Update README.md
Browse files
README.md
CHANGED
|
@@ -1,9 +1,20 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
tags:
|
| 3 |
- fp8
|
| 4 |
- vllm
|
|
|
|
| 5 |
---
|
| 6 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
This quantized model:
|
| 8 |
```
|
| 9 |
lm_eval --model vllm --model_args pretrained=Minitron-8B-Base-FP8 --tasks gsm8k --num_fewshot 5 --batch_size auto
|
|
|
|
| 1 |
---
|
| 2 |
+
license: other
|
| 3 |
+
license_name: nvidia-open-model-license
|
| 4 |
+
license_link: >-
|
| 5 |
+
https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf
|
| 6 |
tags:
|
| 7 |
- fp8
|
| 8 |
- vllm
|
| 9 |
+
base_model: nvidia/Minitron-8B-Base
|
| 10 |
---
|
| 11 |
|
| 12 |
+
# Minitron-8B-Base-FP8
|
| 13 |
+
|
| 14 |
+
FP8 quantized checkpoint of [nvidia/Minitron-8B-Base](https://huggingface.co/nvidia/Minitron-4B-Base) for use with vLLM.
|
| 15 |
+
|
| 16 |
+
## Evaluations
|
| 17 |
+
|
| 18 |
This quantized model:
|
| 19 |
```
|
| 20 |
lm_eval --model vllm --model_args pretrained=Minitron-8B-Base-FP8 --tasks gsm8k --num_fewshot 5 --batch_size auto
|