Instructions to use CarrotAI/ko-gemma-2b-it-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CarrotAI/ko-gemma-2b-it-sft with Transformers:

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

pipe = pipeline("text-generation", model="CarrotAI/ko-gemma-2b-it-sft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CarrotAI/ko-gemma-2b-it-sft")
model = AutoModelForCausalLM.from_pretrained("CarrotAI/ko-gemma-2b-it-sft")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use CarrotAI/ko-gemma-2b-it-sft with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/CarrotAI/ko-gemma-2b-it-sft

SGLang

How to use CarrotAI/ko-gemma-2b-it-sft 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 "CarrotAI/ko-gemma-2b-it-sft" \
    --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": "CarrotAI/ko-gemma-2b-it-sft",
		"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 "CarrotAI/ko-gemma-2b-it-sft" \
        --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": "CarrotAI/ko-gemma-2b-it-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CarrotAI/ko-gemma-2b-it-sft with Docker Model Runner:
```
docker model run hf.co/CarrotAI/ko-gemma-2b-it-sft
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model

Model Page: Gemma

fine-tuned the google/gemma-2b-it model.

How to Use it

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("carrotter/ko-gemma-2b-it-sft")
model = AutoModelForCausalLM.from_pretrained("carrotter/ko-gemma-2b-it-sft")

chat = [
    { "role": "user", "content": "피보나치 수열 파이썬 코드로 알려줘" },
]
prompt = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)

inputs = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")
outputs = model.generate(input_ids=inputs.to(model.device), max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Example Output

<bos><start_of_turn>user
피보나치 수열 파이썬 코드로 알려줘<end_of_turn>
<start_of_turn>model
다음은 피보나치 수열을 파이썬으로 구현하는 방법의 예입니다:

def fibonacci(n):
    if n <= 1:
        return n
    else:
        return fibonacci(n-1) + fibonacci(n-2)

이 함수는 n이 피보나치 수열의 몇 번째 항인지에 따라 반환합니다. n이 1이거나 2인 경우

Applications

This fine-tuned model is particularly suited for [mention applications, e.g., chatbots, question-answering systems, etc.]. Its enhanced capabilities ensure more accurate and contextually appropriate responses in these domains.

Limitations and Considerations

While our fine-tuning process has optimized the model for specific tasks, it's important to acknowledge potential limitations. The model's performance can still vary based on the complexity of the task and the specificities of the input data. Users are encouraged to evaluate the model thoroughly in their specific context to ensure it meets their requirements.

Downloads last month: 6

Safetensors

Model size

3B params

Tensor type

F16

Model tree for CarrotAI/ko-gemma-2b-it-sft

Quantizations

2 models

CarrotAI
/

ko-gemma-2b-it-sft