saisaharsh3/Soup
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
AI/ML Engineer • Building Agentic AI, Local LLMs & Autonomous Systems Focused on Edge AI, RAG pipelines, workflow automation, and real-time intelligence.
Repositories
saisaharsh3/colibri
Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
saisaharsh3/Jira-to-GitLab-AI-Pipeline
saisaharsh3/jira-to-github-n8n-automation-
saisaharsh3/ServiceNow_to_GitLab_devops_Autonomous-Agent
saisaharsh3/Orchestrix_AI-Multi-Model_Agentic_AI_Assistant
Orchestrix AI – A Multi-Model Agentic AI Assistant with local LLM, RAG, web automation, and Gmail integration