Instructions to use zake7749/gemma-2-2b-it-chinese-kyara-dpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zake7749/gemma-2-2b-it-chinese-kyara-dpo with Transformers:

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

pipe = pipeline("text-generation", model="zake7749/gemma-2-2b-it-chinese-kyara-dpo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zake7749/gemma-2-2b-it-chinese-kyara-dpo")
model = AutoModelForCausalLM.from_pretrained("zake7749/gemma-2-2b-it-chinese-kyara-dpo", 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/gemma-2-2b-it-chinese-kyara-dpo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zake7749/gemma-2-2b-it-chinese-kyara-dpo"
# 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/gemma-2-2b-it-chinese-kyara-dpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zake7749/gemma-2-2b-it-chinese-kyara-dpo

SGLang

How to use zake7749/gemma-2-2b-it-chinese-kyara-dpo 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/gemma-2-2b-it-chinese-kyara-dpo" \
    --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/gemma-2-2b-it-chinese-kyara-dpo",
		"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/gemma-2-2b-it-chinese-kyara-dpo" \
        --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/gemma-2-2b-it-chinese-kyara-dpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zake7749/gemma-2-2b-it-chinese-kyara-dpo with Docker Model Runner:
```
docker model run hf.co/zake7749/gemma-2-2b-it-chinese-kyara-dpo
```

zake7749 commited on Oct 28, 2024

Commit

2ca8e31

verified ·

1 Parent(s): ed5c045

Update README.md

Browse files

Files changed (1) hide show

README.md +17 -1

README.md CHANGED Viewed

@@ -117,6 +117,8 @@ license: gemma
 # Kyara: Knowledge Yielding Adaptive Retrieval Augmentation for LLM Fine-tuning
 <p align="left">
     🤗 <a href="https://huggingface.co/zake7749/gemma-2-2b-it-chinese-kyara-dpo">Hugging Face</a>&nbsp; ｜ 🚀<a href="https://github.com/zake7749/kyara">Github</a>&nbsp; ｜ &nbsp;📑 <a href="#">Paper</a>&nbsp; ｜ &nbsp;📖 <a href="https://github.com/zake7749/kyara/blob/main/document/README_EN.md">English</a>&nbsp; ｜ &nbsp;📖 <a href="https://github.com/zake7749/kyara">Chinese</a>&nbsp; ｜ &nbsp;💻 <a href="https://www.kaggle.com/code/zake7749/kyara-a-compact-yet-powerful-chinese-llm">Kaggle Notebook</a>
 </p>
@@ -418,4 +420,18 @@ However, the model would respond that this quote is from The "Legend of the Cond
 總結起來，這段話表達了楊過對於自己行為的獨特理解和自豪感。他明白自己的行為和價值觀取決於個人的內心和對正義的追求，而非外界的評價和名利。他也承認了自己的責任，作為唐門下一代，必須繼承和發揚門風，這一點是無可替代的。
 ```
-It is recommended to exercise caution when using language models.

 # Kyara: Knowledge Yielding Adaptive Retrieval Augmentation for LLM Fine-tuning
+[![DOI](https://zenodo.org/badge/844304447.svg)](https://zenodo.org/badge/latestdoi/844304447)
 <p align="left">
     🤗 <a href="https://huggingface.co/zake7749/gemma-2-2b-it-chinese-kyara-dpo">Hugging Face</a>&nbsp; ｜ 🚀<a href="https://github.com/zake7749/kyara">Github</a>&nbsp; ｜ &nbsp;📑 <a href="#">Paper</a>&nbsp; ｜ &nbsp;📖 <a href="https://github.com/zake7749/kyara/blob/main/document/README_EN.md">English</a>&nbsp; ｜ &nbsp;📖 <a href="https://github.com/zake7749/kyara">Chinese</a>&nbsp; ｜ &nbsp;💻 <a href="https://www.kaggle.com/code/zake7749/kyara-a-compact-yet-powerful-chinese-llm">Kaggle Notebook</a>
 </p>
 總結起來，這段話表達了楊過對於自己行為的獨特理解和自豪感。他明白自己的行為和價值觀取決於個人的內心和對正義的追求，而非外界的評價和名利。他也承認了自己的責任，作為唐門下一代，必須繼承和發揚門風，這一點是無可替代的。
 ```
+It is recommended to exercise caution when using language models.
+## Citation
+```bibtex
+@software{Yang_Kyara_2024,
+  author = {Yang, Kai-Chou},
+  doi = {10.5281/zenodo.14001626},
+  month = oct,
+  title = {{Kyara}},
+  url = {https://github.com/zake7749/Kyara},
+  version = {1.0.0},
+  year = {2024}
+}
+```