Instructions to use Xenova/tiny-random-GemmaForCausalLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Xenova/tiny-random-GemmaForCausalLM with Transformers:

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

pipe = pipeline("text-generation", model="Xenova/tiny-random-GemmaForCausalLM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Xenova/tiny-random-GemmaForCausalLM")
model = AutoModelForCausalLM.from_pretrained("Xenova/tiny-random-GemmaForCausalLM")
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

vLLM

How to use Xenova/tiny-random-GemmaForCausalLM with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Xenova/tiny-random-GemmaForCausalLM

SGLang

How to use Xenova/tiny-random-GemmaForCausalLM 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 "Xenova/tiny-random-GemmaForCausalLM" \
    --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": "Xenova/tiny-random-GemmaForCausalLM",
		"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 "Xenova/tiny-random-GemmaForCausalLM" \
        --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": "Xenova/tiny-random-GemmaForCausalLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Xenova/tiny-random-GemmaForCausalLM with Docker Model Runner:
```
docker model run hf.co/Xenova/tiny-random-GemmaForCausalLM
```

tiny-random-GemmaForCausalLM / quantize_config.json

Xenova HF Staff

Upload folder using huggingface_hub (#4)

0f7386d verified about 2 years ago

raw

history blame

3.62 kB

	{
	"fp16": {},
	"q8": {
	"per_model_config": {
	"model": {
	"op_types": [
	"Add",
	"Cast",
	"Concat",
	"Constant",
	"ConstantOfShape",
	"Cos",
	"Div",
	"Equal",
	"Expand",
	"Gather",
	"Greater",
	"Identity",
	"MatMul",
	"Mul",
	"Neg",
	"Pow",
	"Range",
	"ReduceMean",
	"Reshape",
	"ScatterND",
	"Shape",
	"Sin",
	"Slice",
	"Softmax",
	"Sqrt",
	"Tanh",
	"Transpose",
	"Trilu",
	"Unsqueeze",
	"Where"
	],
	"weight_type": "QInt8"
	}
	},
	"per_channel": true,
	"reduce_range": true
	},
	"int8": {
	"per_model_config": {
	"model": {
	"op_types": [
	"Add",
	"Cast",
	"Concat",
	"Constant",
	"ConstantOfShape",
	"Cos",
	"Div",
	"Equal",
	"Expand",
	"Gather",
	"Greater",
	"Identity",
	"MatMul",
	"Mul",
	"Neg",
	"Pow",
	"Range",
	"ReduceMean",
	"Reshape",
	"ScatterND",
	"Shape",
	"Sin",
	"Slice",
	"Softmax",
	"Sqrt",
	"Tanh",
	"Transpose",
	"Trilu",
	"Unsqueeze",
	"Where"
	],
	"weight_type": "QInt8"
	}
	},
	"per_channel": true,
	"reduce_range": true
	},
	"uint8": {
	"per_model_config": {
	"model": {
	"op_types": [
	"Add",
	"Cast",
	"Concat",
	"Constant",
	"ConstantOfShape",
	"Cos",
	"Div",
	"Equal",
	"Expand",
	"Gather",
	"Greater",
	"Identity",
	"MatMul",
	"Mul",
	"Neg",
	"Pow",
	"Range",
	"ReduceMean",
	"Reshape",
	"ScatterND",
	"Shape",
	"Sin",
	"Slice",
	"Softmax",
	"Sqrt",
	"Tanh",
	"Transpose",
	"Trilu",
	"Unsqueeze",
	"Where"
	],
	"weight_type": "QUInt8"
	}
	},
	"per_channel": true,
	"reduce_range": true
	},
	"q4": {
	"block_size": 32,
	"is_symmetric": true,
	"accuracy_level": null
	},
	"bnb4": {
	"block_size": 64,
	"quant_type": 1
	}
	}