Instructions to use RUCAIBox/mtl-open-dialog with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RUCAIBox/mtl-open-dialog with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="RUCAIBox/mtl-open-dialog")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("RUCAIBox/mtl-open-dialog", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RUCAIBox/mtl-open-dialog with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RUCAIBox/mtl-open-dialog"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RUCAIBox/mtl-open-dialog",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RUCAIBox/mtl-open-dialog

SGLang

How to use RUCAIBox/mtl-open-dialog with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "RUCAIBox/mtl-open-dialog" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RUCAIBox/mtl-open-dialog",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "RUCAIBox/mtl-open-dialog" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RUCAIBox/mtl-open-dialog",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RUCAIBox/mtl-open-dialog with Docker Model Runner:
```
docker model run hf.co/RUCAIBox/mtl-open-dialog
```

StevenTang commited on Jun 22, 2022

Commit

bf39b60

1 Parent(s): f551f2b

Update vocab

Browse files

Files changed (3) hide show

added_tokens.json +4 -0
tokenizer.json +0 -18
vocab.json +0 -0

added_tokens.json ADDED Viewed

	@@ -0,0 +1,4 @@

+{
+  "[SEP]": 50265,
+  "[X_SEP]": 50266
+}

tokenizer.json CHANGED Viewed

@@ -47,24 +47,6 @@
       "rstrip": false,
       "normalized": false,
       "special": true
-    },
-    {
-      "id": 50265,
-      "content": "[SEP]",
-      "single_word": false,
-      "lstrip": true,
-      "rstrip": false,
-      "normalized": false,
-      "special": false
-    },
-    {
-      "id": 50266,
-      "content": "[X_SEP]",
-      "single_word": false,
-      "lstrip": true,
-      "rstrip": false,
-      "normalized": false,
-      "special": false
     }
   ],
   "normalizer": null,

       "rstrip": false,
       "normalized": false,
       "special": true
     }
   ],
   "normalizer": null,

vocab.json CHANGED Viewed

The diff for this file is too large to render. See raw diff