Instructions to use zake7749/Llama-3.2-1B-it-chinese-kyara with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zake7749/Llama-3.2-1B-it-chinese-kyara with Transformers:

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

pipe = pipeline("text-generation", model="zake7749/Llama-3.2-1B-it-chinese-kyara")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zake7749/Llama-3.2-1B-it-chinese-kyara")
model = AutoModelForCausalLM.from_pretrained("zake7749/Llama-3.2-1B-it-chinese-kyara", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use zake7749/Llama-3.2-1B-it-chinese-kyara with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zake7749/Llama-3.2-1B-it-chinese-kyara"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zake7749/Llama-3.2-1B-it-chinese-kyara",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zake7749/Llama-3.2-1B-it-chinese-kyara

SGLang

How to use zake7749/Llama-3.2-1B-it-chinese-kyara 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 "zake7749/Llama-3.2-1B-it-chinese-kyara" \
    --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": "zake7749/Llama-3.2-1B-it-chinese-kyara",
		"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 "zake7749/Llama-3.2-1B-it-chinese-kyara" \
        --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": "zake7749/Llama-3.2-1B-it-chinese-kyara",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zake7749/Llama-3.2-1B-it-chinese-kyara with Docker Model Runner:
```
docker model run hf.co/zake7749/Llama-3.2-1B-it-chinese-kyara
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Kyara: Knowledge Yielding Adaptive Retrieval Augmentation for LLM Fine-tuning

🤗 Hugging Face ｜ 🚀Github ｜ 📑 Paper ｜ 📖 English ｜ 📖 Chinese ｜ 💻 Kaggle Notebook

Kyara (Knowledge Yielding Adaptive Retrieval Augmentation) is an experimental project aimed at improving language models through knowledge retrieval processes. The project seeks to enhance the model’s ability to adapt knowledge and improve language comprehension, particularly in underrepresented languages like Traditional Chinese. Given the relatively scarce availability of Traditional Chinese data compared to the vast corpus of English data used for model training, Kyara addresses this gap by expanding the limited corpus for this language.

This is a preview model, with the stable version set to be released soon.

Benchmark

All evaluations are conducted in a zero-shot setting.

Metric	Kyara-1b-it	Llama3.2-1b-it
TMMLUPlus	31.92	30.48
- STEM	32.56	29.74
- Humanities	30.60	29.89
- Other	31.08	30.32
- Social-Science	33.42	31.98
MMLU-Redux	41.40	19.62⁺
GSM8K	31.31	31.61
MATH-L5	5.55	2.91
CRUX	14	11
AlpacaEval	10.79	7.39

⁺: Llama3.2-1b-it appears to have failed to follow the output schema of ZeroEval on MMLU, with 45.28% of examples lacking answers, which has resulted in a lower MMLU score.

Downloads last month: 6

Safetensors

Model size

1B params

Tensor type

BF16

Model tree for zake7749/Llama-3.2-1B-it-chinese-kyara

Base model

meta-llama/Llama-3.2-1B-Instruct

Finetuned

(1767)

this model

Quantizations

2 models