LocalAI v1.17.0 — Release Notes & Engineering Impact
LocalAI v1.17.0. Source highlight: Bump rwkv
AI Models & LLM Frameworks archive — Page 22
1172 tracked entries. Older history is imported progressively; see source coverage.
LocalAI v1.16.0 — Release Notes & Engineering Impact
LocalAI v1.16.0. Source highlight: :arrow_up: Update ggerganov/whisper.cpp
Dify: Version 0.3.0
Dify 0.3.0. Source highlight: Feat/explore
Dify: Version 0.2.2
Dify 0.2.2. Source highlight: fix: Fix symbol errors in the nodejs-client's README.md file of the SDK
LocalAI v1.15.0 — Release Notes & Engineering Impact
LocalAI v1.15.0. Source highlight: feat: update go-gpt2
Hugging Face Transformers: v4.29.2: Patch release
Hugging Face Transformers v4.29.2 is published, but the available notes are too limited to assess upgrade impact. Review the official source before upgrading.
Dify: Version 0.2.1
Dify 0.2.1 is published, but the available notes are too limited to assess upgrade impact. Review the official source before upgrading.
Hugging Face Transformers: V4.29.1: Patch release
Hugging Face Transformers v4.29.1. Source highlight: Reverts a regression in the FSDP integration.
Hugging Face Transformers: v4.29.0: Transformers Agents, SAM, RWKV, FocalNet, OpenLLaMa
Hugging Face Transformers v4.29.0. Source highlight: Transformers Agent is a new API that lets you use the library and Diffusers by prompting an agent (which is a large language model) in natural language. That agent will then output code using a set of predefined tools, leveraging the appropriate (and state-of-the-art) models for the task the user wa
Hugging Face Transformers: v4.28.1: Patch release
Hugging Face Transformers v4.28.1 is published, but the available notes are too limited to assess upgrade impact. Review the official source before upgrading.
Hugging Face Transformers: v4.28.0: LLaMa, Pix2Struct, MatCha, DePlot, MEGA, NLLB-MoE, GPTBigCode
Hugging Face Transformers v4.28.0. Source highlight: The LLaMA model was proposed in LLaMA: Open and Efficient Foundation Language Models. It is a collection of foundation language models ranging from 7B to 65B parameters. You can request access to the weights here then use the conversion script to generate a checkpoint compatible with Hugging Face
Hugging Face Transformers: v4.27.4: Patch release
Hugging Face Transformers v4.27.4. Source highlight: This patch fixes a regression with FlauBERT and XLM models.
Hugging Face Transformers: v4.27.3: Patch release
Hugging Face Transformers v4.27.3 is published, but the available notes are too limited to assess upgrade impact. Review the official source before upgrading.
Hugging Face Transformers: v4.27.2: Patch release
Hugging Face Transformers v4.27.2 is published, but the available notes are too limited to assess upgrade impact. Review the official source before upgrading.
Hugging Face Transformers: v4.27.1: Patch release
Hugging Face Transformers v4.27.1. Source highlight: Patches two unwanted breaking changes that were released in v4.27.0:
Hugging Face Transformers: BridgeTower, Whisper speedup, DETA, SpeechT5, BLIP-2, CLAP, ALIGN, API updates
Hugging Face Transformers v4.27.0. Source highlight: The goal of this model is to build a bridge between each uni-modal encoder and the cross-modal encoder to enable comprehensive and detailed interaction at each layer of the cross-modal encoder thus achieving remarkable performance on various downstream tasks with almost negligible additional perform
Hugging Face Transformers: V4.26.1: Patch release
Hugging Face Transformers v4.26.1. Source highlight: ESM openfold_utils type hints by @ringohoffman in #20544
Hugging Face Transformers: v4.26.0: Generation configs, image processors, backbones and plenty of new models!
Hugging Face Transformers v4.26.0. Source highlight: The `generate` method has multiple arguments whose defaults were lying in the model config. We have now decoupled these in a separate generation config, which makes it easier to store different sets of parameters for a given model, with different generation strategies. While we will keep supporting
Hugging Face Transformers: PyTorch 2.0 support, Audio Spectogram Transformer, Jukebox, Switch Transformers and more
Hugging Face Transformers v4.25.1. Source highlight: PyTorch 2.0 stack support
Hugging Face Transformers: v4.24.0: ESM-2/ESMFold, LiLT, Flan-T5, Table Transformer and Contrastive search decoding
Hugging Face Transformers v4.24.0. Source highlight: ESM-2 and ESMFold are new state-of-the-art Transformer protein language and folding models from Meta AI's Fundamental AI Research Team (FAIR). ESM-2 is trained with a masked language modeling objective, and it can be easily transferred to sequence and token classification tasks for proteins. Checkpo
Hugging Face Transformers: v4.23.1 Patch release
Hugging Face Transformers v4.23.1. Source highlight: Fix a revert introduced by mistake making the `"automatic-speech-recognition"` for Whisper.
Hugging Face Transformers: v4.23.0: Whisper, Deformable DETR, Conditional DETR, MarkupLM, MSN, `safetensors`
Hugging Face Transformers v4.23.0. Source highlight: The Whisper model was proposed in Robust Speech Recognition via Large-Scale Weak Supervision by Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, Ilya Sutskever.
Hugging Face Transformers: # v4.22.2 Patch release
Hugging Face Transformers v4.22.2. Source highlight: Fixes a bug where a cached tokenizer/model was not accessible anymore offline (either forcing offline mode or because of an internet issue).
Hugging Face Transformers: v4.22.1: Patch release:
Hugging Face Transformers v4.22.1. Source highlight: Patch release for the following PRs:
Hugging Face Transformers: v4.22.0: Swin Transformer v2, VideoMAE, Donut, Pegasus-X, X-CLIP, ERNIE
Hugging Face Transformers v4.22.0. Source highlight: The Swin Transformer V2 model was proposed in Swin Transformer V2: Scaling Up Capacity and Resolution by Ze Liu, Han Hu, Yutong Lin, Zhuliang Yao, Zhenda Xie, Yixuan Wei, Jia Ning, Yue Cao, Zheng Zhang, Li Dong, Furu Wei, Baining Guo.
Hugging Face Transformers: v4.21.3: Patch release
Hugging Face Transformers v4.21.3. Source highlight: Patch release to add a disclaimer about torch models hosted on the Hub. See autoclass tutorial.
Hugging Face Transformers: v4.21.2: Patch release
Hugging Face Transformers v4.21.2. Source highlight: Fix a regression in the TableQA pipeline: Fix a regression in Trainer checkpoint loading: #18428
Hugging Face Transformers: # v4.21.1: Patch release
Hugging Face Transformers v4.21.1 is published, but the available notes are too limited to assess upgrade impact. Review the official source before upgrading.
Hugging Face Transformers: v4.21.0: TF XLA text generation - Custom Pipelines - OwlViT, NLLB, MobileViT, Nezha, GroupViT, MVP, CodeGen, UL2
Hugging Face Transformers v4.21.0. Source highlight: TensorFlow XLA Text Generation
Hugging Face Transformers: # v4.20.1 Patch release
Hugging Face Transformers v4.20.1. Source highlight: This patch releases fixes a bug in the OPT models and makes Transformers compatible with `huggingface_hub` version 0.8.1.
Hugging Face Transformers: v4.20.0 Big Model inference, BLOOM, CvT, GPT Neo-X, LayoutLMv3, LeViT, LongT5, M-CTC-T, Trajectory Transformer and Wav2Vec2-Conformer
Hugging Face Transformers v4.20.0. Source highlight: You can now use the big model inference of Accelerate directly in any call to `from_pretrained` by specifying `device_map="auto"` (or your own `device_map`). It will automatically load the model taking advantage of your GPU(s) then offloading what doesn't fit in RAM, or even on the hard drive if you
Hugging Face Transformers: # v4.19.4 Patch release
Hugging Face Transformers v4.19.4. Source highlight: Fixes the errors message when trying to access a repo that does not exist (started to break due to changes in Hub API).
Hugging Face Transformers: # v4.19.3 Patch release
Hugging Face Transformers v4.19.3. Source highlight: This patch release fixes the install of protobuf when a user wants to do `pip install transformers[sentencepiece]`.
Hugging Face Transformers: v4.19.2: Patch release
Hugging Face Transformers v4.19.2. Source highlight: Patch release for the following PRs/commits:
Hugging Face Transformers: v4.19.1 Patch release
Hugging Face Transformers v4.19.1 is published, but the available notes are too limited to assess upgrade impact. Review the official source before upgrading.
Hugging Face Transformers: v4.19.0: OPT, FLAVA, YOLOS, RegNet, TAPEX, Data2Vec vision, FSDP integration
Hugging Face Transformers v4.19.0. Source highlight: *Disclaimer*: this release is the first release with no Python 3.6 support.
Hugging Face Transformers: v4.18.0: Checkpoint sharding, vision models
Hugging Face Transformers v4.18.0. Source highlight: You'll notice that we are starting to add several older models in vision. This is because those models are used as backbones in recent architectures. While we could rely on existing libraries for such pretrained models, we will ultimately need some support for those backbones in PyTorch/TensorFlow a
Hugging Face Transformers: v4.17.0: XGLM, ConvNext, PoolFormer, PLBart, Data2Vec, MaskFormer and code in the Hub
Hugging Face Transformers v4.17.0. Source highlight: The XGLM model was proposed in Few-shot Learning with Multilingual Language Models by Xi Victoria Lin, Todor Mihaylov, Mikel Artetxe, Tianlu Wang, Shuohui Chen, Daniel Simig, Myle Ott, Naman Goyal, Shruti Bhosale, Jingfei Du, Ramakanth Pasunuru, Sam Shleifer, Punit Singh Koura, Vishrav Chaudhary, Br
Hugging Face Transformers: v4.16.2: Patch release
Hugging Face Transformers v4.16.2. Source highlight: Add header (huggingface#15434)
Hugging Face Transformers: # V4.16.1: Patch Release
Hugging Face Transformers v4.16.1 is published, but the available notes are too limited to assess upgrade impact. Review the official source before upgrading.
Hugging Face Transformers: v4.16.0: Nyströmformer, REALM, ViTMAE, ViLT, Swin Transformer, YOSO, ...
Hugging Face Transformers v4.16.0. Source highlight: The Nyströmformer model was proposed in Nyströmformer: A Nyström-Based Algorithm for Approximating Self-Attention by Yunyang Xiong, Zhanpeng Zeng, Rudrasis Chakraborty, Mingxing Tan, Glenn Fung, Yin Li, and Vikas Singh.
Hugging Face Transformers v4.15.0 — Release Notes & Engineering Impact
Hugging Face Transformers v4.15.0. Source highlight: WavLM was proposed in WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing by Sanyuan Chen, Chengyi Wang, Zhengyang Chen, Yu Wu, Shujie Liu, Zhuo Chen, Jinyu Li, Naoyuki Kanda, Takuya Yoshioka, Xiong Xiao, Jian Wu, Long Zhou, Shuo Ren, Yanmin Qian, Yao Qian, Jian Wu, Mich
Hugging Face Transformers: v4.14.1: Patch release
Hugging Face Transformers v4.14.1. Source highlight: v4.14.1 Patch release
Hugging Face Transformers: v4.14.0: Perceiver, Keras model cards
Hugging Face Transformers v4.14.0. Source highlight: The Perceiver model was released in the previous version:
Hugging Face Transformers: v4.13.0: Perceiver, ImageGPT, mLUKE, Vision-Text dual encoders, QDQBert, new documentation frontend
Hugging Face Transformers v4.13.0. Source highlight: Eight new models are released as part of the Perceiver implementation: `PerceiverModel`, `PerceiverForMaskedLM`, `PerceiverForSequenceClassification`, `PerceiverForImageClassificationLearned`, `PerceiverForImageClassificationFourier`, `PerceiverForImageClassificationConvProcessing`, `PerceiverForOpt
Hugging Face Transformers: v4.12.5: Patch release
Hugging Face Transformers v4.12.5. Source highlight: Reverts a commit that introduced other issues:
Hugging Face Transformers: v4.12.4: Patch release
Hugging Face Transformers v4.12.4. Source highlight: Fix gradient_checkpointing backward compatibility (#14408)
Hugging Face Transformers: v4.12.3: Patch release
Hugging Face Transformers v4.12.3. Source highlight: v4.12.3: Patch release
Hugging Face Transformers: v4.12.2: Patch release
Hugging Face Transformers v4.12.2 is published, but the available notes are too limited to assess upgrade impact. Review the official source before upgrading.
Hugging Face Transformers: v4.12.1: Patch release
Hugging Face Transformers v4.12.1 is published, but the available notes are too limited to assess upgrade impact. Review the official source before upgrading.