Instructions to use espressor/google.gemma-7b-it_W8A8_FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use espressor/google.gemma-7b-it_W8A8_FP8 with Transformers:

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

pipe = pipeline("text-generation", model="espressor/google.gemma-7b-it_W8A8_FP8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("espressor/google.gemma-7b-it_W8A8_FP8")
model = AutoModelForCausalLM.from_pretrained("espressor/google.gemma-7b-it_W8A8_FP8")
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-7b-it_W8A8_FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "espressor/google.gemma-7b-it_W8A8_FP8"
# 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-7b-it_W8A8_FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/espressor/google.gemma-7b-it_W8A8_FP8

SGLang

How to use espressor/google.gemma-7b-it_W8A8_FP8 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-7b-it_W8A8_FP8" \
    --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-7b-it_W8A8_FP8",
		"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-7b-it_W8A8_FP8" \
        --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-7b-it_W8A8_FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use espressor/google.gemma-7b-it_W8A8_FP8 with Docker Model Runner:
```
docker model run hf.co/espressor/google.gemma-7b-it_W8A8_FP8
```

google/gemma-7b-it - W8A8_FP8 Compression

This is a compressed model using llmcompressor.

Compression Configuration

Base Model: google/gemma-7b-it
Compression Scheme: W8A8_FP8
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>
Alan Turing was a mathematician, computer scientist, and cryptanalyst who played a pivotal role in the breaking of Nazi Germany's Enigma code during World War II. He is considered one of the fathers of modern computer science and is known for his contributions to the development of the Turing Test, which is a measure of a machine's ability to exhibit intelligent behavior equivalent to that of a human.

Here is a summary of his contributions:

* **Breaking the Enigma code:** Turing played a key role in cracking the Enigma code used by the Germans to encrypt their communications during the war. This significantly impacted the Allied war effort.
* **

Evaluation

Downloads last month: 4

Safetensors

Model size

9B params

Tensor type

BF16

F8_E4M3

Model tree for espressor/google.gemma-7b-it_W8A8_FP8

Base model

google/gemma-7b

Finetuned

google/gemma-7b-it

Quantized

(17)

this model

espressor
/

google.gemma-7b-it_W8A8_FP8