thank you, I'll try these first. really appreciate the help!
Melvin Vivas PRO
melvindave
AI & ML interests
Small Language Models, Vision, TTS, STT, Image Gen
Recent Activity
liked
a Space
about 6 hours ago
ekwek/Soprano-TTS
updated
a collection
about 6 hours ago
Text to Speech
liked
a model
about 6 hours ago
ekwek/Soprano-80M
Organizations
replied to
their
post
1 day ago
replied to
their
post
1 day ago
I saw this. Is this good enough? https://huggingface.co/mradermacher/Distil-PII-Llama-3.2-1B-Instruct-GGUF
replied to
their
post
1 day ago
thank you so much for the detailed reply. i was checking the deployment guide for https://huggingface.co/distil-labs/Distil-PII-Llama-3.2-1B-Instruct but it's not available in their website anymore
posted
an
update
1 day ago
Post
119
I am looking for a model which is good at redaction of sensitive info
Preferably, a small model which I can run locally. If there isn't a small one, I'd be interested to explore even larger ones. I just need it for a project I am building.
Any ideas?
Preferably, a small model which I can run locally. If there isn't a small one, I'd be interested to explore even larger ones. I just need it for a project I am building.
Any ideas?
-
- 5 replies
reacted to
mahimairaja's
post with 🚀
1 day ago
Post
4644
Happy New Years 2026!
For next 365 days I will be commit to work on:
- Document AI and OCR Automations
- Voice Agents
- Long Running Tasks - Durable Agents
For next 365 days I will be commit to work on:
- Document AI and OCR Automations
- Voice Agents
- Long Running Tasks - Durable Agents
- 1 reply
reacted to
prithivMLmods's
post with 🤗
16 days ago
Post
2001
Demo for Molmo2 on Hugging Face is live now, including Single/Multi-Image VQA, Visual Pointing/Grounding, Video VQA, and Video Point Tracking. Find the demo and related collections below. 🔥🤗
● Molmo2 HF Demo🖥️: prithivMLmods/Molmo2-HF-Demo
● Model Collection: https://huggingface.co/collections/allenai/molmo2
● Related Multimodal Space Collection: https://huggingface.co/collections/prithivMLmods/multimodal-implementations
To know more about it, visit the app page or the respective model page!
● Molmo2 HF Demo🖥️: prithivMLmods/Molmo2-HF-Demo
● Model Collection: https://huggingface.co/collections/allenai/molmo2
● Related Multimodal Space Collection: https://huggingface.co/collections/prithivMLmods/multimodal-implementations
To know more about it, visit the app page or the respective model page!
reacted to
danielhanchen's
post with 🔥
20 days ago
Post
5310
NVIDIA releases Nemotron 3 Nano, a new 30B hybrid reasoning model! 🔥
Has 1M context window & best in class performance for SWE-Bench, reasoning & chat. Run the MoE model locally with 24GB RAM.
GGUF: unsloth/Nemotron-3-Nano-30B-A3B-GGUF
💚 Step-by-step Guide: https://docs.unsloth.ai/models/nemotron-3
Has 1M context window & best in class performance for SWE-Bench, reasoning & chat. Run the MoE model locally with 24GB RAM.
GGUF: unsloth/Nemotron-3-Nano-30B-A3B-GGUF
💚 Step-by-step Guide: https://docs.unsloth.ai/models/nemotron-3
- 1 reply
i made mine. too embarassing to post 😂
reacted to
Kseniase's
post with 👍
21 days ago
Post
5899
6 Comprehensive Resources on AI Coding
AI coding is moving fast, and it’s getting harder to tell what actually works. Agents, workflows, context management and many other aspects are reshaping how software gets built.
We’ve collected a set of resources to help you understand how AI coding is evolving today and what building strategies work best:
1. AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities (2508.11126)
Provides a clear taxonomy, compares agent architectures, and exposes practical gaps in tools, benchmarks, and reliability that AI coding agents now struggle with
2. Does AI-Assisted Coding Deliver? A Difference-in-Differences Study of Cursor's Impact on Software Projects (2511.04427)
This survey from Carnegie Mellon University shows causal evidence that LLM agent assistants deliver short-term productivity gains but have lasting quality costs that can slow development over time
3. A Survey of Vibe Coding with Large Language Models (2510.12399)
Turns Vibe Coding from hype into a structured field, categorizing real development workflows. It shows which models, infrastructure, tool requirements, context, and collaboration setups affect real software development outcomes
4. From Code Foundation Models to Agents and Applications: A Practical Guide to Code Intelligence (2511.18538) (from Chinese institutes and companies like ByteDance and Alibaba)
Compares real code LLMs, shows how training and alignment choices affect code quality and security, and connects academic benchmarks to everyday software development
5. Build Your Own Coding Agent via a Step-by-Step Workshop⟶ https://github.com/ghuntley/how-to-build-a-coding-agent
A great guide that covers the basics of building an AI-powered coding assistant – from a chatbot to a file reader/explorer/editor and code search
6. State of AI Coding: Context, Trust, and Subagents⟶ https://www.turingpost.com/p/aisoftwarestack
Here is our in-depth analysis of where AI coding is heading and the new directions we see today – like agent swarms and context management importance – offering an emerging playbook beyond the IDE
If you like it, also subscribe to the Turing Post: https://www.turingpost.com/subscribe
AI coding is moving fast, and it’s getting harder to tell what actually works. Agents, workflows, context management and many other aspects are reshaping how software gets built.
We’ve collected a set of resources to help you understand how AI coding is evolving today and what building strategies work best:
1. AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities (2508.11126)
Provides a clear taxonomy, compares agent architectures, and exposes practical gaps in tools, benchmarks, and reliability that AI coding agents now struggle with
2. Does AI-Assisted Coding Deliver? A Difference-in-Differences Study of Cursor's Impact on Software Projects (2511.04427)
This survey from Carnegie Mellon University shows causal evidence that LLM agent assistants deliver short-term productivity gains but have lasting quality costs that can slow development over time
3. A Survey of Vibe Coding with Large Language Models (2510.12399)
Turns Vibe Coding from hype into a structured field, categorizing real development workflows. It shows which models, infrastructure, tool requirements, context, and collaboration setups affect real software development outcomes
4. From Code Foundation Models to Agents and Applications: A Practical Guide to Code Intelligence (2511.18538) (from Chinese institutes and companies like ByteDance and Alibaba)
Compares real code LLMs, shows how training and alignment choices affect code quality and security, and connects academic benchmarks to everyday software development
5. Build Your Own Coding Agent via a Step-by-Step Workshop⟶ https://github.com/ghuntley/how-to-build-a-coding-agent
A great guide that covers the basics of building an AI-powered coding assistant – from a chatbot to a file reader/explorer/editor and code search
6. State of AI Coding: Context, Trust, and Subagents⟶ https://www.turingpost.com/p/aisoftwarestack
Here is our in-depth analysis of where AI coding is heading and the new directions we see today – like agent swarms and context management importance – offering an emerging playbook beyond the IDE
If you like it, also subscribe to the Turing Post: https://www.turingpost.com/subscribe
replied to
sergiopaniego's
post
25 days ago
thank you for this!
wow. that's so fast. what gpu are you using?
reacted to
mitkox's
post with 🚀
25 days ago
Post
2288
Got to 1199.8 tokens/sec with Devstral Small -2 on my desktop GPU workstation. vLLM nightly.
Works out of the box with Mistral Vibe. Next is time to test the big one.
Works out of the box with Mistral Vibe. Next is time to test the big one.
-
- 3 replies
replied to
sergiopaniego's
post
25 days ago
Hi, I was trying this in Google Colab and I got a memory issue. How much vram does this need? Sorry just new to this
Is there an easy way to know how much vram is required to train a model from the HF model card?
Thanks
from trl import SFTTrainer
from datasets import load_dataset
trainer = SFTTrainer(
model="Qwen/Qwen3-0.6B",
train_dataset=load_dataset("trl-lib/Capybara", split="train"),
)
trainer.train()```
reacted to
sergiopaniego's
post with 🤗
25 days ago
Post
2268
We just released TRL v0.26.0!
It comes packed with updates:
> Agent training with tools in GRPO
> New CISPO & SAPO losses + reasoning rewards
> vLLM quantization in colocate mode
> Dataset shuffling in SFT
> Lots of NEW examples
> Tons of fixes and documentation improvements
It comes packed with updates:
> Agent training with tools in GRPO
> New CISPO & SAPO losses + reasoning rewards
> vLLM quantization in colocate mode
> Dataset shuffling in SFT
> Lots of NEW examples
> Tons of fixes and documentation improvements
-
- 3 replies
replied to
their
post
25 days ago
yeah I tried llama.cpp. was curious how to running the model from transformers code. i also tried llama-cpp-python which can do an inference of the model from your own code
what is this flag for? --mmproj
replied to
their
post
25 days ago
thank you. i agree. since i have my gpu in windows, that took time to setup too. yeah it’s a small model which works locally. trying to do more tests
replied to
their
post
25 days ago
thank you. what’s the best way to start fine-tuning?
posted
an
update
26 days ago
Post
2565
Currently having a blast learning the transformers library.
I noticed that model cards usually have Transformers code as usage examples.
So I tried to figure out how to load a model just using the transformers library without using ollama, lmstudio, or llamacpp.
Learned how to install dependencies required to make it work like pytorch and CUDA. I also used Conda for python environment dependencies.
Once I got the model loaded and sample inference working, I made an API to serve it.
I know it's very basic stuff for machine learning experts here in HF but I'm completely new to this so I'm happy to get it working!
Model used: Qwen/Qwen3-VL-8B-Instruct
GPU: NVIDIA GeForce RTX 3090
Here's the result of my experimentation
I noticed that model cards usually have Transformers code as usage examples.
So I tried to figure out how to load a model just using the transformers library without using ollama, lmstudio, or llamacpp.
Learned how to install dependencies required to make it work like pytorch and CUDA. I also used Conda for python environment dependencies.
Once I got the model loaded and sample inference working, I made an API to serve it.
I know it's very basic stuff for machine learning experts here in HF but I'm completely new to this so I'm happy to get it working!
Model used: Qwen/Qwen3-VL-8B-Instruct
GPU: NVIDIA GeForce RTX 3090
Here's the result of my experimentation
-
- 6 replies
replied to
their
post
26 days ago
thanks a lot. will check these out!