appvoid/carbono-001
Text Generation • 0.4B • Updated • 7
🤏 pico mode
appvoid
appvoid
AI & ML interests
Working on small sota models
Recent Activity
reacted to FredyRivera-dev's post with 🚀 about 7 hours ago
We wrote a full technical guide on how to train a bilingual (ES/EN) LLM from scratch: TinyQwen.
Covers:
- Hybrid architecture based on Qwen3.5
- Pre-training with 15B tokens
- Cost benchmark between H200 and B200
- Post-training with SFT + LoRA
- Full code and data, open source
With ~$11 of compute on an H200 we ran an initial training run, enough to validate the full architecture and pipeline.
Blog post: https://aquiles-ai.vercel.app/blog/tinyqwen-from-scratch
Technical feedback welcome, especially from anyone looking to replicate the pipeline with more compute. posted an update about 8 hours ago
i love reinforcement learning updated a model about 10 hours ago
appvoid/palmer-006Organizations
appvoid/graphite-001-xl
Text Generation • 0.5B • Updated • 12
appvoid/graphite-001-large-Q8_0-GGUF
Text Generation • 0.4B • Updated • 9
appvoid/graphite-001-large
Text Generation • 0.4B • Updated • 11
appvoid/Falcon-H1-Tiny-Multilingual-100M-Instruct-Q8_0-GGUF
0.1B • Updated • 10
appvoid/Falcon-H1-Tiny-Multilingual-100M-Base-Q8_0-GGUF
0.1B • Updated • 12
appvoid/Falcon-H1-Tiny-90M-Instruct-pre-DPO-Q8_0-GGUF
91.1M • Updated • 5
appvoid/Falcon-H1-Tiny-90M-Instruct-Curriculum-pre-DPO-Q8_0-GGUF
91.1M • Updated • 9
appvoid/Falcon-H1-Tiny-90M-Instruct-Curriculum-Q8_0-GGUF
91.1M • Updated • 6
appvoid/Falcon-H1-Tiny-90M-Base-Q8_0-GGUF
91.1M • Updated • 7
appvoid/e5-gguf
0.1B • Updated • 10
appvoid/harrier-gguf
0.3B • Updated • 11
appvoid/shakespeare-uai
Updated
appvoid/granite-4.0-350m-minimal-mix-sft-lora
Updated
appvoid/granite-4.0-350m-minimal-mix-sft-merged
Text Generation • 0.4B • Updated • 10
appvoid/dot
Updated • 1
appvoid/functiongemma-hermes-3k-ft-Q8_0-GGUF
Text Generation • 0.3B • Updated • 6 • 1
appvoid/arco-3-unleashed
Text Generation • 0.6B • Updated • 4
appvoid/arco-3
Text Generation • 0.6B • Updated • 3
appvoid/arco-3-gguf
Text Generation • 0.6B • Updated • 10
appvoid/arco-3-exp-1025
Text Generation • 0.6B • Updated • 3
appvoid/Qwen3-0.6B-notetaker-Q8_0-GGUF
0.6B • Updated • 8
appvoid/qwen3-0.6b-refiner-codeql-self-nothink-full-Q8_0-GGUF
0.6B • Updated • 4
appvoid/RAGU-lm-Q8_0-GGUF
0.6B • Updated • 7
appvoid/Qwen3-0.6B-Shadow-FT-BAAI-2k-Q8_0-GGUF
0.6B • Updated • 2
appvoid/Dripper-Q8_0-GGUF
Text Generation • 0.8B • Updated • 3
appvoid/event-attribute-extractor-Q8_0-GGUF
0.6B • Updated • 3
appvoid/Qwen3-0.6B-Books-Intent-Q8_0-GGUF
0.6B • Updated • 12
appvoid/syngen-reasoning-0.6b-Q8_0-GGUF
Text Generation • 0.6B • Updated • 8
appvoid/Qwen3-0.6B-m3-mcqa-reason-besthyper-fixed-Q8_0-GGUF
0.6B • Updated • 6