Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
Llama 3 8B Instruct that has been compressed in one-shot to 50% sparsity and INT8 weights+activations using SparseGPT, SmoothQuant, and GPTQ.
|
| 2 |
|
| 3 |
Made with SparseML+DeepSparse=1.7. Install with `pip install deepsparse~=1.7 "sparseml[transformers]"~=1.7 "numpy<2"`.
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
| 3 |
+
inference: false
|
| 4 |
+
tags:
|
| 5 |
+
- deepsparse
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
Llama 3 8B Instruct that has been compressed in one-shot to 50% sparsity and INT8 weights+activations using SparseGPT, SmoothQuant, and GPTQ.
|
| 9 |
|
| 10 |
Made with SparseML+DeepSparse=1.7. Install with `pip install deepsparse~=1.7 "sparseml[transformers]"~=1.7 "numpy<2"`.
|