https://ainewz.ai/daily1.0https://ainewz.ai/story/4m-models-scanned-protect-ai-hugging-face-6-months-in-hugging-face-and-protec-1080/weekly0.8https://ainewz.ai/story/17-reasons-why-gradio-isn-t-just-another-ui-library-introduction-oh-gradio-th-1076/weekly0.8https://ainewz.ai/story/accelerating-llm-inference-with-tgi-on-intel-gaudi-what-s-new-we-ve-fully-i-1089/weekly0.8https://ainewz.ai/story/accelerating-pytorch-distributed-fine-tuning-with-intel-technologies-graphical-p-1106/weekly0.8https://ainewz.ai/story/active-learning-with-autonlp-and-prodigy-autonlp-autonlp-is-a-framework-created-1099/weekly0.8https://ainewz.ai/story/ai-policy-response-to-the-white-house-ai-action-plan-rfi-context-don-t-slee-1095/weekly0.8https://ainewz.ai/story/analytics-is-important-analytics-and-metrics-are-the-cornerstone-of-understandin-1093/weekly0.8https://ainewz.ai/story/arabic-leaderboards-introducing-arabic-instruction-following-updating-aragen-1083/weekly0.8https://ainewz.ai/story/blazingly-fast-whisper-transcriptions-with-inference-endpoints-through-this-rele-1065/weekly0.8https://ainewz.ai/story/block-sparse-matrices-for-smaller-and-faster-language-models-saving-space-and-ti-1143/weekly0.8https://ainewz.ai/story/codeagents-structure-a-better-way-to-execute-actions-figure-1-accuracy-compa-1053/weekly0.8https://ainewz.ai/story/cohere-on-hugging-face-inference-providers-we-re-thrilled-to-share-that-cohere-1077/weekly0.8https://ainewz.ai/story/course-launch-community-event-to-go-with-this-release-we-are-organizing-a-large-1109/weekly0.8https://ainewz.ai/story/deep-learning-over-the-internet-training-language-models-collaboratively-in-thi-1119/weekly0.8https://ainewz.ai/story/dell-enterprise-hub-is-all-you-need-to-build-ai-on-premises-models-ready-for-act-1055/weekly0.8https://ainewz.ai/story/deploy-hugging-face-models-easily-with-amazon-sagemaker-today-we-are-excited-1121/weekly0.8https://ainewz.ai/story/distributed-training-train-bart-t5-for-summarization-using-transformers-and-a-1127/weekly0.8https://ainewz.ai/story/efficient-request-queueing-optimizing-llm-performance-starting-point-a-bare-i-1087/weekly0.8https://ainewz.ai/story/exploring-quantization-backends-in-diffusers-before-we-dive-into-the-technical-d-1059/weekly0.8https://ainewz.ai/story/falcon-arabic-a-breakthrough-in-arabic-language-models-we-are-excited-to-introd-1058/weekly0.8https://ainewz.ai/story/falcon-edge-a-series-of-powerful-universal-fine-tunable-1-58bit-language-mode-1062/weekly0.8https://ainewz.ai/story/falcon-h1-a-family-of-hybrid-head-language-models-redefining-efficiency-and-per-1057/weekly0.8https://ainewz.ai/story/faster-tensorflow-models-in-hugging-face-transformers-computational-performanc-1136/weekly0.8https://ainewz.ai/story/few-shot-learning-in-practice-gpt-neo-and-the-accelerated-inference-api-what-1123/weekly0.8https://ainewz.ai/story/fine-tune-wav2vec2-for-english-asr-with-transformers-using-a-novel-contrastive-1131/weekly0.8https://ainewz.ai/story/fine-tuning-clip-with-remote-sensing-satellite-images-and-captions-fine-tuning-1113/weekly0.8https://ainewz.ai/story/fine-tuning-xls-r-for-multi-lingual-asr-with-transformers-wav2vec2-is-a-pretra-1107/weekly0.8https://ainewz.ai/story/finetuning-olmocr-to-be-a-faithful-ocr-engine-in-this-example-crucial-informati-1074/weekly0.8https://ainewz.ai/story/fit-more-and-train-faster-with-zero-via-deepspeed-and-fairscale-as-recent-machin-1137/weekly0.8https://ainewz.ai/story/getting-started-with-hugging-face-transformers-for-ipus-with-optimum-luckily-hu-1104/weekly0.8https://ainewz.ai/story/gradio-is-joining-hugging-face-gradio-is-joining-hugging-face-by-acquiring-gra-1100/weekly0.8https://ainewz.ai/story/holo1-new-family-of-gui-automation-vlms-powering-gui-agent-surfer-h-surfer-h-a-1050/weekly0.8https://ainewz.ai/story/hosting-your-models-and-datasets-on-hugging-face-spaces-using-streamlit-showcase-1114/weekly0.8https://ainewz.ai/story/how-hugging-face-scaled-secrets-management-for-ai-infrastructure-last-year-the-1088/weekly0.8https://ainewz.ai/story/how-to-build-an-mcp-server-in-5-lines-of-python-updated-september-2025-this-p-1068/weekly0.8https://ainewz.ai/story/how-to-generate-text-using-different-decoding-methods-for-language-generation-w-1145/weekly0.8https://ainewz.ai/story/how-to-train-a-new-language-model-from-scratch-using-transformers-and-tokenizers-1146/weekly0.8https://ainewz.ai/story/how-we-sped-up-transformer-inference-100x-for-api-customers-while-experimentin-1138/weekly0.8https://ainewz.ai/story/hugging-face-and-cloudflare-partner-to-make-real-time-speech-and-video-seamless-1082/weekly0.8https://ainewz.ai/story/hugging-face-and-graphcore-partner-for-ipu-optimized-transformers-graphcore-and-1117/weekly0.8https://ainewz.ai/story/hugging-face-on-pytorch-xla-tpus-faster-and-cheaper-training-training-your-fa-1135/weekly0.8https://ainewz.ai/story/hugging-face-reads-feb-2021-long-range-transformers-each-month-we-will-choo-1132/weekly0.8https://ainewz.ai/story/hugging-face-to-sell-open-source-robots-thanks-to-pollen-robotics-acquisition-1079/weekly0.8https://ainewz.ai/story/hyperparameter-search-with-transformers-and-ray-tune-a-guest-blog-post-by-richar-1141/weekly0.8https://ainewz.ai/story/improving-hugging-face-model-access-for-kaggle-users-beginning-today-kaggle-is-1064/weekly0.8https://ainewz.ai/story/introducing-accelerate-accelerate-run-your-raw-pytorch-training-scripts-on-a-1126/weekly0.8https://ainewz.ai/story/introducing-gradio-s-new-dataframe-gr-dataframe-component-is-one-of-our-most-po-1092/weekly0.8https://ainewz.ai/story/introducing-helmet-holistically-evaluating-long-context-language-models-paper-1078/weekly0.8https://ainewz.ai/story/introducing-optimum-the-optimization-toolkit-for-transformers-at-scale-why-1118/weekly0.8https://ainewz.ai/story/introducing-snowball-fight-our-first-ml-agents-environment-snowball-fight-is-1103/weekly0.8https://ainewz.ai/story/introducing-the-data-measurements-tool-an-interactive-tool-for-looking-at-dat-1105/weekly0.8https://ainewz.ai/story/journey-to-1-million-gradio-users-5-years-ago-we-launched-gradio-as-a-simple-p-1085/weekly0.8https://ainewz.ai/story/large-language-models-a-new-moore-s-law-this-is-an-impressive-show-of-machine-1110/weekly0.8https://ainewz.ai/story/lerobot-community-datasets-the-imagenet-of-robotics-when-and-how-in-this-p-1067/weekly0.8https://ainewz.ai/story/leveraging-pre-trained-language-model-checkpoints-for-encoder-decoder-models-sim-1139/weekly0.8https://ainewz.ai/story/liger-grpo-meets-trl-motivation-fine-tuning-language-models-using-reinforcemen-1054/weekly0.8https://ainewz.ai/story/microsoft-and-hugging-face-expand-collaboration-to-make-open-models-easy-to-use-1061/weekly0.8https://ainewz.ai/story/my-journey-to-a-serverless-transformers-pipeline-on-google-cloud-this-article-wi-1130/weekly0.8https://ainewz.ai/story/nanovlm-the-simplest-repository-to-train-your-vlm-in-pure-pytorch-we-were-inspi-1060/weekly0.8https://ainewz.ai/story/no-gpu-left-behind-unlocking-efficiency-with-co-located-vllm-in-trl-introduct-1052/weekly0.8https://ainewz.ai/story/nvidia-s-gtc-2025-announcement-for-physical-ai-developers-new-open-models-and-d-1096/weekly0.8https://ainewz.ai/story/open-r1-how-to-use-olympiccoder-locally-for-coding-everyone-s-been-using-claude-1094/weekly0.8https://ainewz.ai/story/open-r1-update-4-welcome-deepseek-v3-0324-this-week-a-new-model-from-deepseek-1090/weekly0.8https://ainewz.ai/story/perceiver-io-a-scalable-fully-attentional-model-that-works-on-any-modality-tld-1101/weekly0.8https://ainewz.ai/story/pipelinerl-in-this-blog-post-we-show-that-1-inflight-weight-updates-do-not-har-1072/weekly0.8https://ainewz.ai/story/porting-fairseq-wmt19-translation-system-to-transformers-a-guest-blog-post-by-st-1140/weekly0.8https://ainewz.ai/story/prefill-and-decode-for-concurrent-requests-optimizing-llm-performance-at-tng-1075/weekly0.8https://ainewz.ai/story/real-time-ai-sound-generation-on-arm-a-personal-tool-for-creative-freedom-as-a-1049/weekly0.8https://ainewz.ai/story/retrieval-augmented-generation-with-huggingface-transformers-and-ray-a-guest-blo-1134/weekly0.8https://ainewz.ai/story/scaling-up-bert-like-model-inference-on-modern-cpu-part-1-1-context-and-motiv-1125/weekly0.8https://ainewz.ai/story/scaling-up-bert-like-model-inference-on-modern-cpu-part-2-introduction-using-1108/weekly0.8https://ainewz.ai/story/sentence-transformers-in-the-hugging-face-hub-sentence-transformers-is-a-framewo-1122/weekly0.8https://ainewz.ai/story/showcase-your-projects-in-spaces-using-gradio-in-this-blog-post-we-ll-walk-you-1115/weekly0.8https://ainewz.ai/story/simple-considerations-for-simple-people-building-fancy-neural-networks-photo-b-1133/weekly0.8https://ainewz.ai/story/smolvla-efficient-vision-language-action-model-trained-on-lerobot-community-dat-1051/weekly0.8https://ainewz.ai/story/spaces-duplicated-from-r3gm-wan2-2-fp8da-aoti-preview-r3gm-wan2-2-fp8da-aoti-p-1147/weekly0.8https://ainewz.ai/story/spaces-duplicated-from-zerogpu-aoti-wan2-2-fp8da-aoti-faster-r3gm-wan2-2-fp8da-1148/weekly0.8https://ainewz.ai/story/summer-at-hugging-face-in-this-blog-post-you-ll-catch-up-on-everything-that-ha-1116/weekly0.8https://ainewz.ai/story/the-4-things-qwen-3-s-chat-template-teaches-us-the-new-qwen-3-model-by-qwen-ship-1069/weekly0.8https://ainewz.ai/story/the-age-of-machine-learning-as-code-has-arrived-ai-is-increasingly-being-applie-1112/weekly0.8https://ainewz.ai/story/the-nlp-course-is-becoming-the-llm-course-education-has-always-been-at-the-hear-1086/weekly0.8https://ainewz.ai/story/the-partnership-amazon-sagemaker-and-hugging-face-look-at-these-smiles-today-1129/weekly0.8https://ainewz.ai/story/the-reformer-pushing-the-limits-of-language-modeling-how-the-reformer-uses-les-1144/weekly0.8https://ainewz.ai/story/the-transformers-library-standardizing-model-definitions-transformers-was-creat-1063/weekly0.8https://ainewz.ai/story/tiny-agents-an-mcp-powered-agent-in-50-lines-of-code-tiny-agents-in-python-ne-1073/weekly0.8https://ainewz.ai/story/tiny-agents-in-python-an-mcp-powered-agent-in-70-lines-of-code-agents-md-stand-1056/weekly0.8https://ainewz.ai/story/train-a-sentence-embedding-model-with-1-billion-training-pairs-we-developed-stat-1111/weekly0.8https://ainewz.ai/story/training-and-finetuning-reranker-models-with-sentence-transformers-finetuning-re-1091/weekly0.8https://ainewz.ai/story/training-codeparrot-from-scratch-creating-a-large-dataset-of-source-code-the-f-1102/weekly0.8https://ainewz.ai/story/transformers-based-encoder-decoder-models-pip-install-transformers-4-2-1-pip-1142/weekly0.8https://ainewz.ai/story/understanding-bigbird-s-block-sparse-attention-introduction-transformer-based-mo-1128/weekly0.8https://ainewz.ai/story/using-mixing-hugging-face-models-with-gradio-2-0-cross-posted-from-the-gradio-1124/weekly0.8https://ainewz.ai/story/vision-language-models-better-faster-stronger-motivation-vision-language-mod-1066/weekly0.8https://ainewz.ai/story/visual-salamandra-pushing-the-boundaries-of-multimodal-understanding-designed-w-1081/weekly0.8https://ainewz.ai/story/welcome-gemma-3-google-s-all-new-multimodal-multilingual-long-context-open-ll-1098/weekly0.8https://ainewz.ai/story/welcome-llama-4-maverick-scout-on-hugging-face-released-today-these-powerful-1084/weekly0.8https://ainewz.ai/story/welcome-spacy-to-the-hugging-face-hub-hugging-face-makes-it-really-easy-to-share-1120/weekly0.8https://ainewz.ai/story/welcoming-llama-guard-4-on-hugging-face-hub-table-of-contents-what-is-llama-guar-1070/weekly0.8https://ainewz.ai/story/what-is-autoround-autoround-is-a-weight-only-post-training-quantization-ptq-m-1071/weekly0.8https://ainewz.ai/story/xet-is-on-the-hub-over-the-past-few-weeks-hugging-face-s-xet-team-took-a-major-1097/weekly0.8