Downloads · 30 days
0
bird-of-paradise/Llama-Hopper-Reasoning-v1
Llama-Hopper-Reasoning-v1 is a reinforcement learning model from bird-of-paradise. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This model is a research artifact from the blog post: Hopper: The Optimizer That Learns Parallelism 2x Faster Than Adam.
Downloads · 30 days
0
Access
Public
Updated Feb 6, 2026
Repo size
1000 MB
Likes
0
Public
Click a slice to open those files.
.safetensors988 MB · 99%
From the Hugging Face model README
This model is a research artifact from the blog post: Hopper: The Optimizer That Learns Parallelism 2x Faster Than Adam.
It was trained to benchmark Hopper (a modified Muon optimizer with ns_steps=1 + Variance Normalization) against AdamW in a Reinforcement Learning (DAPO) setting.
We found that standard Muon (ns_steps=5) causes entropy collapse in RL, while Adam (ns_steps=0) relies on linear heuristics.
This model (cp-200) demonstrates a unique property: It solves parallel reasoning tasks that Adam fails, even though it is slightly clumsy at arithmetic.
Qwen/Qwen2.5-0.5B-Instructfrom huggingface_hub import HfApi, login
# 1. Login
login()
# 2. Upload only the essentials
api = HfApi()
repo_id = "JenWei/Llama-Hopper-Reasoning-v1"
checkpoint_path = "./hopper-cp-200" # folder path for the check point
print("🚀 Uploading ONLY inference files...")
api.upload_folder(
folder_path=checkpoint_path,
repo_id=repo_id,
repo_type="model",
)