Qwen released QvQ 72B OpenAI o1 like reasoning model on Hugging Face with Vision capabilities - beating GPT4o, Claude Sonnet 3.5 🔥
December 24, 2024 at 5:25 PM
Qwen released QvQ 72B OpenAI o1 like reasoning model on Hugging Face with Vision capabilities - beating GPT4o, Claude Sonnet 3.5 🔥
BOOOOM! 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 ⚡
Comparable performance to 405B with 6x LESSER parameters ⚡
December 6, 2024 at 6:19 PM
BOOOOM! 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 ⚡
Comparable performance to 405B with 6x LESSER parameters ⚡
Introducing 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
w/ fully customisable speech and voice personas!
Try it out directly below or use the model weights as you want!
🇮🇳/acc
December 3, 2024 at 9:31 PM
Introducing 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
w/ fully customisable speech and voice personas!
Try it out directly below or use the model weights as you want!
🇮🇳/acc
you 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! 🤗
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! 🤗
December 2, 2024 at 2:41 PM
you 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! 🤗
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! 🤗
Fuck 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!!
Powered by MLC Web-LLM & XGrammar ⚡
Define a JSON schema, Input free text, get structured data right in your browser - profit!!
November 28, 2024 at 10:24 PM
Fuck 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!!
Powered by MLC Web-LLM & XGrammar ⚡
Define a JSON schema, Input free text, get structured data right in your browser - profit!!
yo! 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
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
November 26, 2024 at 7:34 PM
yo! 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
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
Smol 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
> 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
November 25, 2024 at 9:32 PM
Smol 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
> 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
SmolLM - 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!
Run with Transformers, MLX, Transformers.js, MLC Web-LLM, Ollama, Candle and more!
Apache 2.0 licensed codebase - go explore now!
November 25, 2024 at 1:17 PM
SmolLM - 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!
Run with Transformers, MLX, Transformers.js, MLC Web-LLM, Ollama, Candle and more!
Apache 2.0 licensed codebase - go explore now!
Massive 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
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
November 24, 2024 at 8:12 PM
Massive 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
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
Apple 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
> 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
November 23, 2024 at 4:22 PM
Apple 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
> 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
Check out my new swanky handle! 🦋 - Drop your Hugging Face ID in the comments if you want the same!
November 23, 2024 at 3:01 PM
Check out my new swanky handle! 🦋 - Drop your Hugging Face ID in the comments if you want the same!
LFG!! 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! ⚡
> 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! ⚡
November 22, 2024 at 9:21 PM
LFG!! 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! ⚡
> 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! ⚡
🚨 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...
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...
November 20, 2024 at 10:45 PM
🚨 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...
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...
OH 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 ⚡
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 ⚡
November 20, 2024 at 11:42 AM
OH 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 ⚡
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 ⚡
Great 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...
Pixtral Large: huggingface.co/mistralai/Pi...
Mistral Large: huggingface.co/mistralai/Mi...
November 18, 2024 at 5:40 PM
Great 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...
Pixtral Large: huggingface.co/mistralai/Pi...
Mistral Large: huggingface.co/mistralai/Mi...
New 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 🏃
> 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 🏃
November 18, 2024 at 11:23 AM
New 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 🏃
> 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 🏃
What a brilliant week in Open Source!
November 17, 2024 at 9:09 PM
What a brilliant week in Open Source!
🚨 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! ⚡
> 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! ⚡
November 15, 2024 at 9:41 AM
🚨 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! ⚡
> 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! ⚡
Smol 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 ⚡
> Pure language modeling approach to TTS
> Zero-shot voice cloning
> LLaMa architecture w/ Audio tokens (WavTokenizer)
> BONUS: Works on-device w/ llama.cpp ⚡
November 4, 2024 at 5:19 PM
Smol 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 ⚡
> Pure language modeling approach to TTS
> Zero-shot voice cloning
> LLaMa architecture w/ Audio tokens (WavTokenizer)
> BONUS: Works on-device w/ llama.cpp ⚡
What a fantastic and 🐌 paced weekend! ♥️
May 14, 2023 at 11:02 PM
What a fantastic and 🐌 paced weekend! ♥️