Instructions to use espressor/google.gemma-2-2b-it_W4A16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use espressor/google.gemma-2-2b-it_W4A16 with Transformers:

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

pipe = pipeline("text-generation", model="espressor/google.gemma-2-2b-it_W4A16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("espressor/google.gemma-2-2b-it_W4A16")
model = AutoModelForCausalLM.from_pretrained("espressor/google.gemma-2-2b-it_W4A16")
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 espressor/google.gemma-2-2b-it_W4A16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "espressor/google.gemma-2-2b-it_W4A16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "espressor/google.gemma-2-2b-it_W4A16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/espressor/google.gemma-2-2b-it_W4A16

SGLang

How to use espressor/google.gemma-2-2b-it_W4A16 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 "espressor/google.gemma-2-2b-it_W4A16" \
    --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": "espressor/google.gemma-2-2b-it_W4A16",
		"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 "espressor/google.gemma-2-2b-it_W4A16" \
        --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": "espressor/google.gemma-2-2b-it_W4A16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use espressor/google.gemma-2-2b-it_W4A16 with Docker Model Runner:
```
docker model run hf.co/espressor/google.gemma-2-2b-it_W4A16
```

google/gemma-2-2b-it - W4A16 Compression

This is a compressed model using llmcompressor.

Compression Configuration

Base Model: google/gemma-2-2b-it
Compression Scheme: W4A16
Dataset: HuggingFaceH4/ultrachat_200k
Dataset Split: train_sft
Number of Samples: 512
Preprocessor: chat
Maximum Sequence Length: 8192

Sample Output

Prompt:

<bos><start_of_turn>user
Who is Alan Turing?<end_of_turn>

Output:

<bos><bos><start_of_turn>user
Who is Alan Turing?<end_of_turn>
* **A mathematician and computer scientist**
* **A pioneer in artificial intelligence**
* **A codebreaker during World War II**
* **A symbol of LGBTQ+ rights**

All of the above

**Answer:** All of the above

**Explanation:**

Alan Turing was a truly remarkable individual who made significant contributions in multiple fields. 

* **Mathematician and Computer Scientist:** Turing was a brilliant mathematician who made groundbreaking contributions to theoretical computer science, including the Turing Machine, a theoretical model of computation that laid the foundation for modern computers. He also made significant contributions to logic, number theory, and other areas

Evaluation

Downloads last month: 5

Safetensors

Model size

3B params

Tensor type

I64

I32

BF16

Model tree for espressor/google.gemma-2-2b-it_W4A16

Base model

google/gemma-2-2b

Finetuned

google/gemma-2-2b-it

Quantized

(177)

this model

espressor
/

google.gemma-2-2b-it_W4A16