Instructions to use morningstarxcdcode/adaption-opus-100-translation-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use morningstarxcdcode/adaption-opus-100-translation-model with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("google/gemma-4-31B-it")
model = PeftModel.from_pretrained(base_model, "morningstarxcdcode/adaption-opus-100-translation-model")

Transformers

How to use morningstarxcdcode/adaption-opus-100-translation-model with Transformers:

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

pipe = pipeline("text-generation", model="morningstarxcdcode/adaption-opus-100-translation-model")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("morningstarxcdcode/adaption-opus-100-translation-model")
model = AutoModelForMultimodalLM.from_pretrained("morningstarxcdcode/adaption-opus-100-translation-model", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use morningstarxcdcode/adaption-opus-100-translation-model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "morningstarxcdcode/adaption-opus-100-translation-model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "morningstarxcdcode/adaption-opus-100-translation-model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/morningstarxcdcode/adaption-opus-100-translation-model

SGLang

How to use morningstarxcdcode/adaption-opus-100-translation-model 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 "morningstarxcdcode/adaption-opus-100-translation-model" \
    --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": "morningstarxcdcode/adaption-opus-100-translation-model",
		"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 "morningstarxcdcode/adaption-opus-100-translation-model" \
        --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": "morningstarxcdcode/adaption-opus-100-translation-model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use morningstarxcdcode/adaption-opus-100-translation-model with Docker Model Runner:
```
docker model run hf.co/morningstarxcdcode/adaption-opus-100-translation-model
```

Adaption OPUS 100 Translation SFT 31B

LoRA adapter fine-tuned on OPUS 100-language parallel corpora for machine translation using Adaption's AutoScientist platform.

Model Details

Base model: google/gemma-4-31B-it (31B parameters)
Adapter: LoRA rank 16, alpha 32, targeting q_proj and v_proj
Training data: 20,000 parallel translation pairs from OPUS (100 languages, primarily paired with English)
Training: 3 epochs, 81 steps
Languages: Arabic-English, French-English, Chinese-English, and 97 more

Training Results

Metric	Before	After
Quality	2.0	5.9 (+195.0%)
Grade	E	C
Percentile	0.1	7.2
Win Rate	46%	54%

How to Use

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base_model = AutoModelForCausalLM.from_pretrained(
    "google/gemma-4-31B-it",
    torch_dtype="bfloat16",
    device_map="auto"
)
model = PeftModel.from_pretrained(base_model, "morningstarxcdcode/adaption-opus-100-translation-model")
tokenizer = AutoTokenizer.from_pretrained("morningstarxcdcode/adaption-opus-100-translation-model")

inputs = tokenizer("Translate to French: The weather is nice today.", return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Team

Sourav Rajak, Priyanshu Tomar, Roshan G, Vivek Rajput

Part of the AutoScientist Challenge — Healthcare, Finance, Language, Legal, and Marketing tracks.

Downloads last month: 1

Model tree for morningstarxcdcode/adaption-opus-100-translation-model

Base model

google/gemma-4-31B

Finetuned

google/gemma-4-31B-it

Adapter

(304)

this model