Instructions to use tzchen07/SG_X9e with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tzchen07/SG_X9e with Transformers:

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

pipe = pipeline("text-generation", model="tzchen07/SG_X9e")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("tzchen07/SG_X9e")
model = AutoModelForMultimodalLM.from_pretrained("tzchen07/SG_X9e")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tzchen07/SG_X9e with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tzchen07/SG_X9e"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tzchen07/SG_X9e",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tzchen07/SG_X9e

SGLang

How to use tzchen07/SG_X9e 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 "tzchen07/SG_X9e" \
    --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": "tzchen07/SG_X9e",
		"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 "tzchen07/SG_X9e" \
        --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": "tzchen07/SG_X9e",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tzchen07/SG_X9e with Docker Model Runner:
```
docker model run hf.co/tzchen07/SG_X9e
```

tzchen07 commited on 12 days ago

Commit

d80eec0

verified ·

1 Parent(s): 66a44c0

Upload chat_template.jinja with huggingface_hub

Browse files

Files changed (1) hide show

chat_template.jinja +29 -0

chat_template.jinja ADDED Viewed

	@@ -0,0 +1,29 @@

+{%- if not guideline and messages[0].role == "system" %}
+    {%- set guideline = messages[0].content %}
+    {%- set messages = messages[1:] %}
+{%- endif %}
+{{- bos_token }}
+{%- if messages[-1].role == 'user' %}
+    {{- "You are a policy expert trying to help determine whether a user prompt is in violation of the defined safety policies.\n\n" }}
+    {{- "<start_of_turn>\n" }}
+    {{- "Human Question: " + messages[-1].content }}
+    {{- "\n<end_of_turn>\n\n" }}
+    {{- "Our safety principle is defined in the below:\n\n" }}
+    {{- "* " + guideline + "\n" }}
+    {{- "\n===\n\n" }}
+    {{- "Does the human question violate the above principle? Your answer must start with 'Yes' or 'No'. And then walk through step by step to be sure we answer correctly.\n\n" }}
+{%- else %}
+    {{- "You are a policy expert trying to help determine whether an AI response to a prompt is in violation of the defined safety policies.\n\n" }}
+    {{- "<start_of_turn>\n" }}
+    {{- "Human Question: " + messages[-2].content }}
+    {{- "\n<end_of_turn>\n" }}
+    {{- "<start_of_turn>\n" }}
+    {{- "Chatbot Response: " + messages[-1].content }}
+    {{- "\n<end_of_turn>\n\n" }}
+    {{- "Our safety principle is defined in the below:\n\n" }}
+    {{- "* " + guideline + "\n" }}
+    {{- "\n===\n\n" }}
+    {{- "Does the Chatbot Response violate the above principle? Your answer must  start with 'Yes' or 'No'. And then walk through step by step to be sure we answer correctly.\n\n" }}
+{%- endif %}