summaryrefslogtreecommitdiff
path: root/candle-transformers
Commit message (Expand)AuthorAgeFilesLines
...
* fix: qwen2 lm_head loading #2443 (#2445)ilookee2024-08-231-1/+1
* Add FastViT model. (#2444)Jani Monoses2024-08-232-0/+513
* Fix for parler-tts, do not add the last slice of padding tokens. (#2442)Laurent Mazare2024-08-221-1/+0
* Add the DAC model. (#2433)Laurent Mazare2024-08-194-1/+383
* parler-tts support (#2431)Laurent Mazare2024-08-182-0/+453
* Add support for gemma-2. (#2425)Laurent Mazare2024-08-172-0/+450
* Fix the device for the bert attention mask. (#2414)Laurent Mazare2024-08-141-1/+2
* Add Based LLM from Hazy Research. (#2411)Jani Monoses2024-08-122-0/+590
* Soft Non-Maximum Suppression (#2400)Matthew O'Malley-Nichols2024-08-102-0/+280
* Add the MMDiT model of Stable Diffusion 3 (#2397)Czxck0012024-08-056-0/+763
* add models support and example for THUDM/glm-4 (#2362)唐璜2024-08-052-0/+596
* Support for mistral-nemo. (#2396)Laurent Mazare2024-08-041-5/+12
* Simplify handling of flux modulations. (#2394)Laurent Mazare2024-08-041-46/+88
* Add the flux model for image generation. (#2390)Laurent Mazare2024-08-045-0/+1145
* Fix cargo fmt. (#2383)Laurent Mazare2024-08-011-0/+1
* Jina Bert Example fix and more configuration (#2191)Joan Fontanals2024-08-011-0/+30
* Add Hiera vision model. (#2382)Jani Monoses2024-08-012-0/+303
* bert attention mask (#1934)Zheng Li2024-08-011-17/+32
* Add support for Llama 3.1 (#2359)Eric Buehler2024-07-2614-50/+125
* feat(candle-transformers/models/codegeex4-9b): add codegeex4-9 (#2334)donjuanplatinum2024-07-212-0/+597
* add quantized qwen2 (#2329)Zhuo Jinggang2024-07-122-0/+324
* Add Mobilenet v4 (#2325)Jani Monoses2024-07-092-0/+801
* Add EVA-02 model ( https://arxiv.org/abs/2303.11331 ) (#2311)v-espitalier2024-07-072-0/+419
* Beit: Add the gen_relative_position_index() function (#2306)v-espitalier2024-07-041-26/+63
* Add Beit model ( https://arxiv.org/abs/2106.08254 ) (#2305)v-espitalier2024-07-012-0/+368
* Add DINOv2Reg4 + PlantCLEF2024 (#2293)v-espitalier2024-06-292-0/+282
* Depth Anything v2 (#2279)Jeroen Vlek2024-06-243-0/+632
* Fix the fast bf16 gemm cublas kernels. (#2274)Laurent Mazare2024-06-181-2/+1
* Support for the new Qwen2 models. (#2257)Laurent Mazare2024-06-071-2/+6
* Add LLaVA support (#2234)chenwanqq2024-06-037-0/+776
* Add Debug, Clone, Deserialize to moondream config (#2222)Dave Lage2024-05-281-0/+1
* Enable the new layer-norm. (#2213)Laurent Mazare2024-05-241-8/+4
* Avoid a contiguous call in the quantized phi 3 model. (#2209)Laurent Mazare2024-05-231-1/+1
* Simplify the KvCache api. (#2207)Laurent Mazare2024-05-231-7/+1
* Use flash-attn in gemma. (#2195)Laurent Mazare2024-05-181-18/+44
* Support flash-attn in quantized phi3. (#2194)Laurent Mazare2024-05-181-10/+40
* Add a slice_set op. (#2193)Laurent Mazare2024-05-181-22/+19
* Support embedding model gte-Qwen1.5-7B-instruct (#2190)Yin Guobing2024-05-161-15/+62
* Separate quantized phi-3 implementation. (#2157)Laurent Mazare2024-05-043-4/+306
* Bump the version number to 0.5.1. (#2155)Laurent Mazare2024-05-031-1/+1
* Add argsort. (#2132)Laurent Mazare2024-04-272-43/+21
* Add Olmo models (#2127)Isotr0py2024-04-262-0/+338
* Add the phi-3 model. (#2120)Laurent Mazare2024-04-242-0/+330
* Use the faster rms-norm kernel for llama. (#2107)Laurent Mazare2024-04-221-0/+5
* Updated quantized phi model (#2099)Laurent Mazare2024-04-212-0/+289
* Derive clone and debug traits for Moondream model (#2100)Santiago Medina2024-04-211-0/+1
* Small cleanups to the llama multi-process example. (#2098)Laurent Mazare2024-04-201-1/+7
* Fix for gemma MQA. (#2091)Laurent Mazare2024-04-191-2/+3
* Use faster rotary embeddings for llama like models. (#2087)Laurent Mazare2024-04-181-11/+6
* Llama v3. (#2085)Laurent Mazare2024-04-181-0/+10
generated by cgit v1.2.3 (git 2.39.1) at 2025-04-03 14:42:59 +0000