Nevin1901

Hi, I'm a developer in college who has built a side project which generates around $2k ARR in revenue. I'm looking to build a second product which helps users monitor their applications in production, and I wanted to…

I’ve found ggerganovs work on llama.cpp to be amazing, and I’ve loved playing around with it. However, has anyone used it in production? I’m sure there are some really cool use cases, but I haven’t seen any yet.

Hi, During the recent explosion of LLM's, I've been playing around with Llama-2 7b on my Mac, and have wanted to fine tune the model. I've created a service which lets you upload a json/jsonl file, and it'll…

Hi, I’ve been working on a lightweight log collector which will run on any vps, is extremely easy to set up, and works with your current libraries. Most log platforms either - are expensive (datadog, newrelic) - require…

I’ve been looking to instrument opentelemetry into my app, and I was wondering what your guys experiences was with it. Would you use it for small/medium sized projects? What was the most annoying part about setting it…

Hey guys, I’m developing a service (FTN) which lets you host fine tuned variants of llama 2/mistral 7b with the same api access and price as gpt-3.5. I currently have a working prototype, and I’m looking for people to…

Working on a service which uses GPT-3.5 and was wondering how I would go about tracking the usefulness of it. Wondering what you guys have done, or if you guys even track your NLP models at all.

Looking to solve some problems related to logging in my free time, curious what problems you guys have.

I've been looking at transitioning to a cloud dev environment such as github codespaces or just renting out a vps to work on. Those of you who use cloud dev environments at your company/home, what are the most annoying…

Those of you who have fine tuned NLP (GPT-X/Llama) or diffusion models, what was the most difficult or annoying part about the process? I'm trying to help solve problems in this field, so I'm curious about your…

Those of you who use NLP models in production, how do you monitor them? I'm looking at deploying my own gpt-style nlp model soon, and I couldn't find many monitoring tools like one would find with http libraries, etc.…

As someone whose launched a business using generative nlp models, I found my fair share of problems with them. For those of you who used models such as gpt-2/3.5, gpt-neox, etc for a service or in prod, what problems do…

Hey guys, I'm building erlog to try and solve problems with logging. While trying to add logs to my application, I couldn't find any lightweight log platform which was easy to set up without adding tons of dependencies…

I've been thinking of adding logs/metrics to a side project I've been working on. I see tons of APM solutions competing in this space, so I was wondering: what common problems do you guys have with APM solutions…

I'm a software developer whose been creating developer productivity tools over the past few years (logging platforms and documentation tools), and I was thinking of going into a different niche. I've been interested in…

I was trying to add logging to my application when I realized how time consuming and expensive it was. What are some of your guys' problems with logging?

I've been looking into the field of continuous learning recently, and was interested in the various ways people are solving problems. For example, continually fine tuning an NLP model on fresh data to adapt to new…