Instructions to use AdamLucek/gemma2-2b-it-chinese-german with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AdamLucek/gemma2-2b-it-chinese-german with Transformers:

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

pipe = pipeline("text-generation", model="AdamLucek/gemma2-2b-it-chinese-german")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AdamLucek/gemma2-2b-it-chinese-german")
model = AutoModelForCausalLM.from_pretrained("AdamLucek/gemma2-2b-it-chinese-german")
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 AdamLucek/gemma2-2b-it-chinese-german with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AdamLucek/gemma2-2b-it-chinese-german"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AdamLucek/gemma2-2b-it-chinese-german",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AdamLucek/gemma2-2b-it-chinese-german

SGLang

How to use AdamLucek/gemma2-2b-it-chinese-german 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 "AdamLucek/gemma2-2b-it-chinese-german" \
    --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": "AdamLucek/gemma2-2b-it-chinese-german",
		"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 "AdamLucek/gemma2-2b-it-chinese-german" \
        --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": "AdamLucek/gemma2-2b-it-chinese-german",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AdamLucek/gemma2-2b-it-chinese-german with Docker Model Runner:
```
docker model run hf.co/AdamLucek/gemma2-2b-it-chinese-german
```

Gemma2-2B-it Merged Fine-Tuned Models for Chinese & German understanding

Lightweight language model based on Gemma2 2B created by merging multiple fine tuned Gemma2-2B-IT versions to test multilingual conversation capabilities in specialized low parameter language models.

🤏 Models Merged

This is a merge of pre-trained language models created using mergekit. This model was merged using the Model Stock merge method using google/gemma-2-2b-it as a base.

The following models were included in the merge:

🧩 Configuration

The following YAML configuration was used to produce this model:

models:
  - model: google/gemma-2-2b-it
  - model: VAGOsolutions/SauerkrautLM-gemma-2-2b-it
  - model: stvlynn/Gemma-2-2b-Chinese-it
merge_method: model_stock
base_model: google/gemma-2-2b-it
dtype: bfloat16

💻 Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Load the tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("AdamLucek/gemma2-2b-it-chinese-german")
model = AutoModelForCausalLM.from_pretrained(
    "AdamLucek/gemma2-2b-it-chinese-german",
    device_map="cuda",
    torch_dtype=torch.bfloat16
)

# Prepare the input text
input_text = "请解释一下量子力学中的叠加原理，并举例说明该原理在实际应用中的重要性和挑战。"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

# Generate the output
outputs = model.generate(
    **input_ids,
    max_new_tokens=256,
    pad_token_id=tokenizer.eos_token_id
)

# Decode and print the generated text
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Ouptut

## 量子叠加原理：

**叠加原理**是量子力学中一个重要的概念，它描述了量子系统在测量之前处于多个状态的可能性。

**简单来说，就是说，一个量子系统可以同时处于多个状态，直到我们测量它时，才会坍缩到一个确定的状态。**

**具体来说，我们可以用以下方式理解叠加原理：**

* **量子系统：** 比如一个原子，它可以处于多个能量状态。
* **叠加态：**  表示量子系统同时处于多个状态的概率分布。
* **测量：**  当我们测量量子系统时，它会坍缩到一个确定的状态。
* **坍缩：**  测量过程会改变量子系统的状态，使其坍缩到一个确定的状态。

**举例说明：**

想象一下一个量子系统，它可以处于两个状态：上或下。这个系统可以被描述为一个叠加态，表示它同时处于上和下两个状态的概率分布。

**如果我们没有测量这个系统，那么它就处于叠加态，同时处于上和下两个状态。**

**但是，当我们测量这个系统时