Instructions to use RichardErkhov/lemon-mint_-_gemma-2b-translation-v0.103-4bits with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RichardErkhov/lemon-mint_-_gemma-2b-translation-v0.103-4bits with Transformers:

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

pipe = pipeline("text-generation", model="RichardErkhov/lemon-mint_-_gemma-2b-translation-v0.103-4bits")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RichardErkhov/lemon-mint_-_gemma-2b-translation-v0.103-4bits")
model = AutoModelForCausalLM.from_pretrained("RichardErkhov/lemon-mint_-_gemma-2b-translation-v0.103-4bits", 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 RichardErkhov/lemon-mint_-_gemma-2b-translation-v0.103-4bits with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RichardErkhov/lemon-mint_-_gemma-2b-translation-v0.103-4bits"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RichardErkhov/lemon-mint_-_gemma-2b-translation-v0.103-4bits",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RichardErkhov/lemon-mint_-_gemma-2b-translation-v0.103-4bits

SGLang

How to use RichardErkhov/lemon-mint_-_gemma-2b-translation-v0.103-4bits 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 "RichardErkhov/lemon-mint_-_gemma-2b-translation-v0.103-4bits" \
    --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": "RichardErkhov/lemon-mint_-_gemma-2b-translation-v0.103-4bits",
		"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 "RichardErkhov/lemon-mint_-_gemma-2b-translation-v0.103-4bits" \
        --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": "RichardErkhov/lemon-mint_-_gemma-2b-translation-v0.103-4bits",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RichardErkhov/lemon-mint_-_gemma-2b-translation-v0.103-4bits with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/lemon-mint_-_gemma-2b-translation-v0.103-4bits
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

Github

Discord

Request more models

gemma-2b-translation-v0.103 - bnb 4bits

Model creator: https://huggingface.co/lemon-mint/
Original model: https://huggingface.co/lemon-mint/gemma-2b-translation-v0.103/

Original model description:

library_name: transformers language: - ko license: gemma tags: - gemma - pytorch - instruct - finetune - translation widget: - messages: - role: user content: "Hamsters don't eat cats." inference: parameters: max_new_tokens: 2048 base_model: beomi/gemma-ko-2b datasets: - traintogpb/aihub-flores-koen-integrated-sparta-30k pipeline_tag: text-generation

Gemma 2B Translation v0.103

Eval Loss: 1.34507
Train Loss: 1.40326
lr: 3e-05
optimizer: adamw
lr_scheduler_type: cosine

Prompt Template

<bos>### English

Hamsters don't eat cats.

### Korean

햄스터는 고양이를 먹지 않습니다.<eos>

Model Description

Developed by: lemon-mint
Model type: Gemma
Language(s) (NLP): English
License: gemma-terms-of-use
Finetuned from model: beomi/gemma-ko-2b

Downloads last month: 7

Safetensors

Model size

3B params

Tensor type

F32

F16