12 2 178

Samuel L Meyers PRO

MrOvkill

AI & ML interests

Dialogue Generation, Text Generation, etc...

Recent Activity

posted an update 1 day ago

Hello! I was just playing around with Python's MIDI library and Colab's code generation, accidentally cooked up a quick n' dirty audio synthesis template. Have fun! https://colab.research.google.com/drive/1d-AF6jygCwmoJvAa9nnEMe5ROidnMJNY?usp=sharing -<3

liked a Space 3 days ago

tencent/Hunyuan3D-2

reacted to luigi12345's post with 🔥 25 days ago

🚀 OpenAI o3-mini Just Dropped – Here’s What You Need to Know! OpenAI just launched o3-mini, a faster, smarter upgrade over o1-mini. It’s better at math, coding, and logic, making it more reliable for structured tasks. Now available in ChatGPT & API, with function calling, structured outputs, and system messages. 🔥 Why does this matter? ✅ Stronger in logic, coding, and structured reasoning ✅ Function calling now works reliably for API responses ✅ More stable & efficient for production tasks ✅ Faster responses with better accuracy ⚠️ Who should use it? ✔️ Great for coding, API calls, and structured Q&A ❌ Not meant for long conversations or complex reasoning (GPT-4 is better) 💡 Free users: Try it under “Reason” mode in ChatGPT 💡 Plus/Team users: Daily message limit tripled to 150/day!

View all activity

Organizations

MrOvkill's activity

posted an update 1 day ago

Post

1647

Hello!

I was just playing around with Python's MIDI library and Colab's code generation, accidentally cooked up a quick n' dirty audio synthesis template.
Have fun!

https://colab.research.google.com/drive/1d-AF6jygCwmoJvAa9nnEMe5ROidnMJNY?usp=sharing

-<3

reacted to luigi12345's post with 🔥 25 days ago

Post

1930

🚀 OpenAI o3-mini Just Dropped – Here’s What You Need to Know!

OpenAI just launched o3-mini, a faster, smarter upgrade over o1-mini. It’s better at math, coding, and logic, making it more reliable for structured tasks. Now available in ChatGPT & API, with function calling, structured outputs, and system messages.

🔥 Why does this matter?
✅ Stronger in logic, coding, and structured reasoning
✅ Function calling now works reliably for API responses
✅ More stable & efficient for production tasks
✅ Faster responses with better accuracy

⚠️ Who should use it?
✔️ Great for coding, API calls, and structured Q&A
❌ Not meant for long conversations or complex reasoning (GPT-4 is better)

💡 Free users: Try it under “Reason” mode in ChatGPT
💡 Plus/Team users: Daily message limit tripled to 150/day!

2 replies

reacted to MoritzLaurer's post with ❤️ about 2 months ago

Post

1723

The TRL v0.13 release is 🔥! My highlight are the new process reward trainer to train models similar to o1 and tool call support:

🧠 Process reward trainer: Enables training of Process-supervised Reward Models (PRMs), which reward the quality of intermediate steps, promoting structured reasoning. Perfect for tasks like stepwise reasoning.

🔀 Model merging: A new callback leverages mergekit to merge models during training, improving performance by blending reference and policy models - optionally pushing merged models to the Hugging Face Hub.

🛠️ Tool call support: TRL preprocessing now supports tool integration, laying the groundwork for agent fine-tuning with examples like dynamic temperature fetching in prompts.

⚖️ Mixture of judges: The new AllTrueJudge combines decisions from multiple binary judges for more nuanced evaluation.

Read the release notes and other resources here 👇
Release: https://github.com/huggingface/trl/releases/tag/v0.13.0
Mergekit: https://github.com/arcee-ai/mergekit
Mixture of judges paper: The Perfect Blend: Redefining RLHF with Mixture of Judges (2409.20370)

replied to mlabonne's post 8 months ago

I am personally of the opinion that it is likely that the larger models have intentionally, especially technically proficient models like Claude or 4o have been intentionally 'broken' from storytelling, as they have become much more helpful and critical in their role as co-engineers. I have personally conscripted Claude for some testing, and it's given me about 1/3 of an AI model that I basically only had to design and fix instead of consider every detail without knowing the interactions. This lack of hallucination and skill for deterministic writing likely detracts from any creative elements present. Picture a highly autistic person with a savant for programming and logic. This person would be a genius at code, but likely poor at creative writing unless instructed. The same would be true of a synthetic mind given only factual and grounded data for much of it's training, as Anthropic seems to be doing for ( obvious ) safety reasons.

reacted to mlabonne's post with 🤗 8 months ago

Post

19577

Large models are surprisingly bad storytellers.

I asked 8 LLMs to "Tell me a bedtime story about bears and waffles."

Claude 3.5 Sonnet and GPT-4o gave me the worst stories: no conflict, no moral, zero creativity.

In contrast, smaller models were quite creative and wrote stories involving talking waffle trees and bears ostracized for their love of waffles.

Here you can see a comparison between Claude 3.5 Sonnet and NeuralDaredevil-8B-abliterated. They both start with a family of bears but quickly diverge in terms of personality, conflict, etc.

I mapped it to the hero's journey to have some kind of framework. Prompt engineering can definitely help here, but it's still disappointing that the larger models don't create better stories right off the bat.

Do you know why smaller models outperform the frontier models here?

44 replies

posted an update 8 months ago

Post

1190

Hello!

I've been in the lab synthesizing captions, with my trusty sidekick Blip, and along the way I had an interesting idea. I thought of designing an incredibly simple model that accepts simple instruction pairs, adjective noun pairs specifically, and outputs 2d vertices.

The current implementation has been implemented by myself then ran over with Claude, not because I am incompetent, but because I recognize tools written by experts may have more technique than my newbie self.

As with all projects, this will be updated with proportion to the feedback received, if someone's using it and wants to keep using it, i'm happy to keep working on anything. Thanks, all! 🤗

-<3

https://colab.research.google.com/gist/SMeyersMrOvkill/8d4686db803f6c5f43fafc1c94b1c8c6/polypathdelement.ipynb

posted an update 8 months ago

Post

2122

Hello!

I've been in the lab, I think one or two of you saw my furtive attempts to create a dolphinized 2b Gemma, which is still waiting for more funding. I get paid in a week.

Once that funding ran out, I dropped my last pinch of API credits to work on this:

DigitalClockwork/spatial_instruct_v1

It is an instruct database for spatial interactions with color tokens, i'm planning to tune a TBD model. Been experimenting with Gemma, but i'm welcome to ( smaller! ) model suggestions. If you think your favorite 0.5/0.75/1/2b can handle numbers, distances, or colors especially well, most especially community-enhanced models... I'm listening to the comments, intently!
Have a great day, and enjoy! This was one fun! 🤗

-<3

reacted to not-lain's post with ❤️ 8 months ago

Post

2684

I have finished writing a blogpost about building an image-based retrieval system, This is one of the first-ever approaches to building such a pipeline using only open-source models/libraries 🤗

You can checkout the blogpost in https://huggingface.co/blog/not-lain/image-retriever and the associated space at not-lain/image-retriever .

✨ If you want to request another blog post consider letting me know down below or you can reach out to me through any of my social media

📖 Happy reading !

replied to their post 8 months ago

You aren't the one flaming. The others though...

Anyway yes, it's being improved now. Been in the lab since that post. The CO-lab...

replied to their post 8 months ago

As did 'takera' author your thoughts, apparently. You're like snowflakes, each of you.

replied to their post 8 months ago

I was testing some plugins, it didn't occur to me the default installations of some of the most commonly used plugins would cause issues. I apologize for the horrifying inconvenience that you may have suffered at the hands of my blog. It does, after all, have such large and pointy teeth. Oh. Wait...

posted an update 8 months ago

Post

845

Hello!

I've been playing with Claude, and we decided to tackle a real thorn in my side.

"The Truthiness Model" - Analyze arbitrary input text for "truthiness", or likelihood of containing true information according to seed text.

P.S. Yes, v1 was broken. I saw the loss rate going down and go excited. Anyway, it just needed some data and a rollback, me and Claude got WAY too carried away trying to tack on features.

Anyway, fixed now, and working! :D

http://samuelmeyerscode.serveblog.net/?p=49

8 replies

replied to their post 8 months ago

I'm so glad the data proved helpful! Keep me updated, i'm already a follower, looking forward to seeing more! As always, as if you need anything.

replied to their post 8 months ago

You got through to me again:
https://huggingface.co/posts/MrOvkill/139983484226395

posted an update 8 months ago

Post

645

Hello!

https://www.youtube.com/watch?v=6NyDkpfNfUs

I had some feedback recently, that perhaps it would be beneficial to expand upon the fallacy dataset. I took this deeply to heart, and exploded it 10x.

MrOvkill/fallacies-fallacy-base

Produced synthetically with *ALL* the Gemini models on Vertex AI.

*phew* This was a rush. I can promise over 8 it might have been like 16 of straight prompt/copy/paste/fix/re-splice/fix/prompt again/chug caffeine/repeat, but we got there! Thanks for egging me on, all! I appreciate being driven to work! So much better than boredom! 🤗

Have fun!

replied to their post 8 months ago

Was seriously considering a branch-generation into n samples/workarounds for each row of that dataset, if I can once automate a step w/ Gemini i'm pretty confident. Want it? If so, what should n be?

replied to their post 8 months ago

I may have heard your first idea loudest and first:
Post
Dataset

posted an update 8 months ago

Post

1606

Hello!

I've been in the lab playing with various data formats today, and jammed out with some plain text to produce a nice list of fallacies and their solutions from Wikipedia's List of fallacies as JSONL for data processing.

Had some bumps along the way, but me and Gemini 1.5 Pro got there in the end. I must really learn to work with Gemini 1.5 Flash more effectively in future.

MrOvkill/fallacies-list-wikipedia

Enjoy!

-<3

posted an update 8 months ago

Post

1101

Hello!

Fixed Moondream 2 Multi-Interrogation, ( Use ZeroGPU correctly, Sam. *doink* )
Located here:

MrOvkill/moondream-2-multi-interrogation

Also, uploaded pdox-reversed to include some new fields, my bad for not putting the Paradox name in from the start. All good now.

MrOvkill/pdox-reversed

replied to their post 8 months ago

I'm so glad you like it! If you need any other datasets, i'm happy to help. 🤗