Instructions to use llmware/slim-q-gen-tiny-ov with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llmware/slim-q-gen-tiny-ov with Transformers:

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

pipe = pipeline("text-generation", model="llmware/slim-q-gen-tiny-ov")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("llmware/slim-q-gen-tiny-ov")
model = AutoModelForCausalLM.from_pretrained("llmware/slim-q-gen-tiny-ov")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use llmware/slim-q-gen-tiny-ov with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/llmware/slim-q-gen-tiny-ov

SGLang

How to use llmware/slim-q-gen-tiny-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/slim-q-gen-tiny-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": "llmware/slim-q-gen-tiny-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 "llmware/slim-q-gen-tiny-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": "llmware/slim-q-gen-tiny-ov",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use llmware/slim-q-gen-tiny-ov with Docker Model Runner:
```
docker model run hf.co/llmware/slim-q-gen-tiny-ov
```

slim-q-gen-tiny-ov / openvino_tokenizer.xml

doberst

Upload 11 files

641360e verified almost 2 years ago

raw

history blame contribute delete

6.65 kB

	<?xml version="1.0"?>
	<net name="tokenizer" version="11">
	<layers>
	<layer id="0" name="string_input" type="Parameter" version="opset1">
	<data shape="?" element_type="string" />
	<output>
	<port id="0" precision="STRING" names="string_input">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="1" name="Constant_159866" type="Const" version="opset1">
	<data element_type="i32" shape="" offset="0" size="4" />
	<output>
	<port id="0" precision="I32" />
	</output>
	</layer>
	<layer id="2" name="Constant_159859" type="Const" version="opset1">
	<data element_type="u8" shape="499723" offset="4" size="499723" />
	<output>
	<port id="0" precision="U8">
	<dim>499723</dim>
	</port>
	</output>
	</layer>
	<layer id="3" name="SentencepieceTokenizer_159862" type="SentencepieceTokenizer" version="extension">
	<data nbest_size="0" alpha="0" add_bos="true" add_eos="false" reverse="false" />
	<input>
	<port id="0" precision="U8">
	<dim>499723</dim>
	</port>
	<port id="1" precision="STRING">
	<dim>-1</dim>
	</port>
	</input>
	<output>
	<port id="2" precision="I64">
	<dim>-1</dim>
	<dim>2</dim>
	</port>
	<port id="3" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="4" precision="I64">
	<dim>2</dim>
	</port>
	</output>
	</layer>
	<layer id="4" name="Broadcast_159867" type="Broadcast" version="opset3">
	<data mode="numpy" />
	<input>
	<port id="0" precision="I32" />
	<port id="1" precision="I64">
	<dim>2</dim>
	</port>
	</input>
	<output>
	<port id="2" precision="I32">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="5" name="Constant_159868" type="Const" version="opset1">
	<data element_type="i32" shape="" offset="499727" size="4" />
	<output>
	<port id="0" precision="I32" />
	</output>
	</layer>
	<layer id="6" name="ShapeOf_159869" 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="7" name="Broadcast_159870" type="Broadcast" version="opset3">
	<data mode="numpy" />
	<input>
	<port id="0" precision="I32" />
	<port id="1" precision="I64">
	<dim>1</dim>
	</port>
	</input>
	<output>
	<port id="2" precision="I32">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="8" name="ScatterNDUpdate_159874" type="ScatterNDUpdate" version="opset4">
	<input>
	<port id="0" precision="I32">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	<port id="1" precision="I64">
	<dim>-1</dim>
	<dim>2</dim>
	</port>
	<port id="2" precision="I32">
	<dim>-1</dim>
	</port>
	</input>
	<output>
	<port id="3" precision="I32">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="9" name="ScatterNDUpdate_159874" 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="11" name="Constant_159863" type="Const" version="opset1">
	<data element_type="i32" shape="" offset="0" size="4" />
	<output>
	<port id="0" precision="I32" />
	</output>
	</layer>
	<layer id="12" name="Broadcast_159864" type="Broadcast" version="opset3">
	<data mode="numpy" />
	<input>
	<port id="0" precision="I32" />
	<port id="1" precision="I64">
	<dim>2</dim>
	</port>
	</input>
	<output>
	<port id="2" precision="I32">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="13" name="ScatterNDUpdate_159865" type="ScatterNDUpdate" version="opset4">
	<input>
	<port id="0" precision="I32">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	<port id="1" precision="I64">
	<dim>-1</dim>
	<dim>2</dim>
	</port>
	<port id="2" precision="I32">
	<dim>-1</dim>
	</port>
	</input>
	<output>
	<port id="3" precision="I32">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="14" name="ScatterNDUpdate_159865" 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="15" name="Result_159875" type="Result" version="opset1">
	<input>
	<port id="0" precision="I64">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	</input>
	</layer>
	<layer id="10" name="Result_159876" 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="3" to-port="1" />
	<edge from-layer="1" from-port="0" 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="4" to-layer="4" to-port="1" />
	<edge from-layer="3" from-port="3" to-layer="6" to-port="0" />
	<edge from-layer="3" from-port="2" to-layer="8" to-port="1" />
	<edge from-layer="3" from-port="4" to-layer="12" to-port="1" />
	<edge from-layer="3" from-port="2" to-layer="13" to-port="1" />
	<edge from-layer="3" from-port="3" to-layer="13" to-port="2" />
	<edge from-layer="4" from-port="2" to-layer="8" to-port="0" />
	<edge from-layer="5" from-port="0" to-layer="7" to-port="0" />
	<edge from-layer="6" from-port="1" to-layer="7" to-port="1" />
	<edge from-layer="7" from-port="2" to-layer="8" to-port="2" />
	<edge from-layer="8" from-port="3" to-layer="9" to-port="0" />
	<edge from-layer="9" from-port="1" to-layer="10" to-port="0" />
	<edge from-layer="11" from-port="0" to-layer="12" to-port="0" />
	<edge from-layer="12" from-port="2" to-layer="13" to-port="0" />
	<edge from-layer="13" from-port="3" to-layer="14" to-port="0" />
	<edge from-layer="14" from-port="1" to-layer="15" to-port="0" />
	</edges>
	<rt_info>
	<eos_token_id value="2" />
	</rt_info>
	</net>