|
--- |
|
license: llama3.1 |
|
language: |
|
- en |
|
inference: false |
|
fine-tuning: false |
|
tags: |
|
- nvidia |
|
- llama3.1 |
|
datasets: |
|
- nvidia/HelpSteer2 |
|
base_model: meta-llama/Llama-3.1-70B-Instruct |
|
pipeline_tag: text-generation |
|
library_name: transformers |
|
--- |
|
|
|
Quantized model => https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF |
|
|
|
**Quantization Details:** |
|
Quantization is done using turboderp's ExLlamaV2 v0.2.2. |
|
|
|
I use the default calibration datasets and arguments. The repo also includes a "measurement.json" file, which was used during the quantization process. |
|
|
|
For models with bits per weight (BPW) over 6.0, I default to quantizing the `lm_head` layer at 8 bits instead of the standard 6 bits. |
|
|
|
|
|
|
|
--- |
|
|
|
**Who are you? What's with these weird BPWs on [insert model here]?** |
|
I specialize in optimized EXL2 quantization for models in the 70B to 100B+ range, specifically tailored for 48GB VRAM setups. My rig is built using 2 x 3090s with a Ryzen APU (APU used solely for desktop output—no VRAM wasted on the 3090s). I use TabbyAPI for inference, targeting context sizes between 32K and 64K. |
|
|
|
Every model I upload includes a `config.yml` file with my ideal TabbyAPI settings. If you're using my config, don’t forget to set `PYTORCH_CUDA_ALLOC_CONF=backend:cudaMallocAsync` to save some VRAM. |
