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

b4365

36319dec · tts : small QoL for easy model fetch (#10903) · Dec 19, 2024
b4363

a3c33b1d · ggml: fix arm build with gcc (#10895) · Dec 19, 2024
b4362

2fffc52b · llama : fix Roberta embeddings (#10856) · Dec 19, 2024
b4361

7585edbd · convert : Add support for Microsoft Phi-4 model (#10817) · Dec 19, 2024
b4360

cd920d0a · tests: disable GGUF test for bad value size (#10886) · Dec 19, 2024
b4359

7909e858 · llama-run : improve progress bar (#10821) · Dec 19, 2024
b4358

9177484f · ggml : fix arm build (#10890) · Dec 18, 2024
b4357

0bf2d10c · tts : add OuteTTS support (#10784) · Dec 18, 2024
b4354

0e70ba68 · server : add "tokens" output (#10853) · Dec 18, 2024
b4353

46828872 · server : (embeddings) using same format for "input" and "content" (#10872) · Dec 18, 2024
b4351

4da69d1a · Revert "llama : add Falcon3 support (#10864)" (#10876) · Dec 18, 2024
b4350

d62b532c · Use model->gguf_kv for loading the template instead of using the C API. (#10868) · Dec 17, 2024
b4349

081b29bd · tests: add tests for GGUF (#10830) · Dec 17, 2024
b4348

5437d4aa · sync : ggml · Dec 17, 2024
b4343

0006f5a7 · ggml : update ggml_backend_cpu_device_supports_op (#10867) · Dec 17, 2024
b4342

05c3a444 · server : fill usage info in embeddings and rerank responses (#10852) · Dec 17, 2024
b4341

382bc7f2 · llama : add Falcon3 support (#10864) · Dec 17, 2024
b4338

7b1ec53f · vulkan: bugfixes for small subgroup size systems + llvmpipe test (#10809) · Dec 17, 2024
b4337

160bc039 · rwkv6: add wkv6 support for Vulkan backend (#10829) · Dec 16, 2024
b4333

a0974156 · llama : add Deepseek MoE v1 & GigaChat models (#10827) · Dec 15, 2024

1
…
32
33
34
35
36
37
38
39
40
…
178