vb @reach-vb.hf.co · 24/12/2024Qwen released QvQ 72B OpenAI o1 like reasoning model on Hugging Face with Vision capabilities - beating GPT4o, Claude Sonnet 3.5 🔥 4183
vb @reach-vb.hf.co · 06/12/2024BOOOOM! Meta released Llama 3.3 70B - 128K context, multilingual, enhanced tool calling, outperforms Llama 3.1 70B and comparable to Llama 405B 🔥 Comparable performance to 405B with 6x LESSER parameters ⚡ 1291
vb @reach-vb.hf.co · 03/12/2024Introducing Indic-Parler TTS - Trained on 10K hours of data, 938M params, supports 20 Indic languages, emotional synthesis, apache 2.0 licensed! 🔥 w/ fully customisable speech and voice personas! Try it out directly below or use the model weights as you want! 🇮🇳/acc 4353
vb @reach-vb.hf.co · 02/12/2024you can just do things - ask AI to create your SQL queries and execute them right in your browser! 🔥 let your creativity guide you - powered by qwen 2.5 coder 32b ⚡ available on all 254,746 public datasets on the hub! go check it out today! 🤗 1282
vb @reach-vb.hf.co · 28/11/2024Fuck it! Structured Generation w/ SmolLM2 running in browser & WebGPU 🔥 Powered by MLC Web-LLM & XGrammar ⚡ Define a JSON schema, Input free text, get structured data right in your browser - profit!! 410613
vb @reach-vb.hf.co · 26/11/2024yo! nvidia finally released the weights for Hymba-1.5B - outperforms Qwen, and SmolLM2 w/ 6-12x less training trained ONLY on 1.5T tokens > massive reductions in KV cache size and improved throughput > combines Mamba and Attention in a hybrid parallel architecture with a 5:1 ratio and meta-tokens 1292
vb @reach-vb.hf.co · 25/11/2024Smol TTS keeps getting better! Introducing OuteTTS v0.2 - 500M parameters, multilingual with voice cloning! 🔥 > Multilingual - English, Chinese, Korean & Japanese > Cross platform inference w/ llama.cpp > Trained on 5 Billion audio tokens > Qwen 2.5 0.5B LLM backbone > Trained via HF GPU grants 5548
vb @reach-vb.hf.co · 25/11/2024SmolLM - run, pre-train, fine-tune, evaluate SoTA fully open source LM 🔥 Run with Transformers, MLX, Transformers.js, MLC Web-LLM, Ollama, Candle and more! Apache 2.0 licensed codebase - go explore now! 1362
vb @reach-vb.hf.co · 24/11/2024Massive week for Open Source AI/ ML Mistral Pixtral & Instruct Large - ~123B, 128K context, multilingual, json + function calling & open weights Allen AI Tülu 70B & 8B - competive with claude 3.5 haiku, beats all major open models like llama 3.1 70B, qwen 2.5 and nemotron 3559
vb @reach-vb.hf.co · 23/11/2024Apple released blazingly fast CoreML models AND an iOS app to run them on iPhone! ⚡ > S0 matches OpenAI's ViT-B/16 in zero-shot performance but is 4.8x faster and 2.8x smaller > S2 outperforms SigLIP's ViT-B/16 in zero-shot accuracy, being 2.3x faster, 2.1x smaller, and trained with 3x fewer data 2434
vb @reach-vb.hf.co · 23/11/2024Check out my new swanky handle! 🦋 - Drop your Hugging Face ID in the comments if you want the same! 4190
vb @reach-vb.hf.co · 22/11/2024LFG!! XGrammar: a lightning fast, flexible, and portable engine for structured generation! 🔥 > Accurate JSON/grammar generation > 3-10x speedup in latency > 14x faster JSON-schema generation and up to 80x CFG-guided generation GG MLC team is literally the best in the game and slept on! ⚡ 2524
vb @reach-vb.hf.co · 20/11/2024🚨 UPDATE: New Whisper based model competing with Nvidia on Open ASR Leaderboard! 🔥 CrisperWhisper aims to transcribe every spoken word exactly as it is, including fillers, pauses, stutters and false starts Whisper Large V3 fine-tune - beats it by roughly ~1 WER margin ⚡ hf.co/spaces/hf-au... 1183
vb @reach-vb.hf.co · 20/11/2024OH WOW! The Whale aka DeepSeek is BACK!! New model, with complete reasoning outputs and a gracious FREE TIER too! 🔥 Here's a quick snippet of it searching the web for the right documentation, creating the JS files plus the necessary HTML all whilst handling Auth too ⚡ 2210
vb @reach-vb.hf.co · 18/11/2024Great day for M/LLMs, just released Mistral & Pixtral Large - ~123B, 128K context, Multilingual, JSON + Function calling support & open weights! 🔥 Pixtral Large: huggingface.co/mistralai/Pi... Mistral Large: huggingface.co/mistralai/Mi... 0232
vb @reach-vb.hf.co · 18/11/2024New spaces of the week! 🔥 > Qwen 2.5 Coder Artifacts > Flux Kolors Character > X Potrait > Text Behind Image 🤯 > DimensionX > MagicQuill > JanusFlow 1.3B > Netflix Recommentation Check them out at hf.co/spaces 🏃 070
vb @reach-vb.hf.co · 15/11/2024🚨 Nexusflow released Athene v2 72B - competitive with GPT4o & Llama 3.1 405B Chat, Code and Math 🔥 > Arena Hard: GPT4o (84.9) vs Athene v2 (77.9) vs L3.1 405B (69.3) > Bigcode-Bench Hard: 30.8 vs 31.4 vs 26.4 > MATH: 76.6 vs 83 vs 73.8 Open science ftw! ⚡ 051
vb @reach-vb.hf.co · 04/11/2024Smol TTS models are here! OuteTTS-0.1-350M - Zero shot voice cloning, built on LLaMa architecture, CC-BY license! 🔥 > Pure language modeling approach to TTS > Zero-shot voice cloning > LLaMa architecture w/ Audio tokens (WavTokenizer) > BONUS: Works on-device w/ llama.cpp ⚡ 140
