Instructions to use Mr-Vicky-01/gemma-qna with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Mr-Vicky-01/gemma-qna with Transformers:

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

pipe = pipeline("text-generation", model="Mr-Vicky-01/gemma-qna")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Mr-Vicky-01/gemma-qna")
model = AutoModelForMultimodalLM.from_pretrained("Mr-Vicky-01/gemma-qna")
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 Mr-Vicky-01/gemma-qna with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Mr-Vicky-01/gemma-qna"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mr-Vicky-01/gemma-qna",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Mr-Vicky-01/gemma-qna

SGLang

How to use Mr-Vicky-01/gemma-qna 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 "Mr-Vicky-01/gemma-qna" \
    --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": "Mr-Vicky-01/gemma-qna",
		"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 "Mr-Vicky-01/gemma-qna" \
        --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": "Mr-Vicky-01/gemma-qna",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use Mr-Vicky-01/gemma-qna with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Mr-Vicky-01/gemma-qna to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Mr-Vicky-01/gemma-qna to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Mr-Vicky-01/gemma-qna to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Mr-Vicky-01/gemma-qna",
    max_seq_length=2048,
)

Docker Model Runner
How to use Mr-Vicky-01/gemma-qna with Docker Model Runner:
```
docker model run hf.co/Mr-Vicky-01/gemma-qna
```

Mr-Vicky-01 commited on Mar 31, 2025

Commit

a5c10e0

verified ·

1 Parent(s): 3280dfc

Unsloth Model Card

Browse files

Files changed (1) hide show

README.md +14 -67

README.md CHANGED Viewed

@@ -1,74 +1,21 @@
 ---
-library_name: transformers
 license: apache-2.0
 ---
-## INFERENCE
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
-import torch
-# Load model and tokenizer
-tokenizer = AutoTokenizer.from_pretrained("Mr-Vicky-01/gemma-qna")
-model = AutoModelForCausalLM.from_pretrained("Mr-Vicky-01/gemma-qna")
-# Define the system prompt
-prompt = """
-<bos><start_of_turn>user
-You are Securitron, Created by Aquilax, a helpful AI assistant specialized in providing accurate and professional responses. Always prioritize clarity and precision in your answers.
-"""
-# Initialize conversation history
-conversation_history = []
-# Set up device
-device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
-model.to(device)
-i=0
-while True:
-    user_prompt = input("\nUser Question: ")
-    if user_prompt.lower() == 'break':
-        break
-    if i==0:
-         user_message = f"""
-{user_prompt}<end_of_turn>
-<start_of_turn>model"""
-         i+=1
-    else:
-        user_message = f"""
-<start_of_turn>user
-{user_prompt}<end_of_turn>
-<start_of_turn>model"""
-    # Add the user's question to the conversation history
-    conversation_history.append(user_message)
-    # Keep only the last 2 exchanges (4 turns)
-    conversation_history = conversation_history[-5:]
-    # Build the full prompt
-    current_prompt = prompt + "\n".join(conversation_history)
-    # Tokenize the prompt
-    encodeds = tokenizer(current_prompt, return_tensors="pt", truncation=True).input_ids.to(device)
-    # Initialize TextStreamer for real-time token generation
-    text_streamer = TextStreamer(tokenizer, skip_prompt=True)
-    # Generate response with TextStreamer
-    response = model.generate(
-        input_ids=encodeds,
-        streamer=text_streamer,
-        max_new_tokens=2048,
-        use_cache=True,
-        pad_token_id=106,
-        eos_token_id=106,
-        num_return_sequences=1
-    )
-    # Finalize conversation history with the assistant's response
-    conversation_history.append(tokenizer.decode(response[0]).split('<start_of_turn>model')[-1].split('<end_of_turn>')[0].strip())
-```

 ---
+base_model: unsloth/gemma-3-1b-it-unsloth-bnb-4bit
+tags:
+- text-generation-inference
+- transformers
+- unsloth
+- gemma3_text
 license: apache-2.0
+language:
+- en
 ---
+# Uploaded finetuned  model
+- **Developed by:** Mr-Vicky-01
+- **License:** apache-2.0
+- **Finetuned from model :** unsloth/gemma-3-1b-it-unsloth-bnb-4bit
+This gemma3_text model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)