Downloads · 30 days
8
11% of all-time downloads
smol_llama-220M-GQA-bpw2.5
blockblockblock/smol_llama-220M-GQA-bpw2.5
smol_llama-220M-GQA-bpw2.5 is a text generation model from blockblockblock. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
All-time downloads
73
Public
Repo size
421 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors140 MB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- llama
- Access
- Public
- Created
- Mar 12, 2024
- Updated
- Mar 12, 2024
- SHA
- 64bcab63
Try a prompt
Model card
From the Hugging Face model README
smol_llama: 220M GQA
model card WIP, more details to come
A small 220M param (total) decoder model. This is the first version of the model.
- 1024 hidden size, 10 layers
- GQA (32 heads, 8 key-value), context length 2048
- train-from-scratch on one GPU :)
Links
Here are some fine-tunes we did, but there are many more possibilities out there!
- instruct
- code
- python (pypi) - link
- zephyr DPO tune
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 29.44 |
| AI2 Reasoning Challenge (25-Shot) | 24.83 |
| HellaSwag (10-Shot) | 29.76 |
| MMLU (5-Shot) | 25.85 |
| TruthfulQA (0-shot) | 44.55 |
| Winogrande (5-shot) | 50.99 |
| GSM8k (5-shot) | 0.68 |
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- License
- apache-2.0
- Languages
- en
- Created
- Mar 12, 2024
- Updated
- Mar 12, 2024