---
title: README
emoji: 🐢
colorFrom: yellow
colorTo: blue
sdk: static
pinned: false
---
<h1 style="line-height: 50px;"> Spectra Suite </h1>

We release the Spectra Suite consisting of 54 models ranging from 99M to 3.9B parameters across different bitwidths:

FloatLM: LLMs pretrained in FP16 (Half-Precision).
TriLM: LLMs pretrained with effective ternary bitwidth.
QuantLM 8-bit: FloatLM LLMs Quantized to 8-bits.
QuantLM 6-bit: FloatLM LLMs Quantized to 6-bits.
QuantLM 4-bit: FloatLM LLMs Quantized to 4-bits.
QuantLM 3-bit: FloatLM LLMs Quantized to 3-bits.
All models are released in unpacked (FP16 format) - compatible with FP16 GEMMs across any library supporting the LLaMa architecture.

## Usage:

```python
import transformers as tf, torch

# Please select the model you wish to run.
model_name = "SpectraSuite/TriLM_3.9B_Unpacked"

# Please adjust the temperature, repetition penalty, top_k, top_p and other sampling parameters according to your needs.
pipeline = tf.pipeline("text-generation", model=model_id, model_kwargs={"torch_dtype": torch.float16}, device_map="auto")

# These are base (pretrained) LLMs that are not instruction and chat tuned. You may need to adjust your prompt accordingly.
pipeline("Once upon a time")
```

## Citation
If you find these models or the associated paper useful, please cite the paper:

```bibtex
@misc{kaushal2024spectracomprehensivestudyternary,
      title={Spectra: A Comprehensive Study of Ternary, Quantized, and FP16 Language Models}, 
      author={Ayush Kaushal and Tejas Pandey and Tejas Vaidhya and Aaryan Bhagat and Irina Rish},
      year={2024},
      eprint={2407.12327},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2407.12327}, 
}
```