Instructions to use niryuu/Karasu-1.1b-chat-vector with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use niryuu/Karasu-1.1b-chat-vector with Transformers:

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

pipe = pipeline("text-generation", model="niryuu/Karasu-1.1b-chat-vector")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("niryuu/Karasu-1.1b-chat-vector")
model = AutoModelForCausalLM.from_pretrained("niryuu/Karasu-1.1b-chat-vector")
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 Settings

vLLM

How to use niryuu/Karasu-1.1b-chat-vector with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "niryuu/Karasu-1.1b-chat-vector"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "niryuu/Karasu-1.1b-chat-vector",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/niryuu/Karasu-1.1b-chat-vector

SGLang

How to use niryuu/Karasu-1.1b-chat-vector 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 "niryuu/Karasu-1.1b-chat-vector" \
    --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": "niryuu/Karasu-1.1b-chat-vector",
		"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 "niryuu/Karasu-1.1b-chat-vector" \
        --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": "niryuu/Karasu-1.1b-chat-vector",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use niryuu/Karasu-1.1b-chat-vector with Docker Model Runner:
```
docker model run hf.co/niryuu/Karasu-1.1b-chat-vector
```

niryuu commited on Mar 24, 2024

Commit

8a41dc2

verified ·

1 Parent(s): 4ce1e63

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -7,7 +7,7 @@ widget:
 - example_title: 日本語チャット
   messages:
   - role: system
-    content: You are a chatbot.
   - role: user
     content: 日本で一番高い山は？
 pipeline_tag: text-generation

 - example_title: 日本語チャット
   messages:
   - role: system
+    content: あなたは日本語のチャットボットです。
   - role: user
     content: 日本で一番高い山は？
 pipeline_tag: text-generation