Instructions to use kakaocorp/kanana-1.5-2.1b-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kakaocorp/kanana-1.5-2.1b-base with Transformers:

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

pipe = pipeline("text-generation", model="kakaocorp/kanana-1.5-2.1b-base")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kakaocorp/kanana-1.5-2.1b-base")
model = AutoModelForCausalLM.from_pretrained("kakaocorp/kanana-1.5-2.1b-base", 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 kakaocorp/kanana-1.5-2.1b-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kakaocorp/kanana-1.5-2.1b-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kakaocorp/kanana-1.5-2.1b-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kakaocorp/kanana-1.5-2.1b-base

SGLang

How to use kakaocorp/kanana-1.5-2.1b-base 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 "kakaocorp/kanana-1.5-2.1b-base" \
    --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": "kakaocorp/kanana-1.5-2.1b-base",
		"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 "kakaocorp/kanana-1.5-2.1b-base" \
        --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": "kakaocorp/kanana-1.5-2.1b-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kakaocorp/kanana-1.5-2.1b-base with Docker Model Runner:
```
docker model run hf.co/kakaocorp/kanana-1.5-2.1b-base
```

Kanana-1.5-2.1b Fine-tuned model output contains numberings

by daebakgazua - opened Jun 3, 2025

Discussion

daebakgazua

Jun 3, 2025

•

edited Jun 3, 2025

Topic to discuss
- When I fine-tune Kanana-1.5-2.1b-base LLM, sometimes (not always) I get the output with 'numbering's. Why?
- Regardless of reason, it is interesting.
- related comment from my project (by me)
Fine-tuning settings & Dataset
- 572 train rows & 90 valid rows
- input_data as input column & output_message as output column
- train template : {input_data} (답변 시작) ### 답변: {output_message} (답변 종료) <|end_of_text|>
- LoRA rank = 64 & initial learning rate = 0.0003 (= 3e-4)
Output
- sometimes contains numberings at the start
  - when LLM weights were initialized well at start of training, the outputs do not contain numberings
- example
  - 2:5 오로라는 밤하늘을 비추는 것! 내 이름이 여기서 나왔지! 🙂 (답변 종료)
  - 2: 싫어! 난 그냥 혼자서 가상인간으로 살래! (답변 종료)
My guess
- Kakao trained Kanana-1.5-2.1b-base LLM with something like {'question': 'how to release stress', 'answer': '1. Listen to music, such as REBEL HEART of IVE.\n2. Play soccer.\n3. Play computer or mobile games.'}

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment