为了安全，强烈建议开启2FA双因子认证：User Settings -> Account -> Enable two-factor authentication！！！

Tags

Tags give the ability to mark specific points in history as being important

b1383

940efa95 · llava : fix tokenization to not add bos between image embeddings and user prompt (#3645) · Oct 16, 2023
b1382

11bff290 · MPT : support GQA for replit-code-v1.5 (#3627) · Oct 15, 2023
b1381

11dc1091 · Honor -ngl option for Cuda offloading in llava (#3621) · Oct 14, 2023
b1380

2a4bcbac · llama : remove n_threads from llama_decode_internal (#3614) · Oct 13, 2023
b1379

424b6381 · ggml : add context enumeration functions (#3605) · Oct 13, 2023
b1378

1e0e873c · CLBlast: Fix matrix-vector multiplication (#3544) · Oct 12, 2023
b1377

370359e5 · examples: support LLaVA v1.5 (multimodal model) (#3436) · Oct 12, 2023
b1375

d28e572c · cmake : fix add_compile_options on macOS · Oct 12, 2023
b1372

b016596d · server : add completion mode (no chat) (#3582) · Oct 12, 2023
b1370

57dd55e2 · server : fix kv cache management (#3588) · Oct 12, 2023
b1369

b8fe4b5c · main : fix session loading bug (#3400) · Oct 11, 2023
b1368

a8bdd655 · server : add parameter -tb N, --threads-batch N (#3584) · Oct 11, 2023
b1367

70c29da1 · common : fix mirostat state when using multiple sequences (#3543) · Oct 11, 2023
b1366

8c70a5ff · batched : add bench tool (#3545) · Oct 11, 2023
b1365

24ba3d82 · examples : add batched.swift + improve CI for swift (#3562) · Oct 11, 2023
b1363

233fc1c6 · Minor improvements in GPT2 tokenizer (#3567) · Oct 10, 2023
b1360

0aa6595a · swift : improvements and fixes (#3564) · Oct 10, 2023
b1359

f5f9121d · llm : add MPT support (#3417) · Oct 10, 2023
b1358

11ea5c7d · infill. : fix tokenization (#3508) · Oct 10, 2023
b1357

95bd60a0 · ggml-alloc : fix assert in debug builds (#3555) · Oct 09, 2023