Instructions to use DocDuck/microsoft_WizardLM-2-7B-ChatVllm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DocDuck/microsoft_WizardLM-2-7B-ChatVllm with Transformers:

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

pipe = pipeline("text-generation", model="DocDuck/microsoft_WizardLM-2-7B-ChatVllm")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DocDuck/microsoft_WizardLM-2-7B-ChatVllm")
model = AutoModelForCausalLM.from_pretrained("DocDuck/microsoft_WizardLM-2-7B-ChatVllm")
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

vLLM

How to use DocDuck/microsoft_WizardLM-2-7B-ChatVllm with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DocDuck/microsoft_WizardLM-2-7B-ChatVllm"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DocDuck/microsoft_WizardLM-2-7B-ChatVllm",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DocDuck/microsoft_WizardLM-2-7B-ChatVllm

SGLang

How to use DocDuck/microsoft_WizardLM-2-7B-ChatVllm 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 "DocDuck/microsoft_WizardLM-2-7B-ChatVllm" \
    --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": "DocDuck/microsoft_WizardLM-2-7B-ChatVllm",
		"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 "DocDuck/microsoft_WizardLM-2-7B-ChatVllm" \
        --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": "DocDuck/microsoft_WizardLM-2-7B-ChatVllm",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DocDuck/microsoft_WizardLM-2-7B-ChatVllm with Docker Model Runner:
```
docker model run hf.co/DocDuck/microsoft_WizardLM-2-7B-ChatVllm
```

DocDuck commited on Apr 16, 2024

Commit

d763057

verified ·

1 Parent(s): 7d0e7ef

Update tokenizer_config.json

Browse files

Files changed (1) hide show

tokenizer_config.json +1 -1

tokenizer_config.json CHANGED Viewed

@@ -29,7 +29,7 @@
   },
   "additional_special_tokens": [],
   "bos_token": "<s>",
-  "chat_template": "{{ bos_token + (messages[0]['content'].strip() + '\n\n' if messages[0]['role'] == 'system' else '') }}{% for message in (messages[1:] if messages[0]['role'] == 'system' else messages) %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ 'USER: ' + message['content'].strip() + '\n' }}{% elif message['role'] == 'assistant' %}{{ 'ASSISTANT: ' + message['content'].strip() + eos_token + '\n' }}{% endif %}{% if loop.last and message['role'] == 'user' and add_generation_prompt %}{{ 'ASSISTANT:' }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": true,

   },
   "additional_special_tokens": [],
   "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{{ messages[0]['content'].strip() }}{% else %}{% set loop_messages = messages %}{{ 'A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user\\'s questions.' }}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{% if message['role'] == 'system' or message['role'] == 'user' %}{{ ' USER: ' + message['content'].strip() }}{% else %}{{ ' ASSISTANT: ' + message['content'].strip() + eos_token }}{% endif %}{% else %}{% if message['role'] == 'system' or message['role'] == 'user' %}{{ '\nUSER: ' + message['content'].strip() }}{% else %}{{ ' ASSISTANT: ' + message['content'].strip() + eos_token }}{% endif %}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ ' ASSISTANT:' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": true,