Downloads · 30 days
21
11% of all-time downloads
EliasOenal/Llama-3.1-Nemotron-70B-Instruct-W8A8-dynamic
Llama-3.1-Nemotron-70B-Instruct-W8A8-dynamic is a text generation model from EliasOenal. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as llama3.1.
- Model Architecture: Llama-3.1-Nemotron-70B-Instruct-HF - Input: Text - Output: Text - Model Optimizations: - Weight quantization: INT8 - Activation quantization: INT8 - Release Date: 2/12/2025 - Version: 1.0 - Model…
Downloads · 30 days
21
11% of all-time downloads
All-time downloads
185
Public
Parameters
70.6B
72.7 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors72.7 GB · 100%
How the weights are stored.
I868.5B · 97%
From the Hugging Face model README
Quantized version of Llama-3.1-Nemotron-70B-Instruct-HF.
This model was obtained by quantizing the weights and activations to W8A8 data type, ready for inference with vLLM. This optimization reduces the number of bits per parameter from 16 to 8, reducing the disk size and GPU memory requirements by approximately 50%. Only the weights and activations of the linear operators within transformers blocks are quantized.
This model can be deployed efficiently using the vLLM backend.
This model was created with llm-compressor and the neuralmagic/LLM_compression_calibration dataset.