You can now fine-tune LFM2 with @axolotl_ai
! Thanks to @winglian for this! You can use his notebook to smoothly SFT an LFM2 model. I tried it and created my own LFM2-1.2B-Pirate based on this code.
LLMS
-
Fine-tuning LFM2 Models with Axolotl Framework
By
–
-
xAI Launches 3D AI Avatars with Voice Conversation on Grok
By
–
AI NEWS: xAI just launched AI companions on Grok — 3D avatars that can hold voice conversations and develop relationships with users Plus, more news from Meta, Cognition, Google, AWS, and Anthropic. Here's everything you need to know:
-
Future of 3D AI characters in Copilot, Google, Claude
By
–
Not in the same way but we will likely see many 3d AI characters in other products too. MS Copilot is soon to get some Google already has Character AI technically as well Claude will get it as an MCP or something….
-
AI Benchmarking Limitations: Beyond GPQA and MMLU Metrics
By
–
Another sign that the benchmarking of AIs has grown too narrow – needle-in-a-haystack, instruction following, hallucination rates, etc. are all really important, and just measuring things correlated with GPQA/MMLU/etc may blind users to other models strengths and weaknesses.
-
AI Model Limitations: Hallucinations and Narrative Comprehension Issues
By
–
There are lots of other quirks – it loses track of stories or narratives in complicated ways, while also being very good at finding details in large documents. I think its initial impressiveness might blind to some issues with hallucinations and other concerns. Don't know yet.
-
Kimi Model Hallucinations and Testing Limitations Exposed
By
–
Kimi is a really weird model, and it needs a lot more testing to figure out For example, I gave it an altered version of Great Gatsby and it found the two alterations (as does Claude) but then made up a ton of hallucinated nonsense that sounded plausible but was just plain wrong
-
User notes grok blocked from replying to Hitler threads
By
–
I don’t think they let grok reply on threads that mention Hitler anymore. (I don’t have it blocked or anything.)
-
Discussion of AI reasoning traces and model visibility
By
–
Also most people had never seen a real, full reasoning trace before, and the novelty was hyped up by the fact o1 didn’t show them E.g. this got likes at the time despite it being a (relatively) obscure model:
-
Grok 4 Heavy: Multi-Agent Multimodal AI Intelligence
By
–
Grok 4 Heavy is AI with multiple minds. Multi-agent. Multi-modal. Next-gen intelligence. Stay updated on every new AI release via http://
futurepedia.io Follow @futurepedia_io for more AI breakthroughs -
AI Roadmap: Coding Model, Multimodal Agent, Video Generation
By
–
Roadmap: Here’s what’s next: August: Coding-optimized model September: Multimodal agent October: AI video generation The pipeline is heating up fast.