---
library_name: transformers
base_model: HuggingFaceTB/SmolLM2-360M-Instruct
tags:
  - agenttune
  - grpo
  - trl
  - adapter
---

<div align="center">
  <table border="0" cellspacing="0" cellpadding="0" style="border: none; border-collapse: collapse;">
    <tr>
      <td align="center" style="border: none; vertical-align: middle;">
        <a href="https://lexsi.ai/"><img src="https://huggingface.co/ram-lexsi/agenttune-testrun-vector-memory/resolve/main/lexsi_logo.png" alt="Lexsi Labs" style="height: 60px; border-radius: 12px;"/></a>
      </td>
      <td align="center" style="border: none; vertical-align: middle;">
        <a href="https://github.com/Lexsi-Labs/AgentTune_mirror"><img src="https://huggingface.co/ram-lexsi/agenttune-testrun-vector-memory/resolve/main/agenttune_banner.png" alt="AgentTune" style="height: 60px;"/></a>
      </td>
    </tr>
  </table>
</div>

# agenttune-testrun-vector-memory

Built using [AgentTune](https://github.com/Lexsi-Labs/AgentTune_mirror) — agentic workflows, then train / evaluate / distill / self-heal through one trajectory schema.

| | |
|---|---|
| **Finetuned from** | [HuggingFaceTB/SmolLM2-360M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-360M-Instruct) |
| **Algorithm** | grpo |
| **Backend** | trl |
| **Artifact** | adapter |
| **Published** | 2026-09-09 08:32 UTC |



## Usage

```python
from peft import AutoPeftModelForCausalLM
from transformers import AutoTokenizer

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

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](https://discord.com/invite/dtEDQ2Z3eg)