?? Qwen2.5-Coder-32B now available in OpenLLM! It is the first open-source coding model to match GPT-4o's capabilities! It leads the pack with SOTA performance and 128K context support! Serve and deploy it with OpenLLM: openllm serve qwen2.5-coder:32b openllm deploy qwen2.5-coder:32b Check out our demo video to see how it performs in generating the SVG code for a bento box ?? #OpenLLM #AI #MachineLearning #OpenSource #BentoML
BentoML的动态
最相关的动态
-
Customer Care Executive at Amazon (via Teleperformance) | Driving 95% Customer Satisfaction | Multichannel Support Specialist
Just finished "Getting Hands-On with GPT-4: Tips and Tricks“ by Denys Linkov! Check it out: https://lnkd.in/gvFypMU9 #generativeai #gpt4
-
OpenAI is prototyping a new search GPT. This looks similar to what Perplextity provides. You can join the waitlist using the following link. https://lnkd.in/e4mU7KnG
-
?????? Dive deep into the coding world with our latest blog post discussing the epic showdown between AI models DeepSeek R1, GPT-O1, and Claude 3.5 Sonnet! ?? Which one comes out on top when it comes to coding efficiency, creativity, and usability? ?? Get all the insights and make an informed choice for your next coding project! "But right now, if you want top-notch performance, good value, and full control over how you use the AI, DeepSeek R1 is hard to beat." ?? Read more here: [https://lnkd.in/eNV7J3wS] #AI #CodingBattle #TechBlog #DeepSeek #GPTO1 #Claude35Sonnet #DSR1 #Open-R1#DeepSeekR1
-
-
Just finished the course “Getting Hands-On with GPT-4: Tips and Tricks” by Denys Linkov! Check it out: https://lnkd.in/gZtidGcN #generativeai #gpt4.
-
Attended a sharing by Gabriel Chua on creating a daily AI paper summariser at last week's ML SG meetup. Here's my take on it: https://lnkd.in/gKWXPC2i Building on top of Gabriel's work, with addition features (keeping with the spirit of the project, all the output was clobbered together from #Claude, #GPT-4o, Co-pilot and #Gemini): - Auto-classification (currently based on HF taxonomy) - Curation (select the topics of interest to display in the readme) - Parsed Huggingface and Github links (not super accurate, sometimes it takes from other references in the paper) - Single page viewer with the results nicely formatted (The first attempt from Claude was very good out of the box, but it took 15+ tries and more specific prompts + some console inspection work to get all the condition styles and logic right) Not too bad for a half day of work
-
Just finished the course “Getting Hands-On with GPT-4: Tips and Tricks” by Denys Linkov! Check it out: https://lnkd.in/evxUFYbh #generativeai #gpt4.
-
Just dropped into the AI world and wow, DeepSeek is making some serious waves ?? Their new R1 reasoning model is very impressive - outperforming OpenAI's o1 model while being much more affordable. We're talking 90-95% cheaper API costs, which is mind-blowing for me. Breakdown of what makes R1 special: - Open-source (actual transparency) - Killer performance in math, coding, reasoning - Built with this wild multi-stage training approach - API costs just $0.14 per million input tokens (OpenAI was charging $7.50 ) What's cool is how they're not just releasing one model - they've got like 8 different versions exploring different AI training techniques. The R1-Zero version was even trained entirely through reinforcement learning without supervised fine tuning. That's some next level innovation. Feels like we're watching a real paradigm shift in AI development. #AI #DeepSeek #TechInnovation #MachineLearning #DeepSeekAI #LLM
-
-
Just finished the course “Getting Hands-On with GPT-4: Tips and Tricks” by Denys Linkov! Check it out: https://lnkd.in/diK-3iMi #generativeai #gpt4.
-
Just finished the course “Getting Hands-On with GPT-4: Tips and Tricks” by Denys Linkov! Check it out: https://lnkd.in/duhmw55x #generativeai #gpt4.
