Downloads · 30 days
18
3% of all-time downloads
gpt-oss-20b-nvfp4
narendra747/gpt-oss-20b-nvfp4
gpt-oss-20b-nvfp4 is a machine learning model from narendra747. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for nml. The card lists the license as apache-2.0.
This is the deterministic NML NVFP4 recipe-v2 conversion of unsloth/gpt-oss-20b-BF16@cc89b3e7fd423253264883a80a4fa5abc619649f. It uses last-axis one-dimensional blocks of 16 weights, low-nibble-first E2M1 payloads, po…
All-time downloads
560
Public
Parameters
11.8B
23.6 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors11.8 GB · 100%
Parameter types
How the weights are stored.
U811.8B · 100%
Base models
Model card
From the Hugging Face model README
GPT-OSS 20B NVFP4
This is the deterministic NML NVFP4 recipe-v2 conversion of unsloth/gpt-oss-20b-BF16@cc89b3e7fd423253264883a80a4fa5abc619649f. It uses last-axis one-dimensional blocks of 16 weights, low-nibble-first E2M1 payloads, positive E4M3FN block scales, and one F32 global factor per quantized parameter. Small and sensitivity-critical tensors remain BF16 exactly as declared by nml-source-tensors.json.
Conversion is CPU-only; exact converter and dependency provenance is recorded in nml-artifact-manifest.json. This artifact is intended for NML and is not mislabeled as the original GPT-OSS MXFP4 representation. Exact source hashes, tensor disposition, and conversion semantics are included in the repository. Recipe: nml-nvfp4-weight-v2.
- Library
- nml
- Type
- gpt_oss
- License
- apache-2.0
- Created
- Jul 17, 2026
- Updated
- Jul 19, 2026