Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,27 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
run
|
| 6 |
+
```
|
| 7 |
+
docker run -it --name llama-31 --rm \
|
| 8 |
+
-p 8080:80 \
|
| 9 |
+
-v /home/ec2-user/models-hf/:/models \
|
| 10 |
+
-e HF_MODEL_ID=/models/NousResearch/Meta-Llama-3.1-8B-Instruct \
|
| 11 |
+
-e MAX_INPUT_TOKENS=256 \
|
| 12 |
+
-e MAX_TOTAL_TOKENS=4096 \
|
| 13 |
+
-e MAX_BATCH_SIZE=1 \
|
| 14 |
+
-e LOG_LEVEL="info,text_generation_router=debug,text_generation_launcher=debug" \
|
| 15 |
+
--device=/dev/neuron0 \
|
| 16 |
+
neuronx-tgi:latest \
|
| 17 |
+
--model-id /models/NousResearch/Meta-Llama-3.1-8B-Instruct \
|
| 18 |
+
--max-batch-size 1 \
|
| 19 |
+
--max-input-tokens 256 \
|
| 20 |
+
--max-total-tokens 4096
|
| 21 |
+
|
| 22 |
+
```
|
| 23 |
+
|
| 24 |
+
test
|
| 25 |
+
```
|
| 26 |
+
curl 127.0.0.1:8080/generate -X POST -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":20}}' -H 'Content-Type: application/json'
|
| 27 |
+
```
|