Downloads · 30 days
142
3% of all-time downloads
llama-161M-100B
abacaj/llama-161M-100B
llama-161M-100B is a text generation model from abacaj. 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.
Trained on 100B tokens. - 1e-3 LR - 0.1 wd - WSD scheduler with 10% decay - 80% code, 10% NL, 10% instruction data - Dataset decontaminated against popular benchmarks following bigcode - 8x3090s 110~ hours
All-time downloads
5.5K
Public
Parameters
162M
2 GB on disk
Likes
23
Public
Repo makeup
Click a slice to open those files.
.onnx1.9 GB · 85%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- llama
- Access
- Public
- Created
- Jul 7, 2024
- Updated
- Jul 7, 2024
- SHA
- ab1b2283
Try a prompt
Model card
From the Hugging Face model README
llama-161M
Trained on 100B tokens.
- 1e-3 LR
- 0.1 wd
- WSD scheduler with 10% decay
- 80% code, 10% NL, 10% instruction data
- Dataset decontaminated against popular benchmarks following bigcode
- 8x3090s 110~ hours
This is a base pretrained model and requires further fine tuning to be useful.
Model Details
| openai/openai_humaneval (greedy) | mbpp (greedy) |
|---|---|
| 9.2% | 9.8% |
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- License
- apache-2.0
- Created
- Jul 7, 2024
- Updated
- Jul 7, 2024