Instructions to use llmware/phi-3-ov with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llmware/phi-3-ov with Transformers:

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

pipe = pipeline("text-generation", model="llmware/phi-3-ov", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("llmware/phi-3-ov", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("llmware/phi-3-ov", trust_remote_code=True)
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 llmware/phi-3-ov with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "llmware/phi-3-ov"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "llmware/phi-3-ov",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/llmware/phi-3-ov

SGLang

How to use llmware/phi-3-ov 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 "llmware/phi-3-ov" \
    --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": "llmware/phi-3-ov",
		"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 "llmware/phi-3-ov" \
        --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": "llmware/phi-3-ov",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use llmware/phi-3-ov with Docker Model Runner:
```
docker model run hf.co/llmware/phi-3-ov
```

doberst commited on Aug 30, 2024

Commit

9652ec8

verified ·

1 Parent(s): 6d51e84

Update config.json

Browse files

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -36,7 +36,7 @@
   "prompt_format": "<|user|>\n{context_passage}\n{question}\n<|end|>\n<|assistant|>",
   "prompt_format_dict": {"system_start": "<|system|>\n", "system_stop": "<|end|>\n", "main_start": "<|user|>\n", "main_stop": "<|end|>\n", "start_llm_response": "<|assistant|>"},
   "tokenizer_local": "tokenizer_phi3.json",
-  "tokenizer_config": {"bos_id": [1], "bos_token": ["<s>"], "eos_id": [32000,32001,32007], "eos_token": ["<|endoftext|>","<|assistant|>","<|end|>"},
   "model_parent": "microsoft/Phi-3-mini-4k-instruct",
   "description": "Microsoft Phi-3-mini - 3.8 parameter base",
   "quantization": "int4",

   "prompt_format": "<|user|>\n{context_passage}\n{question}\n<|end|>\n<|assistant|>",
   "prompt_format_dict": {"system_start": "<|system|>\n", "system_stop": "<|end|>\n", "main_start": "<|user|>\n", "main_stop": "<|end|>\n", "start_llm_response": "<|assistant|>"},
   "tokenizer_local": "tokenizer_phi3.json",
+  "tokenizer_config": {"bos_id": [1], "bos_token": ["<s>"], "eos_id": [32000,32001,32007], "eos_token": ["<|endoftext|>","<|assistant|>","<|end|>"]},
   "model_parent": "microsoft/Phi-3-mini-4k-instruct",
   "description": "Microsoft Phi-3-mini - 3.8 parameter base",
   "quantization": "int4",