Instructions to use OpenVINO/persimmon-8b-chat-int4-ov with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenVINO/persimmon-8b-chat-int4-ov with Transformers:

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

pipe = pipeline("text-generation", model="OpenVINO/persimmon-8b-chat-int4-ov")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OpenVINO/persimmon-8b-chat-int4-ov")
model = AutoModelForCausalLM.from_pretrained("OpenVINO/persimmon-8b-chat-int4-ov", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OpenVINO/persimmon-8b-chat-int4-ov with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenVINO/persimmon-8b-chat-int4-ov"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenVINO/persimmon-8b-chat-int4-ov",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OpenVINO/persimmon-8b-chat-int4-ov

SGLang

How to use OpenVINO/persimmon-8b-chat-int4-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 "OpenVINO/persimmon-8b-chat-int4-ov" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenVINO/persimmon-8b-chat-int4-ov",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "OpenVINO/persimmon-8b-chat-int4-ov" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenVINO/persimmon-8b-chat-int4-ov",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OpenVINO/persimmon-8b-chat-int4-ov with Docker Model Runner:
```
docker model run hf.co/OpenVINO/persimmon-8b-chat-int4-ov
```

persimmon-8b-chat-int4-ov / openvino_detokenizer.xml

openvino-ci

Upload folder using huggingface_hub

e7e1495 verified about 2 years ago

Raw

History Blame Contribute Delete

6 kB

	<?xml version="1.0"?>
	<net name="detokenizer" version="11">
	<layers>
	<layer id="0" name="Parameter_330600" type="Parameter" version="opset1">
	<data shape="?,?" element_type="i64" />
	<output>
	<port id="0" precision="I64" names="Parameter_330600">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="1" name="Convert_330616" 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_330498" type="Const" version="opset1">
	<data element_type="u8" shape="558397" offset="0" size="558397" />
	<output>
	<port id="0" precision="U8">
	<dim>558397</dim>
	</port>
	</output>
	</layer>
	<layer id="3" name="StringTensorUnpack_330499" type="StringTensorUnpack" version="extension">
	<data mode="begins_ends" />
	<input>
	<port id="0" precision="U8">
	<dim>558397</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_330601" type="VocabDecoder" version="extension">
	<data skip_tokens="0, 1" />
	<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="CharsToBytes_330602" type="CharsToBytes" 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>
	</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="6" name="Constant_330604" type="Const" version="opset1">
	<data element_type="u8" shape="47" offset="558397" size="47" />
	<output>
	<port id="0" precision="U8">
	<dim>47</dim>
	</port>
	</output>
	</layer>
	<layer id="7" name="Constant_330606" type="Const" version="opset1">
	<data element_type="u8" shape="2" offset="558444" size="2" />
	<output>
	<port id="0" precision="U8">
	<dim>2</dim>
	</port>
	</output>
	</layer>
	<layer id="8" name="RegexNormalization_330607" 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>47</dim>
	</port>
	<port id="4" precision="U8">
	<dim>2</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="9" name="StringTensorPack_330608" 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="10" name="Result_330609" 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="8" to-layer="5" to-port="4" />
	<edge from-layer="4" from-port="7" to-layer="5" to-port="3" />
	<edge from-layer="4" from-port="6" to-layer="5" to-port="2" />
	<edge from-layer="4" from-port="5" to-layer="5" to-port="1" />
	<edge from-layer="4" from-port="4" to-layer="5" to-port="0" />
	<edge from-layer="5" from-port="5" to-layer="8" to-port="0" />
	<edge from-layer="5" from-port="6" to-layer="8" to-port="1" />
	<edge from-layer="5" from-port="7" to-layer="8" to-port="2" />
	<edge from-layer="6" from-port="0" to-layer="8" to-port="3" />
	<edge from-layer="7" from-port="0" to-layer="8" to-port="4" />
	<edge from-layer="8" from-port="5" to-layer="9" to-port="0" />
	<edge from-layer="8" from-port="6" to-layer="9" to-port="1" />
	<edge from-layer="8" from-port="7" to-layer="9" to-port="2" />
	<edge from-layer="9" from-port="3" to-layer="10" to-port="0" />
	</edges>
	<rt_info>
	<eos_token_id value="0" />
	</rt_info>
	</net>