Mingzhuo Yin
Mingzhuo Yin
Wait for https://github.com/openssh-rust/openssh/issues/119
Benchmark results in aws [r6a.xlarge](https://aws.amazon.com/cn/ec2/instance-types/r6a/) (4 vCPU, 32 GB) for reference pgvector_rust_HNSW_single_node_laion-768-5m-ip: | num | precisions | rps | | --- | ---------- | ------ | | 1 | 93.64%...
https://github.com/TusKANNy/seismic ## benchmark on my local machine - datasets: Splade on Ms Marco small - machine: 8 vCPU, 32 GB, AMD Ryzen 7 7700, vmware Virtualization - index build time:...
About [`Triggered by Size Ratio`](https://skyzh.github.io/mini-lsm/week2-03-tiered.html#task-12-triggered-by-size-ratio) in [`Universal Compaction`](https://skyzh.github.io/mini-lsm/week2-03-tiered.html#task-1-universal-compaction), it says `For all tiers, if there is a tier n that size of all previous tiers / this tier >= (100...
(`cls.predictions.decoder.weight`, `bert.embeddings.word_embeddings.weight`) and (`cls.predictions.decoder.bias`, `cls.predictions.bias`) are shared tensor in `BertForMaskedLM` model. They may not exist in `model.safetensors` file.
It seems that attention mask should be reversed first in `distilbert::MultiHeadSelfAttention` https://github.com/huggingface/transformers/blob/main/src/transformers/models/distilbert/modeling_distilbert.py#L218
## Tasks - [x] Introducing new cpp binding #2980 - [x] Add Contribution docs #2984 - [x] Add API documents #2988 - [x] Add CI jobs on building and testing...
I hereby agree to the terms of the [RisingWave Labs, Inc. Contributor License Agreement](https://raw.githubusercontent.com/risingwavelabs/risingwave/17af8a747593ebdbfa826691daf75bdab7d14fa0/.github/contributor-license-agreement.txt). ## What's changed and what's your intention? This PR improves error handling in the DataFusion integration....