Downloads · 30 days
0
agenttune-agent-ops-GRPO
ram-lexsi/agenttune-agent-ops-GRPO
agenttune-agent-ops-GRPO is a machine learning model from ram-lexsi. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
<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/"<i…
Access
Public
Updated Sep 10, 2026
Repo size
313 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt170 MB · 45%
At a glance
- Library
- transformers
- Access
- Public
- Created
- Sep 10, 2026
- Updated
- Sep 10, 2026
- SHA
- fa21dcfd
Base models
Model card
From the Hugging Face model README
<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-agent-ops-GRPO/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-agent-ops-GRPO/resolve/main/agenttune_banner.png" alt="AgentTune" style="height: 60px;"/></a>
</td>
</tr>
</table>
</div>
agenttune-agent-ops-GRPO
Built using AgentTune — agentic workflows, then train / evaluate / distill / self-heal through one trajectory schema.
| Finetuned from | Qwen/Qwen3.5-4B |
| Algorithm | grpo |
| Backend | trl |
| Artifact | adapter |
| Published | 2026-09-10 20:25 UTC |
Usage
from peft import AutoPeftModelForCausalLM
from transformers import AutoTokenizer
model = AutoPeftModelForCausalLM.from_pretrained("ram-lexsi/agenttune-agent-ops-GRPO")
tokenizer = AutoTokenizer.from_pretrained("ram-lexsi/agenttune-agent-ops-GRPO")
This repo is a LoRA adapter. Load it on top of Qwen/Qwen3.5-4B (PEFT does that from adapter_config.json).
Community: Lexsi Discord
- Library
- transformers
- Created
- Sep 10, 2026
- Updated
- Sep 10, 2026