Instructions to use CarrotAI/Carrot-Ko-2B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CarrotAI/Carrot-Ko-2B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="CarrotAI/Carrot-Ko-2B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CarrotAI/Carrot-Ko-2B-Instruct")
model = AutoModelForCausalLM.from_pretrained("CarrotAI/Carrot-Ko-2B-Instruct", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CarrotAI/Carrot-Ko-2B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CarrotAI/Carrot-Ko-2B-Instruct"
# 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/Carrot-Ko-2B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CarrotAI/Carrot-Ko-2B-Instruct

SGLang

How to use CarrotAI/Carrot-Ko-2B-Instruct 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/Carrot-Ko-2B-Instruct" \
    --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/Carrot-Ko-2B-Instruct",
		"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/Carrot-Ko-2B-Instruct" \
        --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/Carrot-Ko-2B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CarrotAI/Carrot-Ko-2B-Instruct with Docker Model Runner:
```
docker model run hf.co/CarrotAI/Carrot-Ko-2B-Instruct
```

CarrotAI commited on Jul 4, 2024

Commit

21b1e47

verified ·

1 Parent(s): 0e17f50

Update README.md

Browse files

Files changed (1) hide show

README.md +12 -12

README.md CHANGED Viewed

@@ -14,7 +14,7 @@ library_name: transformers
 생성한 한국어 데이터셋으로 axolotl을 이용하여 파인튜닝하였습니다.
-[LogicKor](https://lk.instruct.kr/)에서 2.1B의 파라메터로 default 기준 4.07점을 기록하였습니다.
 아직 실험중인 모델입니다.
@@ -27,19 +27,19 @@ Qwen/Qwen2-1.5B-Instruct 모델을 이용하여 생성하였습니다.
 default
 | Category | Single turn | Multi turn |
-|---|---|---|
-| 추론(Reasoning) | 4.14 | 2.29 |
-| 수학(Math) | 2.43 | 1.14 |
-| 글쓰기(Writing) | 6.43 | 7.86 |
-| 코딩(Coding) | 5.14 | 4.57 |
-| 이해(Understanding) | 5.29 | 4.57 |
-| 문법(Grammar) | 3.71 | 1.29 |
 | Category | Score |
-|---|---|
-| Single turn | 4.52 |
-| Multi turn | 3.62 |
-| Overall | 4.07 |

 생성한 한국어 데이터셋으로 axolotl을 이용하여 파인튜닝하였습니다.
+[LogicKor](https://lk.instruct.kr/)에서 2.1B의 파라메터로 default 기준 4.21점을 기록하였습니다.
 아직 실험중인 모델입니다.
 default
 | Category | Single turn | Multi turn |
+|----------|-------------|------------|
+| 이해 (Understanding) | 6.14 | 5.43 |
+| 문법 (Grammar) | 5.00 | 2.43 |
+| 수학 (Math) | 1.86 | 1.86 |
+| 추론 (Reasoning) | 5.57 | 2.14 |
+| 코딩 (Coding) | 3.57 | 3.71 |
+| 글쓰기 (Writing) | 6.00 | 6.86 |
 | Category | Score |
+|----------|------|
+| Single turn | 4.69 |
+| Multi turn | 3.74 |
+| Overall | 4.21 |