Instructions to use SWSnowball/Aliak_ChatBot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SWSnowball/Aliak_ChatBot with Transformers:

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

pipe = pipeline("text-generation", model="SWSnowball/Aliak_ChatBot")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SWSnowball/Aliak_ChatBot")
model = AutoModelForCausalLM.from_pretrained("SWSnowball/Aliak_ChatBot", 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 SWSnowball/Aliak_ChatBot with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/SWSnowball/Aliak_ChatBot

SGLang

How to use SWSnowball/Aliak_ChatBot 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 "SWSnowball/Aliak_ChatBot" \
    --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": "SWSnowball/Aliak_ChatBot",
		"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 "SWSnowball/Aliak_ChatBot" \
        --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": "SWSnowball/Aliak_ChatBot",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SWSnowball/Aliak_ChatBot with Docker Model Runner:
```
docker model run hf.co/SWSnowball/Aliak_ChatBot
```

Model Details

Model Description

SW_Snowball_'s own dragon OC Aliak's ChatBot. You'd better use Chinese to communicate with him.

**Developed by: SW_Snowball_
**Original Model: Qwen/Qwen1.5-0.5B-Chat

How to Get Started with the Model

Use the code below to get started with the model.

================================================== import torch from transformers import AutoModelForCausalLM, AutoTokenizer import time

def s(): global start start = time.time()

def e(): global end end = time.time() return round(end-start, 2)

model_path = "SWSnowball/Aliak_ChatBot"

tokenizer = AutoTokenizer.from_pretrained(model_path) if tokenizer.pad_token is None: tokenizer.pad_token = tokenizer.eos_token

model = AutoModelForCausalLM.from_pretrained( model_path, torch_dtype=torch.float16, device_map="auto" )

messages = [] print("对话开始，输入 'exit' 退出\n")

while True: user_input = input("You：") if user_input.lower() == "exit": break messages.append({"role": "user", "content": user_input}) s() text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) inputs = tokenizer(text, return_tensors="pt").to(model.device) with torch.no_grad(): outputs = model.generate( **inputs, max_new_tokens=128, do_sample=True, temperature=0.7, top_p=0.9, repetition_penalty=1.1, ) response = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True).strip() print(f"AI（生成用时{e()}s）：{response}") messages.append({"role": "assistant", "content": response})

Training Data

My own hand-writing novel and other my own hand-writing Aliak's Conversations.

Downloads last month: 6

Safetensors

Model size

0.6B params

Tensor type

BF16