Beta

Explore
Marketplace
Neural Labs
Chat
Wallet
Docs

Beta

Explore Marketplace Neural Labs Wallet Docs

Build

Manage

My assets Manage wallet Organization

Community

Discord X (Twitter)Telegram

Docs Privacy Policy Terms and Conditions

Proud member of

Proud member of

Docs Cookie Policy

Privacy Policy Terms and Conditions

© 2026 AlphaNeural AI. All rights reserved.

SpeciaRL_qwen2_5vl-7b_rft – AI Model by s-angheben | AlphaNeural AI

You can deploy this model and start earning money today!

s-angheben/
SpeciaRL_qwen2_5vl-7b_rft

like

0

text-generation

Qwen/Qwen2.5-VL-7B-Instruct

Views

No views yet

SpeciaRL_rft

This repository provides the LoRA adapter for the rft fine-tuned model introduced in SpeciaRL. Built on top of Qwen/Qwen2.5-VL-7B-Instruct.

Training hyperparameters

algorithm: GRPO
learning_rate: 3e-5
train_batch_size: 256
max_prompt_length: 2048
max_response_length: 2048
lora_rank: 64
lora_alpha: 32
target_modules: all-linear (visual layers excluded)
kl_loss: True (coef=0.01, type=low_var_kl)
rollout_n: 10
num_gpus: 4
total_epochs: 15

Framework versions

VERL
PEFT 0.17.1
Transformers 4.57.0
PyTorch 2.6.0+cu124