introduc ing Hunyuan-Large, which is currently the largest open-source Transformer-based mixture of experts model, with a total of 389 billion parameters and 52 billion activation parameters, capable of handling up to 256K tokens.
OPEN SOURCE
-
Tencent Releases Hunyuan-Large Open-Source MoE Model
By
–
Tencent released Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters https://
llm.hunyuan.tencent.com https://
github.com/Tencent/Hunyua
n-Large
… https://
huggingface.co/tencent/Hunyua
n-Large/tree/main
… https://
huggingface.co/spaces/tencent
/Hunyuan-Large
… https://
arxiv.org/abs/2411.02265 -
Create AI Chatbot Apps Instantly with SambaNovaAI and Gradio
By
–
Developers can now make ai chatbot apps with one button click
— AK (@_akhaliq) 5 novembre 2024
using @SambaNovaAI cloud and @Gradio integration with @huggingface Spaces
example with @AIatMeta llama 3.1 8B instruct pic.twitter.com/hyuxnOpd3yDevelopers can now make ai chatbot apps with one button click using @SambaNovaAI cloud and @Gradio integration with @huggingface Spaces example with @AIatMeta llama 3.1 8B instruct
-
ML Engineering Open Book: Comprehensive Machine Learning Resource Guide
By
–
GitHub – stas00/ml-engineering: Machine Learning Engineering Open Book https://
bit.ly/3SP0qtv
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
Moshi Open Source Realtime Voice AI Model Paper Club
By
–
Next Paper Club: @kyutai_labs Moshi! Realtime voice is all the rage, lets dive into the best open model so far with @vibhuuuus and @AmgadGamalHasan! https://
lu.ma/p0riwfbs -
Tencent Releases Hunyuan Large Language Model
By
–
https://
huggingface.co/tencent/Tencen
t-Hunyuan-Large
… -
Tencent Hunyuan Large 389B: New LLM Outperforms Llama DeepSeek
By
–
We're sooo back! – Tencent Hunyuan Large – 389B (Total) X 52B (Active) – beats Llama 3.1 405B, Mistral 8x22B, DeepSeek V2! Multilingual, 128K context, Utilizes GQA + CLA for KV Cache compression + Higher throughput Released Pre-train, Instruct & FP8 checkpoints on the Hugging
-
Tencent releases Hunyuan-Large: open MoE model beats LLaMA 3.1-405B
By
–
> Hunyuan-Large just released by @TencentGlobal : Largest ever open MoE LLM, only 52B active parameters but beats LLaMA 3.1-405B on most academic benchmarks! Key insights: Mixture of Experts (MoE) architecture: 389 B parameters in total, but only 52B are activated for any
-
Tencent Hunyuan-Large: New SOTA Open-Source LLM Model
By
–
Impressive new SOTA open-source LLM in the new update of Hunyuan-Large by Tencent Model: https://
huggingface.co/tencent/Tencen
t-Hunyuan-Large
…
Paper and discussion: https://
huggingface.co/papers/2411.02
265
… A couple of strong points:
– strong performances in math (probably from the very large Chinese pretraining datasets –