| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | Fix cargo fmt. (#2383) | Laurent Mazare | 2024-08-01 | 1 | -0/+1 |
| * | Jina Bert Example fix and more configuration (#2191) | Joan Fontanals | 2024-08-01 | 1 | -0/+30 |
| * | Add Hiera vision model. (#2382) | Jani Monoses | 2024-08-01 | 2 | -0/+303 |
| * | bert attention mask (#1934) | Zheng Li | 2024-08-01 | 1 | -17/+32 |
| * | Add support for Llama 3.1 (#2359) | Eric Buehler | 2024-07-26 | 14 | -50/+125 |
| * | feat(candle-transformers/models/codegeex4-9b): add codegeex4-9 (#2334) | donjuanplatinum | 2024-07-21 | 2 | -0/+597 |
| * | add quantized qwen2 (#2329) | Zhuo Jinggang | 2024-07-12 | 2 | -0/+324 |
| * | Add Mobilenet v4 (#2325) | Jani Monoses | 2024-07-09 | 2 | -0/+801 |
| * | Add EVA-02 model ( https://arxiv.org/abs/2303.11331 ) (#2311) | v-espitalier | 2024-07-07 | 2 | -0/+419 |
| * | Beit: Add the gen_relative_position_index() function (#2306) | v-espitalier | 2024-07-04 | 1 | -26/+63 |
| * | Add Beit model ( https://arxiv.org/abs/2106.08254 ) (#2305) | v-espitalier | 2024-07-01 | 2 | -0/+368 |
| * | Add DINOv2Reg4 + PlantCLEF2024 (#2293) | v-espitalier | 2024-06-29 | 2 | -0/+282 |
| * | Depth Anything v2 (#2279) | Jeroen Vlek | 2024-06-24 | 3 | -0/+632 |
| * | Fix the fast bf16 gemm cublas kernels. (#2274) | Laurent Mazare | 2024-06-18 | 1 | -2/+1 |
| * | Support for the new Qwen2 models. (#2257) | Laurent Mazare | 2024-06-07 | 1 | -2/+6 |
| * | Add LLaVA support (#2234) | chenwanqq | 2024-06-03 | 7 | -0/+776 |
| * | Add Debug, Clone, Deserialize to moondream config (#2222) | Dave Lage | 2024-05-28 | 1 | -0/+1 |
| * | Enable the new layer-norm. (#2213) | Laurent Mazare | 2024-05-24 | 1 | -8/+4 |
| * | Avoid a contiguous call in the quantized phi 3 model. (#2209) | Laurent Mazare | 2024-05-23 | 1 | -1/+1 |
| * | Simplify the KvCache api. (#2207) | Laurent Mazare | 2024-05-23 | 1 | -7/+1 |
| * | Use flash-attn in gemma. (#2195) | Laurent Mazare | 2024-05-18 | 1 | -18/+44 |
| * | Support flash-attn in quantized phi3. (#2194) | Laurent Mazare | 2024-05-18 | 1 | -10/+40 |
| * | Add a slice_set op. (#2193) | Laurent Mazare | 2024-05-18 | 1 | -22/+19 |
| * | Support embedding model gte-Qwen1.5-7B-instruct (#2190) | Yin Guobing | 2024-05-16 | 1 | -15/+62 |
| * | Separate quantized phi-3 implementation. (#2157) | Laurent Mazare | 2024-05-04 | 3 | -4/+306 |
| * | Bump the version number to 0.5.1. (#2155) | Laurent Mazare | 2024-05-03 | 1 | -1/+1 |
| * | Add argsort. (#2132) | Laurent Mazare | 2024-04-27 | 2 | -43/+21 |
| * | Add Olmo models (#2127) | Isotr0py | 2024-04-26 | 2 | -0/+338 |
| * | Add the phi-3 model. (#2120) | Laurent Mazare | 2024-04-24 | 2 | -0/+330 |
| * | Use the faster rms-norm kernel for llama. (#2107) | Laurent Mazare | 2024-04-22 | 1 | -0/+5 |
| * | Updated quantized phi model (#2099) | Laurent Mazare | 2024-04-21 | 2 | -0/+289 |
| * | Derive clone and debug traits for Moondream model (#2100) | Santiago Medina | 2024-04-21 | 1 | -0/+1 |
| * | Small cleanups to the llama multi-process example. (#2098) | Laurent Mazare | 2024-04-20 | 1 | -1/+7 |
| * | Fix for gemma MQA. (#2091) | Laurent Mazare | 2024-04-19 | 1 | -2/+3 |
| * | Use faster rotary embeddings for llama like models. (#2087) | Laurent Mazare | 2024-04-18 | 1 | -11/+6 |
| * | Llama v3. (#2085) | Laurent Mazare | 2024-04-18 | 1 | -0/+10 |
| * | Make the falcon model cloneable. (#2067) | Laurent Mazare | 2024-04-15 | 1 | -5/+5 |
| * | Add a function to clear the KV cache in falcon. (#2066) | Laurent Mazare | 2024-04-15 | 1 | -0/+14 |
| * | Add a quantized version of recurrent-gemma. (#2054) | Laurent Mazare | 2024-04-13 | 4 | -61/+477 |
| * | Avoid crashes when running T5 models with F16 tensors on CPU (#2047) | Victor-Mihaila | 2024-04-13 | 1 | -1/+1 |
| * | Change for the encoder-only ProstT5 model (#2045) | Victor-Mihaila | 2024-04-13 | 1 | -1/+3 |
| * | Add the recurrent-gemma model. (#2039) | Laurent Mazare | 2024-04-13 | 2 | -0/+641 |
| * | Use cat for faster MQA computation. (#2043) | Laurent Mazare | 2024-04-12 | 16 | -195/+47 |
| * | Add the code-gemma models. (#2038) | Laurent Mazare | 2024-04-10 | 1 | -4/+15 |
| * | Support alternative dtypes for mamba (#2036) | Laurent Mazare | 2024-04-10 | 3 | -8/+15 |
| * | Add the new gemma models. (#2023) | Laurent Mazare | 2024-04-06 | 1 | -0/+1 |
| * | Fix the final rmsnorm for quantized-metavoice. (#2021) | Laurent Mazare | 2024-04-06 | 1 | -0/+1 |
| * | Faster mask implementation for mixformers. (#2017) | Laurent Mazare | 2024-04-05 | 1 | -21/+6 |
| * | Moondream tracing. (#2016) | Laurent Mazare | 2024-04-05 | 2 | -13/+48 |
| * | Add the rope THD kernel. (#2014) | Laurent Mazare | 2024-04-05 | 1 | -22/+6 |
