Instructions to use fakezeta/gemma-2-9b-it-ov-int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fakezeta/gemma-2-9b-it-ov-int4 with Transformers:

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

pipe = pipeline("text-generation", model="fakezeta/gemma-2-9b-it-ov-int4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fakezeta/gemma-2-9b-it-ov-int4")
model = AutoModelForCausalLM.from_pretrained("fakezeta/gemma-2-9b-it-ov-int4", 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 fakezeta/gemma-2-9b-it-ov-int4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fakezeta/gemma-2-9b-it-ov-int4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fakezeta/gemma-2-9b-it-ov-int4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fakezeta/gemma-2-9b-it-ov-int4

SGLang

How to use fakezeta/gemma-2-9b-it-ov-int4 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 "fakezeta/gemma-2-9b-it-ov-int4" \
    --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": "fakezeta/gemma-2-9b-it-ov-int4",
		"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 "fakezeta/gemma-2-9b-it-ov-int4" \
        --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": "fakezeta/gemma-2-9b-it-ov-int4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use fakezeta/gemma-2-9b-it-ov-int4 with Docker Model Runner:
```
docker model run hf.co/fakezeta/gemma-2-9b-it-ov-int4
```

gemma-2-9b-it-ov-int4 / openvino_tokenizer.xml

fakezeta

Upload folder using huggingface_hub

5d7a128 verified about 2 years ago

Raw History Blame Contribute Delete

8.76 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_312392" 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_312388" type="Const" version="opset1">
	<data element_type="u8" shape="4241003" offset="4" size="4241003" />
	<output>
	<port id="0" precision="U8">
	<dim>4241003</dim>
	</port>
	</output>
	</layer>
	<layer id="3" name="SentencepieceTokenizer_312391" type="SentencepieceTokenizer" version="extension">
	<data nbest_size="0" alpha="0" add_bos="true" add_eos="false" reverse="true" />
	<input>
	<port id="0" precision="U8">
	<dim>4241003</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_312393" 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_312394" type="Const" version="opset1">
	<data element_type="i32" shape="" offset="4241007" size="4" />
	<output>
	<port id="0" precision="I32" />
	</output>
	</layer>
	<layer id="6" name="ShapeOf_312395" 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_312396" 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_312400" 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="Constant_312404" type="Const" version="opset1">
	<data element_type="i64" shape="1" offset="4241011" size="8" />
	<output>
	<port id="0" precision="I64">
	<dim>1</dim>
	</port>
	</output>
	</layer>
	<layer id="10" name="Reverse_312405" type="Reverse" version="opset1">
	<data mode="index" />
	<input>
	<port id="0" precision="I32">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	<port id="1" precision="I64">
	<dim>1</dim>
	</port>
	</input>
	<output>
	<port id="2" precision="I32">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="11" name="Reverse_312405" 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="13" name="Constant_312401" type="Const" version="opset1">
	<data element_type="i32" shape="" offset="0" size="4" />
	<output>
	<port id="0" precision="I32" />
	</output>
	</layer>
	<layer id="14" name="Broadcast_312402" type="Broadcast" version="opset3">
	<data mode="bidirectional" />
	<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="15" name="ScatterNDUpdate_312403" 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="16" name="Constant_312406" type="Const" version="opset1">
	<data element_type="i64" shape="1" offset="4241011" size="8" />
	<output>
	<port id="0" precision="I64">
	<dim>1</dim>
	</port>
	</output>
	</layer>
	<layer id="17" name="Reverse_312407" type="Reverse" version="opset1">
	<data mode="index" />
	<input>
	<port id="0" precision="I32">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	<port id="1" precision="I64">
	<dim>1</dim>
	</port>
	</input>
	<output>
	<port id="2" precision="I32">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="18" name="Reverse_312407" 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="19" name="Result_312408" type="Result" version="opset1">
	<input>
	<port id="0" precision="I64">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	</input>
	</layer>
	<layer id="12" name="Result_312409" 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="3" to-layer="15" to-port="2" />
	<edge from-layer="3" from-port="2" to-layer="15" to-port="1" />
	<edge from-layer="3" from-port="4" to-layer="14" to-port="1" />
	<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="10" to-port="0" />
	<edge from-layer="9" from-port="0" to-layer="10" to-port="1" />
	<edge from-layer="10" from-port="2" to-layer="11" to-port="0" />
	<edge from-layer="11" from-port="1" to-layer="12" to-port="0" />
	<edge from-layer="13" from-port="0" to-layer="14" to-port="0" />
	<edge from-layer="14" from-port="2" to-layer="15" to-port="0" />
	<edge from-layer="15" from-port="3" to-layer="17" to-port="0" />
	<edge from-layer="16" from-port="0" to-layer="17" to-port="1" />
	<edge from-layer="17" from-port="2" to-layer="18" to-port="0" />
	<edge from-layer="18" from-port="1" to-layer="19" to-port="0" />
	</edges>
	<rt_info>
	<bos_token_id value="2" />
	<chat_template value="{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + ' ' + message['content'] \| trim + '<end_of_turn> ' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model '}}{% endif %}" />
	<eos_token_id value="1" />
	<original_tokenizer_class value="<class 'transformers.models.gemma.tokenization_gemma_fast.GemmaTokenizerFast'>" />
	<pad_token_id value="0" />
	</rt_info>
	</net>