Downloads · 30 days
0
serl-models
AshwinKM2005/serl-models
serl-models is a reinforcement learning model from AshwinKM2005. 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.
Compressed checkpoints from SeRL (Self-Evolving Reinforcement Learning) experiments. Files use ZipNN lossless compression (~33% smaller, transparent loading).
Access
Public
Updated Mar 11, 2026
Repo size
8.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.znn8.8 GB · 99%
At a glance
- Task
- Reinforcement Learning
- License
- apache-2.0
- Access
- Public
- Created
- Mar 11, 2026
- Updated
- Mar 11, 2026
- SHA
- c6f3dc7e
Model card
From the Hugging Face model README
SeRL Training Checkpoints
Compressed checkpoints from SeRL (Self-Evolving Reinforcement Learning) experiments. Files use ZipNN lossless compression (~33% smaller, transparent loading).
Quick Start
pip install zipnn huggingface_hub transformers
# Enable ZipNN transparent loading
from zipnn import zipnn_hf
zipnn_hf()
from huggingface_hub import snapshot_download
from transformers import AutoModelForCausalLM, AutoTokenizer
# Download specific checkpoint
path = snapshot_download(
"AshwinKM2005/serl-checkpoints",
allow_patterns="serl_arce_qwen25_1_5b/huggingface/*"
)
# Load model (auto-decompresses .znn files)
model = AutoModelForCausalLM.from_pretrained(
f"{path}/serl_arce_qwen25_1_5b/huggingface/global_step200_hf"
)
Experiments
| Experiment | Base Model | Dataset |
|---|---|---|
| serl_arcc_qwen25_0_5b | Qwen2.5-0.5B | ARC-Challenge |
| serl_ARC-c_qwen25_1_5b | Qwen2.5-1.5B | ARC-Challenge |
| serl_arce_qwen25_0_5b | Qwen2.5-0.5B | ARC-Easy |
| serl_arce_qwen25_1_5b | Qwen2.5-1.5B | ARC-Easy |
Structure
serl-checkpoints/
├── serl_arcc_qwen25_0_5b/
│ ├── huggingface/global_step100_hf/
│ └── deepspeed/global_step100/
├── serl_ARC-c_qwen25_1_5b/
│ └── ...
└── ...
Compression
Files ending in .safetensors.znn are ZipNN compressed.
The zipnn_hf() hook enables transparent loading.
- Task
- Reinforcement Learning
- License
- apache-2.0
- Created
- Mar 11, 2026
- Updated
- Mar 11, 2026