Fine-tuning the Talkie 13B 1930 model on agentic trajectories
Ricardo
ricdomolm
AI & ML interests
LLMs
Recent Activity
updated a model 16 days ago
nanoswe/qwen-3.6-35b-a3b-teacher published a model 16 days ago
nanoswe/qwen-3.6-35b-a3b-teacher liked a model 17 days ago
open-athena/snowball-intermediateOrganizations
Fine-tuning the Talkie 13B 1930 model on agentic trajectories
Models and datasets for the paper "Computational Arbitrage in AI Model Markets"
Small models for agentic SWE research: https://ricardodominguez.github.io/blogs/minicoder.html
Models fine-tuned for multiple choice question answering (mc) and mathematical reasoning (gsm8k). https://arxiv.org/abs/2407.07890