Instructions to use raincandy-u/Coder1.8-ORPO-TEST with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use raincandy-u/Coder1.8-ORPO-TEST with Transformers:

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

pipe = pipeline("text-generation", model="raincandy-u/Coder1.8-ORPO-TEST")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("raincandy-u/Coder1.8-ORPO-TEST")
model = AutoModelForCausalLM.from_pretrained("raincandy-u/Coder1.8-ORPO-TEST")
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

vLLM

How to use raincandy-u/Coder1.8-ORPO-TEST with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "raincandy-u/Coder1.8-ORPO-TEST"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "raincandy-u/Coder1.8-ORPO-TEST",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/raincandy-u/Coder1.8-ORPO-TEST

SGLang

How to use raincandy-u/Coder1.8-ORPO-TEST 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 "raincandy-u/Coder1.8-ORPO-TEST" \
    --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": "raincandy-u/Coder1.8-ORPO-TEST",
		"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 "raincandy-u/Coder1.8-ORPO-TEST" \
        --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": "raincandy-u/Coder1.8-ORPO-TEST",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use raincandy-u/Coder1.8-ORPO-TEST with Docker Model Runner:
```
docker model run hf.co/raincandy-u/Coder1.8-ORPO-TEST
```

Coder1.8-ORPO-TEST

Model Description

Test model for ORPO finetune method, trained on ~20k code examples for 1 epoch on 2 x A40 cards with 4-bit QLora (lora rank=lora alpha=16).

Disclaimer

This is a test model and may generate incorrect responses. Use at your own risk.

Train Details

Base: Qwen1.5-1.8B
Training Data: ~20k code examples
Epochs: 1
Method: ORPO
Hardware: 2 x A40
Quantization: 4-bit QLora
Lora Rank/Alpha: 16

Limitations

Limited training data and quantization may impact performance.

Join the Discussion

Have questions or feedback? Join our Discord server Here.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	45.76
AI2 Reasoning Challenge (25-Shot)	38.82
HellaSwag (10-Shot)	60.48
MMLU (5-Shot)	46.70
TruthfulQA (0-shot)	41.38
Winogrande (5-shot)	59.75
GSM8k (5-shot)	27.45

Downloads last month: 12

Safetensors

Model size

2B params

Tensor type

BF16

Dataset used to train raincandy-u/Coder1.8-ORPO-TEST

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

38.820
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

60.480
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

46.700
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

41.380
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

59.750
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

27.450