Instructions to use RichardErkhov/DeepMount00_-_Gemma_QA_ITA_v3-8bits with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RichardErkhov/DeepMount00_-_Gemma_QA_ITA_v3-8bits with Transformers:

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

pipe = pipeline("text-generation", model="RichardErkhov/DeepMount00_-_Gemma_QA_ITA_v3-8bits")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RichardErkhov/DeepMount00_-_Gemma_QA_ITA_v3-8bits")
model = AutoModelForCausalLM.from_pretrained("RichardErkhov/DeepMount00_-_Gemma_QA_ITA_v3-8bits", 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 RichardErkhov/DeepMount00_-_Gemma_QA_ITA_v3-8bits with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RichardErkhov/DeepMount00_-_Gemma_QA_ITA_v3-8bits"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RichardErkhov/DeepMount00_-_Gemma_QA_ITA_v3-8bits",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RichardErkhov/DeepMount00_-_Gemma_QA_ITA_v3-8bits

SGLang

How to use RichardErkhov/DeepMount00_-_Gemma_QA_ITA_v3-8bits 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 "RichardErkhov/DeepMount00_-_Gemma_QA_ITA_v3-8bits" \
    --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": "RichardErkhov/DeepMount00_-_Gemma_QA_ITA_v3-8bits",
		"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 "RichardErkhov/DeepMount00_-_Gemma_QA_ITA_v3-8bits" \
        --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": "RichardErkhov/DeepMount00_-_Gemma_QA_ITA_v3-8bits",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RichardErkhov/DeepMount00_-_Gemma_QA_ITA_v3-8bits with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/DeepMount00_-_Gemma_QA_ITA_v3-8bits
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Gemma_QA_ITA_v3 - bnb 8bits

Model creator: https://huggingface.co/DeepMount00/
Original model: https://huggingface.co/DeepMount00/Gemma_QA_ITA_v3/

Original model description:

library_name: transformers datasets: - DeepMount00/gquad_it pipeline_tag: question-answering license: apache-2.0 language: - it

How to Use

How to use Gemma Q&A

import transformers
from transformers import TextStreamer, AutoTokenizer
import torch

model_name = "DeepMount00/Gemma_QA_ITA_v3"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = transformers.GemmaForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto").eval()


def stream(contesto, domanda):
  device = "cuda:0"
  prefix_text = 'Di seguito ti verrà fornito un contesto e poi una domanda. Il tuo compito è quello di rispondere alla domanda basandoti esclusivamente sul contesto.\n\n'

  prompt = f"""{prefix_text}##CONTESTO: {contesto}\n##DOMANDA: {domanda}"""

  inputs = tokenizer([prompt], return_tensors="pt").to(device)
  streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)

  _ = model.generate(**inputs, streamer=streamer, max_new_tokens=150, temperature=0.01,
                           repetition_penalty=1.0, eos_token_id=107, do_sample=True, num_return_sequences=1)


contesto = """Seneca seguì molto intensamente gli insegnamenti dei maestri, che esercitarono su di lui un profondo influsso sia con la parola sia con l'esempio di una vita vissuta in coerenza con gli ideali professati. Da Attalo imparò i principi dello stoicismo e l'abitudine alle pratiche ascetiche. Da Sozione, oltre ad apprendere i principi delle dottrine di Pitagora, fu avviato per qualche tempo verso la pratica vegetariana; venne distolto però dal padre che non amava la filosofia e dal fatto che l'imperatore Tiberio proibisse di seguire consuetudini di vita non romane."""
domanda = "Chi è Seneca?"

stream(contesto, domanda)

Downloads last month: 5

Safetensors

Model size

3B params

Tensor type

F32

F16