Update README.md
Browse files
README.md
CHANGED
@@ -5,22 +5,27 @@
|
|
5 |
```
|
6 |
hf download xai-org/grok-2 --local-dir /local/grok-2
|
7 |
```
|
|
|
8 |
You might encounter some errors during the download. Please retry until the download is successful.
|
9 |
If the download succeeds, the folder should contain **42 files** and be approximately 500 GB.
|
10 |
|
11 |
- Launch a server.
|
12 |
|
13 |
-
Install the latest SGLang inference engine
|
14 |
|
15 |
-
|
16 |
```
|
17 |
python3 -m sglang.launch_server --model /local/grok-2 --tokenizer-path /local/grok-2/tokenizer.tok.json --tp 8 --quantization fp8 --attention-backend triton
|
18 |
```
|
19 |
|
20 |
- Send a request.
|
21 |
|
|
|
|
|
22 |
```
|
23 |
python3 -m sglang.test.send_one --prompt "Human: What is your name? <|separator|>\n\nAssistant:"
|
24 |
```
|
25 |
|
26 |
-
|
|
|
|
|
|
5 |
```
|
6 |
hf download xai-org/grok-2 --local-dir /local/grok-2
|
7 |
```
|
8 |
+
|
9 |
You might encounter some errors during the download. Please retry until the download is successful.
|
10 |
If the download succeeds, the folder should contain **42 files** and be approximately 500 GB.
|
11 |
|
12 |
- Launch a server.
|
13 |
|
14 |
+
Install the latest SGLang inference engine (>= v0.5.1) from https://github.com/sgl-project/sglang/
|
15 |
|
16 |
+
Use the command below to launch an inference server. This checkpoint is TP=8, so you will need 8 GPUs (each with > 40GB of memory).
|
17 |
```
|
18 |
python3 -m sglang.launch_server --model /local/grok-2 --tokenizer-path /local/grok-2/tokenizer.tok.json --tp 8 --quantization fp8 --attention-backend triton
|
19 |
```
|
20 |
|
21 |
- Send a request.
|
22 |
|
23 |
+
This is a post-trained model, so please use the correct [chat template](https://github.com/sgl-project/sglang/blob/97a38ee85ba62e268bde6388f1bf8edfe2ca9d76/python/sglang/srt/tokenizer/tiktoken_tokenizer.py#L106).
|
24 |
+
|
25 |
```
|
26 |
python3 -m sglang.test.send_one --prompt "Human: What is your name? <|separator|>\n\nAssistant:"
|
27 |
```
|
28 |
|
29 |
+
You should be able to see the model output its name, Grok.
|
30 |
+
|
31 |
+
Learn more about other ways to send requests [here](https://docs.sglang.ai/basic_usage/send_request.html).
|