Instructions to use AlexKoff88/Phi-3.5-mini-instruct-openvino-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AlexKoff88/Phi-3.5-mini-instruct-openvino-8bit with Transformers:

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

pipe = pipeline("text-generation", model="AlexKoff88/Phi-3.5-mini-instruct-openvino-8bit", 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("AlexKoff88/Phi-3.5-mini-instruct-openvino-8bit", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("AlexKoff88/Phi-3.5-mini-instruct-openvino-8bit", 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 AlexKoff88/Phi-3.5-mini-instruct-openvino-8bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AlexKoff88/Phi-3.5-mini-instruct-openvino-8bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AlexKoff88/Phi-3.5-mini-instruct-openvino-8bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AlexKoff88/Phi-3.5-mini-instruct-openvino-8bit

SGLang

How to use AlexKoff88/Phi-3.5-mini-instruct-openvino-8bit 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 "AlexKoff88/Phi-3.5-mini-instruct-openvino-8bit" \
    --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": "AlexKoff88/Phi-3.5-mini-instruct-openvino-8bit",
		"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 "AlexKoff88/Phi-3.5-mini-instruct-openvino-8bit" \
        --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": "AlexKoff88/Phi-3.5-mini-instruct-openvino-8bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AlexKoff88/Phi-3.5-mini-instruct-openvino-8bit with Docker Model Runner:
```
docker model run hf.co/AlexKoff88/Phi-3.5-mini-instruct-openvino-8bit
```

Phi-3.5-mini-instruct-openvino-8bit / openvino_tokenizer.xml

AlexKoff88

Upload openvino_tokenizer.xml with huggingface_hub

245602b verified almost 2 years ago

Raw

History Blame Contribute Delete

24.3 kB

	<?xml version="1.0"?>
	<net name="tokenizer" version="11">
	<layers>
	<layer id="0" name="Parameter_139828" type="Parameter" version="opset1">
	<data shape="?" element_type="string" />
	<output>
	<port id="0" precision="STRING" names="Parameter_139828">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="1" name="Constant_139834" type="Const" version="opset1">
	<data element_type="i64" shape="" offset="0" size="8" />
	<output>
	<port id="0" precision="I64" />
	</output>
	</layer>
	<layer id="2" name="StringTensorUnpack_139829" type="StringTensorUnpack" version="extension">
	<data mode="begins_ends" />
	<input>
	<port id="0" precision="STRING">
	<dim>-1</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="3" name="ShapeOf_139830" type="ShapeOf" version="opset3">
	<data output_type="i64" />
	<input>
	<port id="0" precision="I32">
	<dim>-1</dim>
	</port>
	</input>
	<output>
	<port id="1" precision="I64">
	<dim>1</dim>
	</port>
	</output>
	</layer>
	<layer id="4" name="Constant_139831" type="Const" version="opset1">
	<data element_type="i64" shape="" offset="0" size="8" />
	<output>
	<port id="0" precision="I64" />
	</output>
	</layer>
	<layer id="5" name="Constant_139832" type="Const" version="opset1">
	<data element_type="i64" shape="" offset="0" size="8" />
	<output>
	<port id="0" precision="I64" />
	</output>
	</layer>
	<layer id="6" name="Gather_139833" type="Gather" version="opset8">
	<data batch_dims="0" />
	<input>
	<port id="0" precision="I64">
	<dim>1</dim>
	</port>
	<port id="1" precision="I64" />
	<port id="2" precision="I64" />
	</input>
	<output>
	<port id="3" precision="I64" />
	</output>
	</layer>
	<layer id="7" name="Constant_139835" type="Const" version="opset1">
	<data element_type="i64" shape="" offset="8" size="8" />
	<output>
	<port id="0" precision="I64" />
	</output>
	</layer>
	<layer id="8" name="Range_139836" type="Range" version="opset4">
	<data output_type="i32" />
	<input>
	<port id="0" precision="I64" />
	<port id="1" precision="I64" />
	<port id="2" precision="I64" />
	</input>
	<output>
	<port id="3" precision="I32">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="9" name="Constant_139837" type="Const" version="opset1">
	<data element_type="i64" shape="" offset="8" size="8" />
	<output>
	<port id="0" precision="I64" />
	</output>
	</layer>
	<layer id="10" name="Constant_139838" type="Const" version="opset1">
	<data element_type="i64" shape="" offset="8" size="8" />
	<output>
	<port id="0" precision="I64" />
	</output>
	</layer>
	<layer id="11" name="Add_139839" type="Add" version="opset1">
	<data auto_broadcast="numpy" />
	<input>
	<port id="0" precision="I64" />
	<port id="1" precision="I64" />
	</input>
	<output>
	<port id="2" precision="I64" />
	</output>
	</layer>
	<layer id="12" name="Constant_139840" type="Const" version="opset1">
	<data element_type="i64" shape="" offset="8" size="8" />
	<output>
	<port id="0" precision="I64" />
	</output>
	</layer>
	<layer id="13" name="Range_139841" type="Range" version="opset4">
	<data output_type="i32" />
	<input>
	<port id="0" precision="I64" />
	<port id="1" precision="I64" />
	<port id="2" precision="I64" />
	</input>
	<output>
	<port id="3" precision="I32">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="14" name="Constant_139903" type="Const" version="opset1">
	<data element_type="u8" shape="328" offset="16" size="328" />
	<output>
	<port id="0" precision="U8">
	<dim>328</dim>
	</port>
	</output>
	</layer>
	<layer id="15" name="SpecialTokensSplit_139904" type="SpecialTokensSplit" 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>
	<port id="4" precision="U8">
	<dim>-1</dim>
	</port>
	<port id="5" precision="U8">
	<dim>328</dim>
	</port>
	</input>
	<output>
	<port id="6" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="7" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="8" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="9" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="10" precision="U8">
	<dim>-1</dim>
	</port>
	<port id="11" precision="BOOL">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="16" name="Constant_139906" type="Const" version="opset1">
	<data element_type="u8" shape="7" offset="344" size="7" />
	<output>
	<port id="0" precision="U8">
	<dim>7</dim>
	</port>
	</output>
	</layer>
	<layer id="17" name="Constant_139908" type="Const" version="opset1">
	<data element_type="u8" shape="5" offset="351" size="5" />
	<output>
	<port id="0" precision="U8">
	<dim>5</dim>
	</port>
	</output>
	</layer>
	<layer id="18" name="RegexNormalization_139909" 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="BOOL">
	<dim>-1</dim>
	</port>
	<port id="4" precision="U8">
	<dim>7</dim>
	</port>
	<port id="5" precision="U8">
	<dim>5</dim>
	</port>
	</input>
	<output>
	<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>
	<port id="9" precision="BOOL">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="19" name="Constant_139911" type="Const" version="opset1">
	<data element_type="u8" shape="1" offset="356" size="1" />
	<output>
	<port id="0" precision="U8">
	<dim>1</dim>
	</port>
	</output>
	</layer>
	<layer id="20" name="Constant_139913" type="Const" version="opset1">
	<data element_type="u8" shape="3" offset="357" size="3" />
	<output>
	<port id="0" precision="U8">
	<dim>3</dim>
	</port>
	</output>
	</layer>
	<layer id="21" name="RegexNormalization_139914" 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="BOOL">
	<dim>-1</dim>
	</port>
	<port id="4" precision="U8">
	<dim>1</dim>
	</port>
	<port id="5" precision="U8">
	<dim>3</dim>
	</port>
	</input>
	<output>
	<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>
	<port id="9" precision="BOOL">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="22" name="Constant_139916" type="Const" version="opset1">
	<data element_type="u8" shape="339140" offset="360" size="339140" />
	<output>
	<port id="0" precision="U8">
	<dim>339140</dim>
	</port>
	</output>
	</layer>
	<layer id="23" name="StringTensorUnpack_139917" 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="24" name="Constant_139922" type="Const" version="opset1">
	<data element_type="u8" shape="499127" offset="339500" size="499127" />
	<output>
	<port id="0" precision="U8">
	<dim>499127</dim>
	</port>
	</output>
	</layer>
	<layer id="25" name="StringTensorUnpack_139923" type="StringTensorUnpack" version="extension">
	<data mode="begins_ends" />
	<input>
	<port id="0" precision="U8">
	<dim>499127</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="26" name="Constant_139925" type="Const" version="opset1">
	<data element_type="u8" shape="412810" offset="838627" size="412810" />
	<output>
	<port id="0" precision="U8">
	<dim>412810</dim>
	</port>
	</output>
	</layer>
	<layer id="27" name="StringTensorUnpack_139926" type="StringTensorUnpack" version="extension">
	<data mode="begins_ends" />
	<input>
	<port id="0" precision="U8">
	<dim>412810</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="28" name="Constant_139919" type="Const" version="opset1">
	<data element_type="u8" shape="8716" offset="1251437" size="8716" />
	<output>
	<port id="0" precision="U8">
	<dim>8716</dim>
	</port>
	</output>
	</layer>
	<layer id="29" name="StringTensorUnpack_139920" type="StringTensorUnpack" version="extension">
	<data mode="begins_ends" />
	<input>
	<port id="0" precision="U8">
	<dim>8716</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="30" name="Constant_139927" type="Const" version="opset1">
	<data element_type="i32" shape="475" offset="1260153" size="1900" />
	<output>
	<port id="0" precision="I32">
	<dim>475</dim>
	</port>
	</output>
	</layer>
	<layer id="31" name="BPETokenizer_139928" type="BPETokenizer" version="extension">
	<data unk_token="<unk>" fuse_unk="true" suffix_indicator="" end_suffix="" byte_fallback="true" cache_capacity="20000" />
	<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>
	<port id="4" precision="U8">
	<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="U8">
	<dim>-1</dim>
	</port>
	<port id="8" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="9" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="10" precision="U8">
	<dim>-1</dim>
	</port>
	<port id="11" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="12" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="13" precision="U8">
	<dim>-1</dim>
	</port>
	<port id="14" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="15" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="16" precision="U8">
	<dim>-1</dim>
	</port>
	<port id="17" precision="I32">
	<dim>475</dim>
	</port>
	</input>
	<output>
	<port id="18" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="19" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="20" precision="I32">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="32" name="Subtract_139929" type="Subtract" version="opset1">
	<data auto_broadcast="numpy" />
	<input>
	<port id="0" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="1" precision="I32">
	<dim>-1</dim>
	</port>
	</input>
	<output>
	<port id="2" precision="I32">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="33" name="Constant_139930" type="Const" version="opset1">
	<data element_type="i32" shape="" offset="1262053" size="4" />
	<output>
	<port id="0" precision="I32" />
	</output>
	</layer>
	<layer id="34" name="Minimum_139931" type="Minimum" version="opset1">
	<data auto_broadcast="numpy" />
	<input>
	<port id="0" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="1" precision="I32" />
	</input>
	<output>
	<port id="2" precision="I32">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="35" name="Add_139932" type="Add" version="opset1">
	<data auto_broadcast="numpy" />
	<input>
	<port id="0" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="1" precision="I32">
	<dim>-1</dim>
	</port>
	</input>
	<output>
	<port id="2" precision="I32">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="36" name="Constant_139933" type="Const" version="opset1">
	<data element_type="i32" shape="1" offset="1262057" size="4" />
	<output>
	<port id="0" precision="I32">
	<dim>1</dim>
	</port>
	</output>
	</layer>
	<layer id="37" name="CombineSegments_139934" type="CombineSegments" 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>
	<port id="6" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="7" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="8" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="9" precision="I32">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="38" name="Subtract_139935" type="Subtract" version="opset1">
	<data auto_broadcast="numpy" />
	<input>
	<port id="0" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="1" precision="I32">
	<dim>-1</dim>
	</port>
	</input>
	<output>
	<port id="2" precision="I32">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="39" name="Constant_139936" type="Const" version="opset1">
	<data element_type="i32" shape="" offset="1262057" size="4" />
	<output>
	<port id="0" precision="I32" />
	</output>
	</layer>
	<layer id="40" name="ReduceMax_139937" type="ReduceMax" version="opset1">
	<data keep_dims="false" />
	<input>
	<port id="0" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="1" precision="I32" />
	</input>
	<output>
	<port id="2" precision="I32" />
	</output>
	</layer>
	<layer id="41" name="Constant_139938" type="Const" version="opset1">
	<data element_type="i32" shape="" offset="1262061" size="4" />
	<output>
	<port id="0" precision="I32" />
	</output>
	</layer>
	<layer id="42" name="RaggedToDense_139939" type="RaggedToDense" version="extension">
	<data pad_right="false" />
	<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" />
	<port id="4" precision="I32" />
	</input>
	<output>
	<port id="5" precision="I32">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	<port id="6" precision="BOOL">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="43" name="Convert_139940" type="Convert" version="opset1">
	<data destination_type="i32" />
	<input>
	<port id="0" precision="BOOL">
	<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="44" name="Convert_139940" type="Convert" version="opset1">
	<data destination_type="i64" />
	<input>
	<port id="0" precision="I32">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	</input>
	<output>
	<port id="1" precision="I64" names="attention_mask">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="46" name="RaggedToDense_139939.0" type="Convert" version="opset1">
	<data destination_type="i64" />
	<input>
	<port id="0" precision="I32">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	</input>
	<output>
	<port id="1" precision="I64" names="input_ids">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="47" name="Result_139943" type="Result" version="opset1">
	<input>
	<port id="0" precision="I64">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	</input>
	</layer>
	<layer id="45" name="Result_139945" type="Result" version="opset1">
	<input>
	<port id="0" precision="I64">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	</input>
	</layer>
	</layers>
	<edges>
	<edge from-layer="0" from-port="0" to-layer="2" to-port="0" />
	<edge from-layer="1" from-port="0" to-layer="8" to-port="0" />
	<edge from-layer="2" from-port="1" to-layer="3" to-port="0" />
	<edge from-layer="2" from-port="3" to-layer="15" to-port="4" />
	<edge from-layer="2" from-port="2" to-layer="15" to-port="3" />
	<edge from-layer="2" from-port="1" to-layer="15" to-port="2" />
	<edge from-layer="3" from-port="1" to-layer="6" to-port="0" />
	<edge from-layer="4" from-port="0" to-layer="6" to-port="1" />
	<edge from-layer="5" from-port="0" to-layer="6" to-port="2" />
	<edge from-layer="6" from-port="3" to-layer="8" to-port="1" />
	<edge from-layer="6" from-port="3" to-layer="11" to-port="0" />
	<edge from-layer="7" from-port="0" to-layer="8" to-port="2" />
	<edge from-layer="8" from-port="3" to-layer="15" to-port="0" />
	<edge from-layer="9" from-port="0" to-layer="13" to-port="0" />
	<edge from-layer="10" from-port="0" to-layer="11" to-port="1" />
	<edge from-layer="11" from-port="2" to-layer="13" to-port="1" />
	<edge from-layer="12" from-port="0" to-layer="13" to-port="2" />
	<edge from-layer="13" from-port="3" to-layer="15" to-port="1" />
	<edge from-layer="14" from-port="0" to-layer="15" to-port="5" />
	<edge from-layer="15" from-port="9" to-layer="18" to-port="1" />
	<edge from-layer="15" from-port="6" to-layer="31" to-port="0" />
	<edge from-layer="15" from-port="7" to-layer="31" to-port="1" />
	<edge from-layer="15" from-port="11" to-layer="18" to-port="3" />
	<edge from-layer="15" from-port="10" to-layer="18" to-port="2" />
	<edge from-layer="15" from-port="8" to-layer="18" to-port="0" />
	<edge from-layer="16" from-port="0" to-layer="18" to-port="4" />
	<edge from-layer="17" from-port="0" to-layer="18" to-port="5" />
	<edge from-layer="18" from-port="6" to-layer="21" to-port="0" />
	<edge from-layer="18" from-port="7" to-layer="21" to-port="1" />
	<edge from-layer="18" from-port="8" to-layer="21" to-port="2" />
	<edge from-layer="18" from-port="9" to-layer="21" to-port="3" />
	<edge from-layer="19" from-port="0" to-layer="21" to-port="4" />
	<edge from-layer="20" from-port="0" to-layer="21" to-port="5" />
	<edge from-layer="21" from-port="8" to-layer="31" to-port="4" />
	<edge from-layer="21" from-port="7" to-layer="31" to-port="3" />
	<edge from-layer="21" from-port="6" to-layer="31" to-port="2" />
	<edge from-layer="22" from-port="0" to-layer="23" to-port="0" />
	<edge from-layer="23" from-port="1" to-layer="31" to-port="5" />
	<edge from-layer="23" from-port="2" to-layer="31" to-port="6" />
	<edge from-layer="23" from-port="3" to-layer="31" to-port="7" />
	<edge from-layer="24" from-port="0" to-layer="25" to-port="0" />
	<edge from-layer="25" from-port="1" to-layer="31" to-port="8" />
	<edge from-layer="25" from-port="2" to-layer="31" to-port="9" />
	<edge from-layer="25" from-port="3" to-layer="31" to-port="10" />
	<edge from-layer="26" from-port="0" to-layer="27" to-port="0" />
	<edge from-layer="27" from-port="3" to-layer="31" to-port="13" />
	<edge from-layer="27" from-port="2" to-layer="31" to-port="12" />
	<edge from-layer="27" from-port="1" to-layer="31" to-port="11" />
	<edge from-layer="28" from-port="0" to-layer="29" to-port="0" />
	<edge from-layer="29" from-port="1" to-layer="31" to-port="14" />
	<edge from-layer="29" from-port="2" to-layer="31" to-port="15" />
	<edge from-layer="29" from-port="3" to-layer="31" to-port="16" />
	<edge from-layer="30" from-port="0" to-layer="31" to-port="17" />
	<edge from-layer="31" from-port="19" to-layer="32" to-port="0" />
	<edge from-layer="31" from-port="18" to-layer="32" to-port="1" />
	<edge from-layer="31" from-port="18" to-layer="35" to-port="0" />
	<edge from-layer="31" from-port="20" to-layer="37" to-port="2" />
	<edge from-layer="31" from-port="18" to-layer="37" to-port="0" />
	<edge from-layer="32" from-port="2" to-layer="34" to-port="0" />
	<edge from-layer="33" from-port="0" to-layer="34" to-port="1" />
	<edge from-layer="34" from-port="2" to-layer="35" to-port="1" />
	<edge from-layer="35" from-port="2" to-layer="37" to-port="1" />
	<edge from-layer="36" from-port="0" to-layer="37" to-port="3" />
	<edge from-layer="37" from-port="5" to-layer="42" to-port="1" />
	<edge from-layer="37" from-port="6" to-layer="42" to-port="2" />
	<edge from-layer="37" from-port="4" to-layer="42" to-port="0" />
	<edge from-layer="37" from-port="4" to-layer="38" to-port="1" />
	<edge from-layer="37" from-port="5" to-layer="38" to-port="0" />
	<edge from-layer="38" from-port="2" to-layer="40" to-port="0" />
	<edge from-layer="39" from-port="0" to-layer="40" to-port="1" />
	<edge from-layer="40" from-port="2" to-layer="42" to-port="3" />
	<edge from-layer="41" from-port="0" to-layer="42" to-port="4" />
	<edge from-layer="42" from-port="6" to-layer="43" to-port="0" />
	<edge from-layer="42" from-port="5" to-layer="46" to-port="0" />
	<edge from-layer="43" from-port="1" to-layer="44" to-port="0" />
	<edge from-layer="44" from-port="1" to-layer="45" to-port="0" />
	<edge from-layer="46" from-port="1" to-layer="47" 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>