Downloads · 30 days
8
16% of all-time downloads
Meta-Llama-3-8B-Instruct-FLUTE
radi-cho/Meta-Llama-3-8B-Instruct-FLUTE
Meta-Llama-3-8B-Instruct-FLUTE is a text generation model from radi-cho. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as llama3.
Revisions available in this repository: - main (W4G64, scales learned); - nflw3g64 (W3G64, scales learned); - nfw4g64 (W4G64, scales not learned); - nfw3g64 (W3G64, scales not learned);
All-time downloads
51
Public
Parameters
2.9B
20.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors5.8 GB · 100%
Parameter types
How the weights are stored.
I161.7B · 60%
Try a prompt
Model card
From the Hugging Face model README
| Wiki | C4 | |
|---|---|---|
| W4G64 | 6.78 | 10.61 |
| W3G64 | 7.75 | 12.28 |
Revisions available in this repository:
main(W4G64, scales learned);nfl_w3g64(W3G64, scales learned);nf_w4g64(W4G64, scales not learned);nf_w3g64(W3G64, scales not learned);
Evaluations are provided for models with learned scales.<br>
Check the base Meta-Llama-3-8B-FLUTE for lm-eval-harness benchmarks.
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- License
- llama3
- Created
- Jul 18, 2024
- Updated
- Jul 21, 2024