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, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("kakaocorp/kanana-1.5-2.1b-base")
model = AutoModelForMultimodalLM.from_pretrained("kakaocorp/kanana-1.5-2.1b-base")
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
```

wavy-jung commited on Apr 15, 2025

Commit

273bbfc

verified ·

1 Parent(s): ad150d6

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -11,7 +11,7 @@ developers: KananaAlpha LLM
 training_regime: bf16 mixed precision
 results: '|   mmlu (5-shots) [acc] |   kmmlu-direct (5-shots) [exact_match] |   haerae (5-shots) [acc_norm] |   gsm8k (5-shots) [exact_match_strict] |   humaneval (0-shots) [pass@1] |   mbpp (3-shots) [pass@1] |
 |------------------------|----------------------------------------|-------------------------------|----------------------------------------|--------------------------------|---------------------------|
-|                  56.26 |                                  45.25 |                         76.72 |                                  53.60 |                          53.66 |                      53.66 |'
 model_summary: Kanana-1.5-2.1b-base is an auto-regressive language model that
   uses an optimized transformer architecture. Kanana-1.5-2.1b-base uses a tokenizer
   with a vocabulary of 128K tokens, and supports sequence length of 32k.
@@ -78,7 +78,7 @@ model-index:
       type: google-research-datasets/mbpp
     metrics:
     - type: pass@1
-      value: 53.66
       name: pass@1
 ---
 # Model Card for kakaocorp/kanana-1.5-2.1b-base
@@ -123,7 +123,7 @@ Kanana-1.5-2.1b-base was continuously pretrained from kakaocorp/kanana-essence-2
 |   mmlu (5-shots) [acc] |   kmmlu-direct (5-shots) [exact_match] |   haerae (5-shots) [acc_norm] |   gsm8k (5-shots) [exact_match_strict] |   humaneval (0-shots) [pass@1] |   mbpp (3-shots) [pass@1] |
 |------------------------|----------------------------------------|-------------------------------|----------------------------------------|--------------------------------|---------------------------|
-|                  56.26 |                                  45.25 |                         76.72 |                                  53.60 |                          53.66 |                      53.66 |
 ### Results for Long-Context Tasks
 | context length | ruler_niah_mk_2 [ruler_recall] | ruler_niah_mk_3 [ruler_recall] | ruler_niah_mv [ruler_recall] | json_kv [substring_exact_match] | niah [avg] |  avg  |

 training_regime: bf16 mixed precision
 results: '|   mmlu (5-shots) [acc] |   kmmlu-direct (5-shots) [exact_match] |   haerae (5-shots) [acc_norm] |   gsm8k (5-shots) [exact_match_strict] |   humaneval (0-shots) [pass@1] |   mbpp (3-shots) [pass@1] |
 |------------------------|----------------------------------------|-------------------------------|----------------------------------------|--------------------------------|---------------------------|
+|                  56.26 |                                  45.25 |                         76.72 |                                  53.60 |                          53.66 |                      56.65 |'
 model_summary: Kanana-1.5-2.1b-base is an auto-regressive language model that
   uses an optimized transformer architecture. Kanana-1.5-2.1b-base uses a tokenizer
   with a vocabulary of 128K tokens, and supports sequence length of 32k.
       type: google-research-datasets/mbpp
     metrics:
     - type: pass@1
+      value: 56.65
       name: pass@1
 ---
 # Model Card for kakaocorp/kanana-1.5-2.1b-base
 |   mmlu (5-shots) [acc] |   kmmlu-direct (5-shots) [exact_match] |   haerae (5-shots) [acc_norm] |   gsm8k (5-shots) [exact_match_strict] |   humaneval (0-shots) [pass@1] |   mbpp (3-shots) [pass@1] |
 |------------------------|----------------------------------------|-------------------------------|----------------------------------------|--------------------------------|---------------------------|
+|                  56.26 |                                  45.25 |                         76.72 |                                  53.60 |                          53.66 |                      56.65 |
 ### Results for Long-Context Tasks
 | context length | ruler_niah_mk_2 [ruler_recall] | ruler_niah_mk_3 [ruler_recall] | ruler_niah_mv [ruler_recall] | json_kv [substring_exact_match] | niah [avg] |  avg  |