Instructions to use AIFunOver/Phi-3.5-mini-instruct-openvino-fp16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AIFunOver/Phi-3.5-mini-instruct-openvino-fp16 with Transformers:

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

pipe = pipeline("text-generation", model="AIFunOver/Phi-3.5-mini-instruct-openvino-fp16", 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("AIFunOver/Phi-3.5-mini-instruct-openvino-fp16", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("AIFunOver/Phi-3.5-mini-instruct-openvino-fp16", trust_remote_code=True, device_map="auto")
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 AIFunOver/Phi-3.5-mini-instruct-openvino-fp16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AIFunOver/Phi-3.5-mini-instruct-openvino-fp16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AIFunOver/Phi-3.5-mini-instruct-openvino-fp16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AIFunOver/Phi-3.5-mini-instruct-openvino-fp16

SGLang

How to use AIFunOver/Phi-3.5-mini-instruct-openvino-fp16 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 "AIFunOver/Phi-3.5-mini-instruct-openvino-fp16" \
    --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": "AIFunOver/Phi-3.5-mini-instruct-openvino-fp16",
		"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 "AIFunOver/Phi-3.5-mini-instruct-openvino-fp16" \
        --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": "AIFunOver/Phi-3.5-mini-instruct-openvino-fp16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AIFunOver/Phi-3.5-mini-instruct-openvino-fp16 with Docker Model Runner:
```
docker model run hf.co/AIFunOver/Phi-3.5-mini-instruct-openvino-fp16
```

Phi-3.5-mini-instruct-openvino-fp16 / openvino_detokenizer.xml

AIFunOver

Upload openvino_detokenizer.xml with huggingface_hub

0dc93f1 verified almost 2 years ago

Raw

History Blame Contribute Delete

9.59 kB

	<?xml version="1.0"?>
	<net name="detokenizer" version="11">
	<layers>
	<layer id="0" name="Parameter_301097" type="Parameter" version="opset1">
	<data shape="?,?" element_type="i64" />
	<output>
	<port id="0" precision="I64" names="Parameter_301097">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="1" name="Convert_301119" type="Convert" version="opset1">
	<data destination_type="i32" />
	<input>
	<port id="0" precision="I64">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	</input>
	<output>
	<port id="1" precision="I32">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="2" name="Constant_301067" type="Const" version="opset1">
	<data element_type="u8" shape="339140" offset="0" size="339140" />
	<output>
	<port id="0" precision="U8">
	<dim>339140</dim>
	</port>
	</output>
	</layer>
	<layer id="3" name="StringTensorUnpack_301068" type="StringTensorUnpack" version="extension">
	<data mode="begins_ends" />
	<input>
	<port id="0" precision="U8">
	<dim>339140</dim>
	</port>
	</input>
	<output>
	<port id="1" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="2" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="3" precision="U8">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="4" name="VocabDecoder_301098" type="VocabDecoder" version="extension">
	<data skip_tokens="0, 1, 32000, 32001, 32002, 32003, 32004, 32005, 32006, 32007, 32008, 32009, 32010" />
	<input>
	<port id="0" precision="I32">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	<port id="1" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="2" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="3" precision="U8">
	<dim>-1</dim>
	</port>
	</input>
	<output>
	<port id="4" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="5" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="6" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="7" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="8" precision="U8">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="5" name="Constant_301100" type="Const" version="opset1">
	<data element_type="u8" shape="3" offset="339140" size="3" />
	<output>
	<port id="0" precision="U8">
	<dim>3</dim>
	</port>
	</output>
	</layer>
	<layer id="6" name="Constant_301102" type="Const" version="opset1">
	<data element_type="u8" shape="1" offset="339143" size="1" />
	<output>
	<port id="0" precision="U8">
	<dim>1</dim>
	</port>
	</output>
	</layer>
	<layer id="7" name="RegexNormalization_301103" type="RegexNormalization" version="extension">
	<data global_replace="true" />
	<input>
	<port id="0" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="1" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="2" precision="U8">
	<dim>-1</dim>
	</port>
	<port id="3" precision="U8">
	<dim>3</dim>
	</port>
	<port id="4" precision="U8">
	<dim>1</dim>
	</port>
	</input>
	<output>
	<port id="5" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="6" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="7" precision="U8">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="8" name="ByteFallback_301104" type="ByteFallback" version="extension">
	<input>
	<port id="0" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="1" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="2" precision="U8">
	<dim>-1</dim>
	</port>
	</input>
	<output>
	<port id="3" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="4" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="5" precision="U8">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="9" name="FuzeRagged_301105" type="FuzeRagged" version="extension">
	<input>
	<port id="0" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="1" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="2" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="3" precision="I32">
	<dim>-1</dim>
	</port>
	</input>
	<output>
	<port id="4" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="5" precision="I32">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="10" name="Constant_301107" type="Const" version="opset1">
	<data element_type="u8" shape="2" offset="339144" size="2" />
	<output>
	<port id="0" precision="U8">
	<dim>2</dim>
	</port>
	</output>
	</layer>
	<layer id="11" name="Constant_301109" type="Const" version="opset1">
	<data element_type="u8" shape="0" offset="339146" size="1" />
	<output>
	<port id="0" precision="U8">
	<dim>0</dim>
	</port>
	</output>
	</layer>
	<layer id="12" name="RegexNormalization_301110" type="RegexNormalization" version="extension">
	<data global_replace="true" />
	<input>
	<port id="0" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="1" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="2" precision="U8">
	<dim>-1</dim>
	</port>
	<port id="3" precision="U8">
	<dim>2</dim>
	</port>
	<port id="4" precision="U8">
	<dim>0</dim>
	</port>
	</input>
	<output>
	<port id="5" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="6" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="7" precision="U8">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="13" name="StringTensorPack_301111" type="StringTensorPack" version="extension">
	<data mode="begins_ends" />
	<input>
	<port id="0" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="1" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="2" precision="U8">
	<dim>-1</dim>
	</port>
	</input>
	<output>
	<port id="3" precision="STRING" names="string_output">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="14" name="Result_301112" type="Result" version="opset1">
	<input>
	<port id="0" precision="STRING">
	<dim>-1</dim>
	</port>
	</input>
	</layer>
	</layers>
	<edges>
	<edge from-layer="0" from-port="0" to-layer="1" to-port="0" />
	<edge from-layer="1" from-port="1" to-layer="4" to-port="0" />
	<edge from-layer="2" from-port="0" to-layer="3" to-port="0" />
	<edge from-layer="3" from-port="1" to-layer="4" to-port="1" />
	<edge from-layer="3" from-port="2" to-layer="4" to-port="2" />
	<edge from-layer="3" from-port="3" to-layer="4" to-port="3" />
	<edge from-layer="4" from-port="6" to-layer="7" to-port="0" />
	<edge from-layer="4" from-port="7" to-layer="7" to-port="1" />
	<edge from-layer="4" from-port="8" to-layer="7" to-port="2" />
	<edge from-layer="4" from-port="5" to-layer="9" to-port="1" />
	<edge from-layer="4" from-port="4" to-layer="9" to-port="0" />
	<edge from-layer="5" from-port="0" to-layer="7" to-port="3" />
	<edge from-layer="6" from-port="0" to-layer="7" to-port="4" />
	<edge from-layer="7" from-port="7" to-layer="8" to-port="2" />
	<edge from-layer="7" from-port="6" to-layer="8" to-port="1" />
	<edge from-layer="7" from-port="5" to-layer="8" to-port="0" />
	<edge from-layer="8" from-port="3" to-layer="9" to-port="2" />
	<edge from-layer="8" from-port="4" to-layer="9" to-port="3" />
	<edge from-layer="8" from-port="5" to-layer="12" to-port="2" />
	<edge from-layer="9" from-port="4" to-layer="12" to-port="0" />
	<edge from-layer="9" from-port="5" to-layer="12" to-port="1" />
	<edge from-layer="10" from-port="0" to-layer="12" to-port="3" />
	<edge from-layer="11" from-port="0" to-layer="12" to-port="4" />
	<edge from-layer="12" from-port="5" to-layer="13" to-port="0" />
	<edge from-layer="12" from-port="6" to-layer="13" to-port="1" />
	<edge from-layer="12" from-port="7" to-layer="13" to-port="2" />
	<edge from-layer="13" from-port="3" to-layer="14" to-port="0" />
	</edges>
	<rt_info>
	<add_attention_mask value="True" />
	<add_prefix_space />
	<add_special_tokens value="True" />
	<bos_token_id value="1" />
	<chat_template value="{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<\|system\|> ' + message['content'] + '<\|end\|> '}}{% elif message['role'] == 'user' %}{{'<\|user\|> ' + message['content'] + '<\|end\|> '}}{% elif message['role'] == 'assistant' %}{{'<\|assistant\|> ' + message['content'] + '<\|end\|> '}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<\|assistant\|> ' }}{% else %}{{ eos_token }}{% endif %}" />
	<clean_up_tokenization_spaces />
	<detokenizer_input_type value="i64" />
	<eos_token_id value="32000" />
	<handle_special_tokens_with_re />
	<number_of_inputs value="1" />
	<openvino_tokenizers_version value="2024.5.0.0.dev20241030" />
	<openvino_version value="2024.5.0.dev20241030" />
	<original_tokenizer_class value="<class 'transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast'>" />
	<pad_token_id value="32000" />
	<sentencepiece_version value="0.2.0" />
	<skip_special_tokens value="True" />
	<streaming_detokenizer value="False" />
	<tiktoken_version value="0.8.0" />
	<tokenizer_output_type value="i64" />
	<tokenizers_version value="0.20.1" />
	<transformers_version value="4.45.2" />
	<use_max_padding value="False" />
	<use_sentencepiece_backend value="False" />
	<utf8_replace_mode />
	<with_detokenizer value="True" />
	</rt_info>
	</net>