loading for new files by @olliestanley in #2344
- Show work config on each message by @AbdBarho in #2372
- Updated localization files for Hungarian language for the Chat tab by @sedthh in #2375
- update gpt4all to add multiround by @CloseChoice in #2371
- Use SSR for every pages by @notmd in #2334
- Persist chat config by @AbdBarho in #2367
Full Changelog: v0.0.1-beta62...v0.0.1-beta63
v0.0.1-beta62
v0.0.1-beta61
What's Changed
- Flash attention support for Llama by @dvruette in #2277
- Use fixed RNG seed value for all DeepSpeed workers by @andreaskoepf in #2324
- Show model config in the chat UI by @AbdBarho in #2317
- Populate env vars before render layout by @notmd in #2323
- Update configs according to feedback to #2277 by @dvruette in #2325
- Disable Initial Prompt Task for en and es Locales by @hzj5790 in #1849
- stats are shown on the admin by @vivasvan1 in #2330
- inference: use uuid v7 for most of table by @notmd in #2327
- fix deepspeed issue on trainer_rm.py, add crossentropy support by @theblackcat102 in #2321
- Improve scores of small 1.4B reward model.. by @andreaskoepf in #2329
- Refactor inference backend auth and switch to authlib by @olliestanley in #2318
- add dataset counts script by @CloseChoice in #2294
- fix typos by @RainRat in #2264
- Updated nginx config for prod, including streaming headers by @yk in #2239
New Contributors
- @vivasvan1 made their first contribution in #2330
- @RainRat made their first contribution in #2264
Full Changelog: v0.0.1-beta60...v0.0.1-beta61
v0.0.1-beta60
What's Changed
- Revert unrelated changes in instructor rank_datasets by @andreaskoepf in #2306
- Some admin route fixes to create api keys by @yk in #2320
- Fix DeepSpeed 0.8.3 training by @dvruette in #2299
Full Changelog: v0.0.1-beta59...v0.0.1-beta60
v0.0.1-beta59
What's Changed
- Set validation max length to a different value. by @jordiclive in #2308
- revert instructor code and fix a bug in anthropic ds parsing by @mikegarts in #2307
- fix for hf dockerfile by @yk in #2313
- OA-261.tell.a.joke.dataset by @mikegarts in #2209
- Reward Model evaluation by @shahules786 in #2314
- Sort chat messages by creation date by @AbdBarho in #2316
- Add Google OAuth support to inference backend by @olliestanley in #2221
New Contributors
- @jordiclive made their first contribution in #2308
Full Changelog: v0.0.1-beta58...v0.0.1-beta59
v0.0.1-beta58
What's Changed
- Introduce model configs to abstract pairings of models and hardware by @yk in #2194
- Add recent changes to eval_model/manual/sampling_report.py by @andreaskoepf in #2191
- fix: ghcr.io build for mulitplatform. includes Apple silicon by @melvinebenezer in #2151
- Revert "fix: ghcr.io build for mulitplatform. includes Apple silicon" by @andreaskoepf in #2199
- Update CODEOWNERS for website by @AbdBarho in #2200
- Post llama merge fixes by @andreaskoepf in #2188
- feature : Alpaca dataset by @theblackcat102 in #2205
- Russian Translation Updated + Stuff by @0x22almostEvil in #2197
- Instruction Dataset: Retrieval-based grounded model generated Q-A pairs (BART version) by @michaelthwan in #2170
- Get available auth providers from inference server by @AbdBarho in #2207
- fixes text client to work with new debug login workflow by @yk in #2212
- Fix horizontal scrolling on mobile by @AbdBarho in #2211
- Update Ukrainian translation by @nmeln in #2214
- Use new inference model config / API by @AbdBarho in #2208
- Added CORS origins to inference settings by @yk in #2217
- Adjusted deployment notebooks for inference by @yk in #2213
- Add ability for inference backend to revoke auth refresh tokens by @olliestanley in #2175
- Fix to rank_datasets.py by @olliestanley in #2220
- Fixed bugs in deployment notebook (Sorry 🙃) by @yk in #2219
- Reduce star motion by @AbdBarho in #2215
- Add Inference sign out functionality by @AbdBarho in #2218
- SFT Rejection Sampling using RM by @shahules786 in #2225
- Various improvements to the dev setup by @yk in #2228
- update deps by @notmd in #2227
- Style updates to chat UI by @AbdBarho in #2226
- Add migrations to web db by @AbdBarho in #2233
- Create worker metrics manually for more control by @yk in #2229
- Sending MessageRead along with error to client by @yk in #2230
- Enabling Threads and Retry for Web Chat by @yk in #2232
- Export script: Fix duplicate loading of models by @andreaskoepf in #2231
- Add re-rank cli utility by @andreaskoepf in #2243
- Provide minimal documentation of oasst-data module and file format by @andreaskoepf in #2237
- update warning and improve readme in model training by @CloseChoice in #2246
- Improved worker script and documentation thereof by @yk in #2247
- Correlation metrics for Reward Model by @shahules786 in #2251
- Revert "Correlation metrics for Reward Model" by @andreaskoepf in #2253
- Add simple OIG data loader by @andreaskoepf in #2260
- Add correlation metrics for Reward Modeling by @shahules786 in #2266
- Expose env vars globally by @notmd in #2244
- Add Esperanto Language [fixed] by @0x22almostEvil in #2271
- Use LLaMA impl of Huggingface Transformers by @andreaskoepf in #2263
- Fix GPTNeoX-20B training by @dvruette in #2240
- Updated Turkish language by @irfantogluk in #2270
- Add loader for CodeAlpaca-20k & gpt4all_pruned dataset by @andreaskoepf in #2273
- Add support for Cerebras-GPT for training by @olliestanley in #2276
- typo in parsing openai/summarize_from_feedback by @mikegarts in #2268
- Add rng_seed parameter to trainers by @andreaskoepf in #2254
- Computing message queue positions by @yk in #2235
- Remove assigning eos token id (llama compatibility) by @andreaskoepf in #2280
- Fix call-to-action responsiveness by @theopfr in #2290
- Added max size to work queue and an error response if full when enqueuing by @yk in #2279
- Fix loading of Nebulous/gpt4all_pruned dataset by @andreaskoepf in #2291
- Move create chat button to the top by @AbdBarho in #2292
- remove CUDA_VISIBLE_DEVICES= which is user specific by @kno10 in #2295
- Use trusted clients for inference auth by @AbdBarho in #2278
- Add missing variables to deployment job by @AbdBarho in #2297
- two more datasets by @mikegarts in #2301
- Added a link to chat to the sidebar by @yk in #2303
- Added CTA buttons to the frontpage by @yk in #2302
- changed basic hf server to support quantization and streaming by @yk in #2293
New Contributors
- @michaelthwan made their first contribution in #2170
- @CloseChoice made their first contribution in #2246
- @irfantogluk made their first contribution in #2270
- @mikegarts made their first contribution in #2268
- @kno10 made their first contribution in #2295
Full Changelog: v0.0.1-beta57...v0.0.1-beta58