Scale AI is proud to announce Defense Llama : the LLM purpose-built for American national security. This is the product of collaboration between @Meta
, Scale, and defense experts, and is available now for integration into US defense systems. Read more below
LLMS
-
Defense Llama: Meta and Scale Launch Security-Focused LLM
By
–
-
Comprehensive Data Scientist Handbook: Essential Learning Resources
By
–
GitHub – andresvourakis/data-scientist-handbook: This is a repo with links to everything you'd ever want to learn about data science https://
bit.ly/3N6nZvo
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
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 – -
Six LLM Inference Modes Evolution and Future Trends
By
–
The 6 "modes" of LLM inference, over time: – 2021: "large" models
– 2023: "turbo"/"mini" models
– Apr 2024: Batch API
– Sep 2024: Reasoning models
– Oct 2024: Realtime API
– Nov 2024: Speculative Decoding APIs seems pretty comprehensive. what else will be coming? -
Haiku vs Haiku 3.5: optimal fallback strategy for AI
By
–
I'm wondering if it's a good fallback – use Haiku, and if the output isn't good, use Haiku 3.5