Downloads · 30 days
14
15% of all-time downloads
internal-testing-qwen3_0.6b-fp8-tuned-orthogonal
amd-quark/internal-testing-qwen3_0.6b-fp8-tuned-orthogonal
internal-testing-qwen3_0.6b-fp8-tuned-orthogonal is a machine learning model from amd-quark. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
96
Public
Parameters
752M
1.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.1 GB · 99%
Parameter types
How the weights are stored.
F8_E4M3440M · 59%
Model card
From the Hugging Face model README
Generated with:
CUDA_VISIBLE_DEVICES=5 python train_rotation.py \
--model_dir /models/Qwen_Qwen3-0.6B \
--quant_scheme fp8 \
--eval_batch_size 16 \
--num_samples 4000 \
--learning_rate 1.5 \
--rotation_algo_config_file ${ROTATION_TRAIN_CFG} \
--output_dir qwen3-0.6b-fp8-tuned-orthogonal \
--max_steps 5 \
--loss_type kl_top_1000 \
--model_attn_implementation sdpa \
--train_batch_size 8 \
--model_export hf_format \
--export_weight_format real_quantized
- Type
- qwen3
- Created
- Jan 21, 2026
- Updated
- Jan 21, 2026