Downloads · 30 days
21
1% of all-time downloads
shermansiu/lc0_BT4-1024x15x32h-swa-5000000
lc0_BT4-1024x15x32h-swa-5000000 is a machine learning model from shermansiu. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as gpl-3.0.
- config.yaml: Originally BT4-init1.yaml, obtained from Discord. - The model was originally downloaded from: https://storage.lczero.org/files/networks-contrib/big-transformers/BT4-1024x15x32h-swa-5000000.pb.gz
Downloads · 30 days
21
1% of all-time downloads
All-time downloads
2.3K
Public
Parameters
206M
1.9 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors824 MB · 43%
From the Hugging Face model README
config.yaml: Originally BT4-init1.yaml, obtained from Discord.from chessnets.pipelines.lc0 import Lc0Pipeline
pipeline = Lc0Pipeline.from_pretrained("shermansiu/lc0_BT4-1024x15x32h-swa-5000000")
predictions = pipeline("1. e4 e5")
config.json: canonical, fully materialized ChessNets architecture configmodel.safetensors: decoded float32 PyTorch tensorsprovenance.json: source and conversion hashesoriginal/model.pb.gz: original Lc0 protobuf checkpointtraining/original_lczero_training_config.yaml: original training configThe learned protobuf weight layers used LINEAR16 encoding. Conversion decoded
those values into float32 tensors; it cannot restore precision already lost in
the source encoding.
This is an Lc0 policy/value network. Its playing behavior and strength depend on the source network and the inference/search settings.
Review legal moves and probabilities in context. Outputs are not guarantees of playing strength, fairness, or suitability for high-stakes decisions.
Credit the source network identified above and the Leela Chess Zero project. This community checkpoint does not have a model-specific paper citation until the official project supplies one.