johhns4

↗ HN profile [ 69.4 ms ] full profile
Karma
87
Created
September 15, 2023 (2y ago)
Submissions
0
  1. To deploy fine-tuned LLMs there are these options yes? 1. HuggingFace 2. Runpod 3. Bedrock 4. FireworksAI 5. TogetherAI 6. Replicate 7. Modal Any other that I'm missing? What do you prefer and for what use, i.e.…

  2. I'm interested to see if people are fine-tuning the larger LLMs just for kicks or if there are situation where it makes sense (not including high-stakes decision making like medical/legal) and it is computationally…

  3. Been deploying a few models to a Nvidia Tesla T4 · 1x GPU · 16 GB via Hugging Face but keep getting back 500 errors every 2 minutes. Hasn't happened before today, just wondering if this is normal? This increases…

  4. Any tips on how to deploy and use a fine-tuned model on Huggingface in a cost effective way? Right now looking into use Gradio with HuggingFace spaces and using the API endpoint from there. Inference endpoints and…

  5. Do you use any of these and if so which one is the best to use? I know there is some skepticism around using these wrappers in the first place.

  6. I want to be able to find relevant content that isn't a bunch of click bait articles I get served each day. I want the ability to search new content but they make it super hard to scrape their archives page. Anyone that…