agenttune-testrun-DPO

Built using AgentTune — agentic workflows, then train / evaluate / distill / self-heal through one trajectory schema.


Finetuned from	HuggingFaceTB/SmolLM2-360M-Instruct
Algorithm	dpo
Backend	trl
Artifact	adapter
Published	2026-09-07 10:37 UTC

Usage

from peft import AutoPeftModelForCausalLM
from transformers import AutoTokenizer

model = AutoPeftModelForCausalLM.from_pretrained("ram-lexsi/agenttune-testrun-DPO")
tokenizer = AutoTokenizer.from_pretrained("ram-lexsi/agenttune-testrun-DPO")

This repo is a LoRA adapter. Load it on top of HuggingFaceTB/SmolLM2-360M-Instruct (PEFT does that from adapter_config.json).

Community: Lexsi Discord

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ram-lexsi/agenttune-testrun-DPO

Base model

HuggingFaceTB/SmolLM2-360M

Quantized

HuggingFaceTB/SmolLM2-360M-Instruct

Finetuned

(170)

this model