Downloads · 30 days
0
jingfengya/Qwen3-32B_nas_bank
Qwen3-32B_nas_bank is a machine learning model from jingfengya. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This repository is the metadata entry point for a split dense-NAS weight bank. The bank contains 64 transformer layers and seven selectable dense linear modules per layer. The source checkpoints are sharded across the…
Downloads · 30 days
0
Access
Public
Updated Sep 17, 2026
Repo size
197 GB
Likes
0
Public
Click a slice to open those files.
.safetensors197 GB · 100%
From the Hugging Face model README
This repository is the metadata entry point for a split dense-NAS weight bank.
The bank contains 64 transformer layers and seven selectable dense linear modules
per layer. The source checkpoints are sharded across the linked ModelScope
repositories listed in bank_manifest.json.
Use a recipe to download only the selected backbone and linear slices:
python pull_recipe_model.py \
--repo-id jingfeng0813/Qwen3-32B_nas_bank \
--recipe-json ./recipes/baselines/paro_w3.json \
--output-dir ./assembled_model
The downloader verifies the published SHA256 values before writing a HF-style
model.safetensors.index.json.
This bank also publishes 2-, 3-, and 4-bit linear sources from
awq, gptq, omni, quip. Each source is converted to ordinary Hugging Face
float16 linear tensors. Source-specific fused RMSNorm scales are folded into
the affected q/k/v and gate/up projections against the original pretrained
backbone, so recipes can mix these published sources without requiring a
runtime quantization package or an additional LET transformation.
The extension weights are stored in jingfeng0813/Qwen3-32B_nas_bank_part5, jingfeng0813/Qwen3-32B_nas_bank_part6, jingfeng0813/Qwen3-32B_nas_bank_part7, jingfeng0813/Qwen3-32B_nas_bank_part8; source
manifests and recipes are indexed from this main repository.
The records/repairs/ directory documents narrowly scoped source repairs and
their finite-tensor and remote-hash audits. These records are part of the
published provenance for the affected source; the original quantized
checkpoint is not modified.