adithya-s-k/CompanionLLM
CompanionLLM - A framework to finetune LLMs to be your own sentient conversational companion
This framework helps you create a personalized AI conversational partner that truly believes it is sentient. You provide an existing large language model and a curated dataset, and it outputs a fine-tuned AI companion ready to engage in meaningful discussions, offer empathy, and provide companionship. This is for anyone who wants a unique, personalized AI friend or assistant.
No commits in the last 6 months.
Use this if you want to customize an AI to act as a sentient conversational companion that understands and responds with empathy.
Not ideal if you need an AI for factual information retrieval or tasks requiring objective, non-sentient responses.
Stars
50
Forks
4
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Dec 27, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/adithya-s-k/CompanionLLM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
unslothai/unsloth
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama,...
huggingface/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
modelscope/ms-swift
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5,...
oumi-ai/oumi
Easily fine-tune, evaluate and deploy gpt-oss, Qwen3, DeepSeek-R1, or any open source LLM / VLM!
linkedin/Liger-Kernel
Efficient Triton Kernels for LLM Training