The Mind of Tashi
Collection
A blind-commit reasoning duel vs a ~200M-active local model. Build Small Hackathon, Track Two. • 11 items • Updated
Mind of Tashi — mini student LoRA adapter
The 21.8 MB LoRA adapter behind mind-of-tashi-mini-sft (see that card for the fine-tune config and eval results): r=32 / α=64 over the attention + MLP projections, trained on the mind-of-tashi-selfplay corpus. Apply with peft onto the base model, or use the merged repo directly.
- Downloads last month
- 32
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for build-small-hackathon/mind-of-tashi-mini-sft-lora
Base model
kshitijthakkar/tracegenix-mini-sft-clean-3ep
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("kshitijthakkar/tracegenix-mini-sft-clean-3ep") model = PeftModel.from_pretrained(base_model, "build-small-hackathon/mind-of-tashi-mini-sft-lora")