You can deploy this model and start earning money today!

AshwinKM2005/
serl-checkpoints

safetensors

serl

reinforcement-learning

qwen2.5

checkpoints

apache-2.0

Views

No views yet

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

python

# 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.