AI & ML interests

Finetune. Train. Merge.

Recent Activity

ehristoforuΒ  updated a model about 2 months ago
fluently/FluentlyQwen3-Coder-4B-0909
ehristoforuΒ  updated a collection about 2 months ago
FluentlyQwen3
ehristoforuΒ  updated a collection about 2 months ago
FluentlyQwen3
View all activity

NymboΒ 
posted an update 9 days ago
view post
Post
1456
Two new tools added to the Nymbo/Tools MCP server, File_System and Shell_Exec. You can theoretically do basically anything with these two tools, and it should enable support for many Claude Skills.

GPT-5-Codex proves that for many cases, shell commands really are all you need, and Claude Skills seem to lean into this. The thing is, nothing about the design of Claude Skills actually restricts them to proprietary models!

# File_System

There's a new directory inside the repo called Filesystem, that's the agent's "root". It can perform the following actions : list, read, write, append, mkdir, move, copy, delete, info, help. It's able to keep this all within the scope of one tool call by making the Action field required and all other fields optional. Using a filesystem shouldn't require 15 different tools.

Files created in the public HF space live in the space's running container, and gets cleared when the space is restarted. When running the server locally, files are actually stored on disk.

# Shell_Exec

What good is a filesystem if you can't execute commands in that filesystem? This tool automatically detects if the server is running on Windows or Linux, and suggests using the appropriate shell (PowerShell/Bash). Both of these new tools require that the agent uses relative paths, rather than absolute paths. I could be convinced to back pedal on this.

# Closing Thoughts

The File_System and Shell_Exec tools aren't super polished yet, I'll continue to improve the agent's instructions and UX of using the new tools. Most of my testing was done with gpt-oss-20b and if it messes up, it gets the gist after one failed tool call. It should work perfectly fine for the GPU poor.
  • 1 reply
Β·
NymboΒ 
posted an update 14 days ago
view post
Post
1655
I've made some improvements to my custom Deep_Research tool in the Nymbo/Tools MCP server. I've added a second LLM process and it still takes less than 1 minute to complete!

The original version of my Deep_Research tool would basically dump up to 50 fetched webpages onto the Researcher model (Qwen3-235B), with only a little bit of context shown from each page.

# New "Filterer" Process

The new process includes another LLM call before the researcher process. The Filterer (also Qwen3-235B) gets the query summary and the original 50 pages with low context, and decides which pages are most relevant to the research topic. The Filterer then outputs the URLs to the relevant pages, which are then re-fetched (with more context) and sent to the Researcher.

# Researcher Context

The Researcher now gets only the relevant webpages, then begins writing the report. When testing with 50 initial results, the researcher would often end up with 10-20 results of relevant context.

It still takes less than a minute to accomplish everything, thanks entirely to Cerebras inference. It now takes about 35-45 seconds to complete once the tool is run.

It's also worth noting that both the Filterer and Researcher now are provided the current time/date before they see the content, reducing hallucinations caused by knowledge cutoffs.
NymboΒ 
posted an update 23 days ago
view post
Post
606
I have a few Sora-2 invites - 15509N
  • 1 reply
Β·
TanaybhΒ 
posted an update about 1 month ago
view post
Post
348
Hi everyone! I'm looking to expand my RL toolkit and would love to hear about what libraries and frameworks the community is using these days. The RL ecosystem has evolved so much, and I want to make sure I'm learning the most relevant and future-proof tools.

What are your current go-to RL libraries and frameworks in 2025? I'm particularly interested in -

What you use for different types of RL problems?

Any newer libraries that have impressed you recently

What you'd recommend for someone looking to learn their next RL framework?

#reinforcement-learning #rl #machine-learning #ai
TanaybhΒ 
posted an update about 1 month ago
view post
Post
2862
The Bias is YOU - LLMs Mirror Your Own Assumptions

AI doesn't just have bias - it reflects yours.

When you ask a question with positive framing, you get positive answers. Ask with negative framing, you get negative answers. The AI becomes a mirror of your own assumptions.

Your framing determines the answer - The same topic yields opposite responses based on how you ask

AIs amplify your sentiment - Negative questions often get even MORE negative responses

This affects everyone - From students doing research to professionals making decisions

Why This Matters

This isn't a technical glitch - it's fundamental to how these systems work. They're trained on human language, and humans frame things with bias. The AI learned to match that framing.

Think about the implications:
- Medical professionals seeking second opinions
- Students researching controversial topics
- Business leaders evaluating strategies
- Anyone using AI for important decisions

The Stochastic Mirror Effect

Let's call this the "Stochastic Mirror" - the AI doesn't give you objective truth, it gives you a probabilistic reflection of your own framing.

You're not querying a neutral database. You're looking into a mirror that reflects and amplifies your assumptions.
Β·
NymboΒ 
posted an update about 1 month ago
view post
Post
1045
There's now a custom Deep_Research tool in my Nymbo/Tools MCP server! TL;DR: The agent using the tools writes a summary of your requests and up to five DuckDuckGo searches (up to 50 results). Each of the webpages found in the searches are then fetched and given to our researcher (Qwen3-235B-A22B-Thinking-2507). The researcher sees the summary, searched queries, and fetched links, then writes a thorough research report. The agent using the tool provides the user with a summary of the report and a link to download research_report.txt. The researcher's instructions are similar to some leaked Perplexity sys prompts.

# Deep_Research Tool

It accomplishes everything in under a minute so it doesn't hit MCP's 60 second timeout, mostly thanks to Cerebras. The only thing required to make this work is a HF_READ_TOKEN for inference.

The Deep_Research tool could certainly be improved. It still needs some sort of mechanism for sorting URLs based on importance (I've got some ideas but I don't want it to be the responsibility of the agent using the tool). I'll probably add a second researcher to filter out the bad sources before inferencing the big researcher. I'm hellbent on keeping this all within the scope of one tool call.

# More Fetch/Web Search Improvements

The Search_DuckDuckGo tool has been further enhanced. It now allows the agent to browse through all pages of results. The results also now include published date (if detected). It also now supports every DDG search types! Default DDG search is called text, but it can also now search by news, images, videos, and books.

The Fetch_Webpage tool now specifies how much of the page has been truncated, and cursor index, allowing it to pickup where it left off without re-consuming tokens. The model can now also choose to strip CSS selectors to remove excess noise, and there's a new URL Scraper mode that only returns URLs found on the full page.

More to come soon ~
ehristoforuΒ 
posted an update about 1 month ago
view post
Post
2129
πŸš€Hello from the Project Fluently team!

✨ We are happy to share with you our new universal LLM models based on Qwen3 1.7B and 4B β€” powerful, multilingual and ready to solve a wide range of problems!

πŸ› οΈ We have conducted additional training and carefully merged them to achieve even better results and maximize the potential of the models.

πŸ†“ And most importantly β€” the models are completely open and free under the Apache-2.0 license!

πŸ”— Links to repositories:
- FluentlyQwen3-4B: fluently/FluentlyQwen3-4B
- FluentlyQwen3-1.7B: fluently/FluentlyQwen3-1.7B

😍 We will be very glad to hear your feedback and impressions! Your opinion is very important to us!
AbhaykoulΒ 
posted an update about 2 months ago
view post
Post
2893
πŸš€ Ever dreamed of training your own Large Language Model from scratch? What if I told you it doesn't require a supercomputer or PhD in ML? 🀯

Introducing LLM Trainer - the educational framework that makes LLM training accessible to EVERYONE! Whether you're on a CPU-only laptop or scaling to distributed GPUs, we've got you covered. πŸ’»βž‘οΈπŸ–₯️

Why LLM Trainer? Because existing tools are either too simplistic (hiding the magic) or too complex (requiring expert knowledge). We bridge the gap with:

πŸŽ“ Educational transparency - every component built from scratch with clear code
πŸ’» CPU-first approach - start training immediately, no GPU needed
πŸ”§ Full customization - modify anything you want
πŸ“ˆ Seamless scaling - from laptop to cluster without code changes
🀝 HuggingFace integration - works with existing models & tokenizers

Key highlights:
βœ… Built-in tokenizers (BPE, WordPiece, HF wrappers)
βœ… Complete Transformer implementation from scratch
βœ… Optimized for CPU training
βœ… Advanced features: mixed precision, gradient checkpointing, multiple generation strategies
βœ… Comprehensive monitoring & metrics

Perfect for:
- Students learning transformers
- Researchers prototyping new ideas
- Developers building domain-specific models

Ready to train your first LLM? It's easier than you think!

πŸ”— Check it out: https://github.com/HelpingAI/llm-trainer
πŸ“š Docs: Getting Started Guide
πŸ’¬ Join the community: GitHub Discussions

#AI #MachineLearning #LLM #DeepLearning #OpenSource #Python #HuggingFace #NLP

Special thanks to HuggingFace and PyTorch teams for the amazing ecosystem! πŸ™
  • 1 reply
Β·