Instructions to use styal/Reflection-Gemma-2-2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use styal/Reflection-Gemma-2-2b with Transformers:

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

pipe = pipeline("text-generation", model="styal/Reflection-Gemma-2-2b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("styal/Reflection-Gemma-2-2b")
model = AutoModelForCausalLM.from_pretrained("styal/Reflection-Gemma-2-2b")
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]:]))

PEFT
How to use styal/Reflection-Gemma-2-2b with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use styal/Reflection-Gemma-2-2b with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/styal/Reflection-Gemma-2-2b

SGLang

How to use styal/Reflection-Gemma-2-2b 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 "styal/Reflection-Gemma-2-2b" \
    --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": "styal/Reflection-Gemma-2-2b",
		"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 "styal/Reflection-Gemma-2-2b" \
        --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": "styal/Reflection-Gemma-2-2b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use styal/Reflection-Gemma-2-2b with Docker Model Runner:
```
docker model run hf.co/styal/Reflection-Gemma-2-2b
```

Usage

This model uses the 4-bits quantization. So you need to install bitsandbytes to use it.

pip install bitsandbytes

For inference (streaming):

from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
import torch
from transformers import TextIteratorStreamer
from threading import Thread
device = 'cuda' if torch.cuda.is_available() else 'cpu'

model_id = "Arthur-LAGACHERIE/Reflection-Gemma-2-2b"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

prompt = """
### System
You are a world-class AI system, capable of complex reasoning and reflection. 
Reason through the query inside <thinking> tags, and then provide your final response inside <output> tags. 
If you detect that you made a mistake in your reasoning at any point, correct yourself inside <reflection> tags.
Try an answer and see if it's correct before generate the ouput. 
But don't forget to think very carefully.

### Question
The question here.
"""

chat = [
    { "role": "user", "content": prompt},
]
question = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
question = tokenizer(question, return_tensors="pt").to(device)
streamer = TextIteratorStreamer(tokenizer, skip_prompt=True)
generation_kwargs = dict(question, streamer=streamer, max_new_tokens=4000)
thread = Thread(target=model.generate, kwargs=generation_kwargs)

# generate
thread.start()
for new_text in streamer:
    print(new_text, end="")

Some info

If you want to know how I fine tune it, what datasets I used and the training code. See here

Model Trained Using AutoTrain

This model was trained using AutoTrain. For more information, please visit AutoTrain.

Downloads last month: 1

Safetensors

Model size

3B params

Tensor type

F32

F16

Model tree for styal/Reflection-Gemma-2-2b

Base model

styal/Gemma-2-2b-4bit

Quantized

(1)

this model