Void's picture

In a Training Loop 🔄

Void

Parveshiiii

·

parveshiiii

AI & ML interests

I love deep neural nets.

Recent Activity

reacted to their post with 🔥 about 6 hours ago

🚀 Wanna train your own AI Model or Tokenizer from scratch? Building models isn’t just for big labs anymore — with the right data, compute, and workflow, you can create **custom AI models** and **tokenizers** tailored to any domain. Whether it’s NLP, domain‑specific datasets, or experimental architectures, training from scratch gives you full control over vocabulary, embeddings, and performance. ✨ Why train your own? - Full control over vocabulary & tokenization - Domain‑specific optimization (medical, legal, technical, etc.) - Better performance on niche datasets - Freedom to experiment with architectures ⚡ The best part? - Tokenizer training (TikToken / BPE) can be done in **just 3 lines of code**. - Model training runs smoothly on **Google Colab notebooks** — no expensive hardware required. 📂 Try out my work: - 🔗 https://github.com/OE-Void/Tokenizer-from_scratch - 🔗 https://github.com/OE-Void/GPT

posted an update about 6 hours ago

🚀 Wanna train your own AI Model or Tokenizer from scratch? Building models isn’t just for big labs anymore — with the right data, compute, and workflow, you can create **custom AI models** and **tokenizers** tailored to any domain. Whether it’s NLP, domain‑specific datasets, or experimental architectures, training from scratch gives you full control over vocabulary, embeddings, and performance. ✨ Why train your own? - Full control over vocabulary & tokenization - Domain‑specific optimization (medical, legal, technical, etc.) - Better performance on niche datasets - Freedom to experiment with architectures ⚡ The best part? - Tokenizer training (TikToken / BPE) can be done in **just 3 lines of code**. - Model training runs smoothly on **Google Colab notebooks** — no expensive hardware required. 📂 Try out my work: - 🔗 https://github.com/OE-Void/Tokenizer-from_scratch - 🔗 https://github.com/OE-Void/GPT

liked a dataset about 7 hours ago

Modotte/MathX-20M

View all activity

Organizations

New activity in Modotte/CodeX-2M-Thinking 2 months ago

[bot] Conversion to Parquet

#1 opened 2 months ago by

parquet-converter

New activity in OEvortex/TTS-OLD 3 months ago

Seeking help: TypeError: DacModel.decode() missing 1 required positional argument: 'quantized_representation'

#3 opened 9 months ago by

New activity in Qwen/Qwen3-8B 3 months ago

Fix incorrect vocab_size in Qwen3-8B config.json

#25 opened 3 months ago by

New activity in IndianAIDevs/README 4 months ago

Let's Talk about AI

#1 opened 5 months ago by

Welcomes and Greetings

#2 opened 5 months ago by

New activity in discord-community/README 4 months ago

How to solve device mismatch issue when using offloading with QwenImageEditPlus pipeline and GGUF weights

#10 opened 4 months ago by

How to run inference with a model loaded on both CPU and GPU with device_map="balanced"

#9 opened 4 months ago by

New activity in Threatthriver/qussar-alpha 5 months ago

Delete training_args.bin

#5 opened 5 months ago by

Delete trainer_state.json

#4 opened 5 months ago by

Delete rng_state.pth

#3 opened 5 months ago by

Delete rng_state.pth

#2 opened 5 months ago by

Delete optimizer.pt

#1 opened 5 months ago by

New activity in Modotte/MathX-5M 6 months ago

Response Model Tag

#5 opened 6 months ago by

Has more rows than mentioned

#4 opened 6 months ago by

What is the model used to produce responses?

#3 opened 6 months ago by

New activity in zero-gpu-explorers/README 7 months ago

How do I join this organisation?

#49 opened over 1 year ago by

New activity in discord-community/WelcomeBot 7 months ago

test

#2 opened 11 months ago by

New activity in social-post-explorers/README 7 months ago

Llama 2 model access grant

#31 opened almost 2 years ago by

Request to post

#36 opened over 1 year ago by

Walmart-the-bag

New activity in deepseek-ai/DeepSeek-Prover-V2-7B 9 months ago

Update README.md

#5 opened 9 months ago by