Downloads · 30 days
29
100% of all-time downloads
qwen36-twla-beam-lambda0p2
minjaechoi/qwen36-twla-beam-lambda0p2
qwen36-twla-beam-lambda0p2 is a machine learning model from minjaechoi. 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
29
Public
Parameters
35.1B
70.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors70.2 GB · 100%
At a glance
- Model type
- qwen3_5_moe
- Access
- Public
- Created
- Sep 10, 2026
- Updated
- Sep 14, 2026
- SHA
- 118b661b
Model card
From the Hugging Face model README
qwen36-twla-beam-lambda0p2
Local code references:
TWLA/branch_bound_search.pyTWLA/build_twla_expert_level_bank.pyTWLA/datautils.pyTWLA/inference.pyTWLA/optimize_twla_hierarchical_nll.pyTWLA/prepare_bipea_v3_data.pyTWLA/quantize/E2M_ATQ.pyTWLA/quantize/E2M_ATQ_10level.pyTWLA/quantize/E2M_ATQ_11level.pyTWLA/quantize/E2M_ATQ_4level.pyTWLA/quantize/E2M_ATQ_5level.pyTWLA/quantize/E2M_ATQ_6level.pyTWLA/quantize/E2M_ATQ_7level.pyTWLA/quantize/E2M_ATQ_8level.pyTWLA/quantize/E2M_ATQ_9level.pyTWLA/quantize/E2M_ATQ_bidirectional.pyTWLA/quantize/E2M_ATQ_groupwise.pyTWLA/quantize/E2M_ATQ_mixed_precision.pyTWLA/quantize/__init__.pyTWLA/quantize/const.pyTWLA/quantize/e2m_atq_fwrd.pyTWLA/quantize/e2m_atq_fwrd_multigpu.pyTWLA/quantize/k_preprocessor_ternary.pyTWLA/quantize/moe_round_worker.pyTWLA/quantize/quantizer.pyTWLA/quantize/ternary_kernel.pyTWLA/quantize/ternary_pack.pyTWLA/quantize_qwen36_experts_5level.pyTWLA/requirements.txtTWLA/run_benchmark_qwen36_multilevel.pyTWLA/taylor_fisher_proxy.py
- Type
- qwen3_5_moe
- Created
- Sep 10, 2026
- Updated
- Sep 14, 2026