Image created with Gemini. Image prompt: A 1983 Gothic rock-opera music video still in a vast deserted Victorian academy hall, where a carved stone llama head high on an arched window has a glowing white eye being eclipsed by a black disc with a blazing gold corona, an anonymous woman in a flowing luminous white dress with wind-teased hair standing on a sweeping marble staircase below as slow-motion doves explode through heavy fog and blinding backlight, with the bold chrome serif title LLAMA glowing across the upper frame, 35mm film grain, soft diffusion bloom, blue-black shadow and bleached white light, 16:9.
Most agentic retrieval demos assume clean, well-structured documents. Enterprise reality is often different, consisting of messy PDFs where critical information is buried across tables, figures, and complex layouts. That’s why we teamed up with @lancedb to explore how LiteParse”
https://x.com/llama_index/status/2074170470119752084
@OpenAI released GPT 5.6 today and we ran a day 0 benchmark in ParseBench to test improvements in document understanding. The new family of models continues to excel at reading text and tables, but continues to struggle with charts and layout. What’s most interesting is that”
https://x.com/llama_index/status/2075351095258296378
llama.cpp recently added DFlash support to its speculative decoding arsenal. Along with MTP, Eagle3 and various ngram-based techniques, the local model performance takes another step up. Special thanks to NVIDIA team and Ruixiang Wang specifically for leading this effort!”
https://x.com/ggerganov/status/2074869767689662643
We made llama.cpp GGUFs for DeepSeek-V4-Flash! Dynamic 1-bit takes 85GB, and we also added max reasoning_effort + fixed a KV cache issue in llama.cpp. Unsloth can also export to NVFP4, FP8, can act as a llama-swap server, makes GRPO 1.3x faster & MoEs 3x faster + 30% less VRAM!”
https://x.com/danielhanchen/status/2074510444778463331
computed the similarity (CKA) on the J-lens geometry of every layer inside and across 38 open models. the patterns are weirdly universal: same depth layout, same organization at the same relative depth, even between unrelated families like llama and olmo
https://x.com/eliebakouch/status/2074532904009421260
How do you trace one number in a 200 page ESG report back to the exact page it came from? We dug into that with the @llama_index team behind LiteParse. We tested five ways to retrieve evidence across six sustainability reports and 50 labeled questions. Fusing pages, chunks,”
https://x.com/lancedb/status/2074153945631457663
Leave a Reply