sushraja/bitnet-b1.58-2B-4T-fp16-onnx

By sushraja · ↓ 0 · ♥ 2 · Updated 2025-08-16

What's in this repo

This page lists the files in sushraja/bitnet-b1.58-2B-4T-fp16-onnx, including model_q158.onnx, model.onnx.

2 ONNX models (.onnx files)
25 files, including 8 .py, 8 .json, 2 .jinja, 2 .onnx, 2 .data, 1 .md
Last updated 2025-08-16

ONNX files

File	Size	Download
bitnet_q158/model_q158.onnx	—	Download
bitnet_q2/model.onnx	—	Download

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

No README provided by the author.

Model info

onnx license:mit region:us

↓ 0 ♥ 2

Created: 2025-07-30

Updated: 2025-08-16

View on Hugging Face

Files (25)

.gitattributes

.gitignore

AdditionalQuantization.py

BitNetWeightProcess.py

ConvertToBitLinear.py

GatherQuantize.py

README.md

bitnet_q158/chat_template.jinja

bitnet_q158/genai_config.json

bitnet_q158/model_q158.onnx ONNX

bitnet_q158/model_q158.onnx.data

bitnet_q158/special_tokens_map.json

bitnet_q158/tokenizer.json

bitnet_q158/tokenizer_config.json

bitnet_q2/chat_template.jinja

bitnet_q2/genai_config.json

bitnet_q2/model.onnx ONNX

bitnet_q2/model.onnx.data

bitnet_q2/special_tokens_map.json

bitnet_q2/tokenizer.json

bitnet_q2/tokenizer_config.json

builder.py

scale_layer20_skipln_input.py

ternary_compression.py

ternary_q2_compression.py

Related models

More from sushraja

No other models by this author.

More models

No task type declared.