Rex Tro 111
RexTRO111
AI & ML interests
pretraining
Recent Activity
reacted to Banaxi-Tech's post with 🔥 5 minutes ago
We did an experiment, we wanted to see if AI is good enough to train models.
We used GPT 5.6 Sol Max for this because its one of the most powerful ones right now.
Our instructions were, it should write the training code, and start the training process and monitor it by itself.
We also gave it a link to BananaMind 2 Mini to get our architecture right.
The result: It worked, it made the working BananaMind 2 Nano, and even beat our previous MiniBananaMind v4 9M.
Its getting way easier to develop your own models now! new activity about 5 hours ago
SupraLabs/Supra2-100M-Instruct:Wow liked a model about 6 hours ago
DinoResearch/EspBPE-49KOrganizations
models 9
RexTRO111/Smollm2-360M-MM2-Comments-LoRA-ZIP
Updated
RexTRO111/rextro-community
Updated
RexTRO111/hn_tokenizer-zip-10k-vocab
Updated
RexTRO111/InstructPythia-410M-LoRA-v1
Text Generation • Updated
RexTRO111/Qwen3-4B-MegaR3ASONER-v1
Text Generation • 4B • Updated • 545 • 1
RexTRO111/Qwen3-4B-MegaR3ASONER-LoRA-v1
Text Generation • Updated • 41
RexTRO111/Alisio-25M-CPT-v1
24.8M • Updated • 56 • 1
RexTRO111/Alisio-25M-Instruct-v1
24.8M • Updated • 90
RexTRO111/Alisio-25M-Base-v1
24.8M • Updated • 98
datasets 37
RexTRO111/Mega-Instruction-Following-Dataset-Queso-Training
Preview • Updated • 11
RexTRO111/mixed-instruction-following-data
Updated • 4
RexTRO111/FINETUNING-RAW-DATASET-V1
Viewer • Updated • 7 • 31
RexTRO111/Text-Pairs-v1-TXT
Viewer • Updated • 301 • 48
RexTRO111/algeria-vs-austria-2026-world-cup-100x
Viewer • Updated • 100 • 34
RexTRO111/2024-Events-Benchmark
Viewer • Updated • 230 • 9
RexTRO111/QandA-Dataset-Vianji
Viewer • Updated • 9 • 38
RexTRO111/DeepSeek-Reasoning-Chains
Viewer • Updated • 5 • 45
RexTRO111/LMArena-SFT-Winners-Rextro
Viewer • Updated • 12 • 71
RexTRO111/lmarena-dataset
Viewer • Updated • 2 • 38