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

b3332

b5040086 · llama : fix n_rot default (#8348) · Jul 07, 2024
b3328

cb4d86c4 · server: Retrieve prompt template in /props (#8337) · Jul 07, 2024
b3327

86e7299e · added support for Authorization Bearer tokens when downloading model (#8307) · Jul 06, 2024
b3325

87e25a1d · llama : add early return for empty range (#8327) · Jul 06, 2024
gguf-v0.9.0

87e25a1d · llama : add early return for empty range (#8327) · Jul 06, 2024
b3324

213701b5 · Detokenizer fixes (#8039) · Jul 05, 2024
b3322

7ed03b89 · llama : fix compile warning (#8304) · Jul 05, 2024
b3317

8e558309 · CUDA: MMQ support for iq4_nl, iq4_xs (#8278) · Jul 05, 2024
b3316

0a423800 · CUDA: revert part of the RDNA1 optimizations (#8309) · Jul 05, 2024
b3315

d12f7810 · llama : streamline embeddings from "non-embedding" models (#8087) · Jul 05, 2024
b3314

bcefa03b · CUDA: fix MMQ stream-k rounding if ne00 % 128 != 0 (#8311) · Jul 05, 2024
b3311

aa5898dc · llama : prefer n_ over num_ prefix (#8308) · Jul 05, 2024
b3309

a9554e20 · [SYCL] Fix WARP_SIZE=16 bug of Intel GPU (#8266) · Jul 05, 2024
b3307

f09b7cb6 · rm get_work_group_size() by local cache for performance (#8286) · Jul 05, 2024
b3306

a38b884c · cli: add EOT when user hit Ctrl+C (#8296) · Jul 04, 2024
b3305

d7fd29ff · llama : add OpenELM support (#7359) · Jul 04, 2024
b3304

6f63d646 · tokenize : add --show-count (token) option (#8299) · Jul 04, 2024
b3303

51d2ebad · build: Export hf-to-gguf as snakecase · Jul 04, 2024
b3295

807b0c49 · Inference support for T5 and FLAN-T5 model families (#5763) · Jul 04, 2024
b3294

f8c4c073 · tests : add _CRT_SECURE_NO_WARNINGS for WIN32 (#8231) · Jul 04, 2024

1
…
67
68
69
70
71
72
73
74
75
…
178