Downloads · 30 days
193
0% of all-time downloads
chargoddard/llama2-22b
llama2-22b is a text generation model from chargoddard. Use it when you need the model to write or continue text. It is set up for transformers.
This is Llama 2 13b with some additional attention heads from original-flavor Llama 33b frankensteined on.
Downloads · 30 days
193
0% of all-time downloads
All-time downloads
52.5K
Public
Repo size
87.3 GB
Likes
46
Public
Click a slice to open those files.
.bin43.7 GB · 100%
From the Hugging Face model README
This is Llama 2 13b with some additional attention heads from original-flavor Llama 33b frankensteined on.
Fine-tuned on ~10M tokens from RedPajama to settle in the transplants a little.
Not intended for use as-is - this model is meant to serve as a base for further tuning, hopefully with a greater capacity for learning than 13b.
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 46.85 |
| ARC (25-shot) | 58.53 |
| HellaSwag (10-shot) | 82.55 |
| MMLU (5-shot) | 54.68 |
| TruthfulQA (0-shot) | 39.84 |
| Winogrande (5-shot) | 76.32 |
| GSM8K (5-shot) | 9.93 |
| DROP (3-shot) | 6.08 |