Tagged: open-source-llms

12 articles

Latest

IBM's Granite 4.2 hits 57% on SWE-Bench — with an off switch for thinking

IBM's Granite 4.2 trains on 15T tokens and learns to code inside real sandboxes

StarCoder's 8K context window turns code LLMs into chat assistants

Writer's CTO on Why Open Source LLMs Beat the Hype Cycle

Open-source LLMs now beat GPT-4 on cost and privacy, led by Llama 2

Meta drops Llama 2: 70B open model rivals ChatGPT, now on Hugging Face

Open LLMs hit a wall in 2023: data scarcity, not model size, became the bottleneck

Mixtral 8x7B Beats Llama 2 70B and GPT-3.5 With an Apache 2.0 License

Transformers 4.49 quietly fixes the mess that made MoE models a deployment nightmare

Claude can now fine-tune open-source LLMs directly on cloud GPUs

Hugging Face TGI 1.4 brings OpenAI API drop-in replacement for open LLMs

Mixtral beats GPT-3.5 as an agent — Hugging Face releases smolagents