Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
LiyuanLucasLiu
/
Qwen2.5-32B-quantized.w8a8
like
0
Safetensors
qwen2
8-bit precision
compressed-tensors
Model card
Files
Files and versions
xet
Community
main
Qwen2.5-32B-quantized.w8a8
/
flashrl_config.bf16.yaml
LiyuanLucasLiu
Upload flashrl_config.bf16.yaml with huggingface_hub
9079e31
verified
3 months ago
raw
Copy download link
history
blame
contribute
delete
Safe
91 Bytes
configs:
-
distributed_executor_backend:
external_launcher
fn:
bf16
load_format:
dummy