Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: text-generation
|
| 3 |
+
tags:
|
| 4 |
+
- Neuron
|
| 5 |
+
- Optimum-Neuron
|
| 6 |
+
- AWS
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
|
| 10 |
+
Compiled Llama-2-7b-chat-hf using optimum-neuron
|
| 11 |
+
|
| 12 |
+
```shell
|
| 13 |
+
optimum-cli export neuron --model NousResearch/Llama-2-7b-chat-hf --batch_size 1 --sequence_length 1024 --num_cores 2 --auto_cast_type fp16 ./models/NousResearch/Llama-2-7b-chat-hf
|
| 14 |
+
```
|