Update README.md
Browse filesfix path after move
README.md
CHANGED
@@ -20,6 +20,7 @@ This model has been exported to the `neuron` format using specific `input_shapes
|
|
20 |
|
21 |
It has been compiled to run on an inf2.24xlarge instance on AWS. Note that while the inf2.24xlarge has 12 cores, this compilation is only use 8. For this model and configuration, the cores have to be a power of 2.
|
22 |
|
|
|
23 |
**This has been compiled using version 2.16 of the Neuron SDK. Make sure your environment has version 2.16 installed**
|
24 |
|
25 |
Please refer to the 🤗 `optimum-neuron` [documentation](https://huggingface.co/docs/optimum-neuron/main/en/guides/models#configuring-the-export-of-a-generative-model) for an explanation of these parameters.
|
@@ -52,7 +53,7 @@ pip3 install git+https://github.com/huggingface/optimum-neuron.git
|
|
52 |
|
53 |
```
|
54 |
from optimum.neuron import pipeline
|
55 |
-
p = pipeline('text-generation', '
|
56 |
p("Hi, my name is ",
|
57 |
do_sample=True,
|
58 |
top_k=10,
|
|
|
20 |
|
21 |
It has been compiled to run on an inf2.24xlarge instance on AWS. Note that while the inf2.24xlarge has 12 cores, this compilation is only use 8. For this model and configuration, the cores have to be a power of 2.
|
22 |
|
23 |
+
|
24 |
**This has been compiled using version 2.16 of the Neuron SDK. Make sure your environment has version 2.16 installed**
|
25 |
|
26 |
Please refer to the 🤗 `optimum-neuron` [documentation](https://huggingface.co/docs/optimum-neuron/main/en/guides/models#configuring-the-export-of-a-generative-model) for an explanation of these parameters.
|
|
|
53 |
|
54 |
```
|
55 |
from optimum.neuron import pipeline
|
56 |
+
p = pipeline('text-generation', 'aws-neuron/SOLAR-10.7B-v1.0-neuron')
|
57 |
p("Hi, my name is ",
|
58 |
do_sample=True,
|
59 |
top_k=10,
|