QwQ-32B-Preview: An Experimental AI Model The Qwen Team’s experimental research model, QwQ-32B-Preview, showcases promising analytical abilities but with several limitations: Language Mixing and Code-Switching: May switch between languages unexpectedly. Recursive Reasoning Loops:…
Month: November 2024
OpenWebUI + Ollama
Models Models keep information about existing models, allow us to modify them by adding functions, tools, system prompts, etc., or even create custom models on existing LLMs like Llama 3.x. It’s worth…
DeepSeek-R1-Lite-Preview Challenges US AI Models
DeepSeek-R1-Lite-Preview is Now Live DeepSeek-R1-Lite-Preview is a new model from China, which is a direct competitor to the best US models like OpenAI’s o1 and Claude 3.5 Sonnet, beating them in some…
Qwen2.5: A High-Performance Coder Model
The new coder model – Qwen2.5 32B coder (also models of various sizes: 0.5B / 1.5B / 3B / 7B / 14B, and quantized models in GPTQ, AWQ, and GGUF formats). Key…
Adobe Firefly, Gemini robotics research + technical reading bonuses
Adobe’s Firefly Video Model Adobe has announced the beta launch of its Firefly Video Model, a web module that generates videos from text prompts or image inputs. Key features include: * Quickly…
X source of AI/ML news
Here, we have a wealth of information about what transpired last week in the highly technical world of AI. This week, you can delve into topics such as: GPT-4o System Card, Can…
Red Panda and Other AI-Related Developments
Red Panda The mysterious Red Panda text-to-image model has finally been revealed by its creators. The company behind this innovative technology is Recraft AI, which has also given the model the name…