qwen2.5-0.5b-instruction-following-sft
Built using Aligntune — supports any open-source model, any algorithm, any backend (TRL / Unsloth / ES / etc).
| Built by | zlyngkhoi |
| Built on | 2026-08-18 07:01 UTC |
| Finetuned from | Qwen/Qwen2.5-0.5B-Instruct |
| Algorithm | SFT (Instruction Following) |
| Backend | Unsloth + TRL |
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("zlyngkhoi/qwen2.5-0.5b-instruction-following-sft")
tokenizer = AutoTokenizer.from_pretrained("zlyngkhoi/qwen2.5-0.5b-instruction-following-sft")