Instructions to use MathGenie/InternLM2-SFT-SCDPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MathGenie/InternLM2-SFT-SCDPO with Transformers:

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

pipe = pipeline("text-generation", model="MathGenie/InternLM2-SFT-SCDPO", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("MathGenie/InternLM2-SFT-SCDPO", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MathGenie/InternLM2-SFT-SCDPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MathGenie/InternLM2-SFT-SCDPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MathGenie/InternLM2-SFT-SCDPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MathGenie/InternLM2-SFT-SCDPO

SGLang

How to use MathGenie/InternLM2-SFT-SCDPO 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 "MathGenie/InternLM2-SFT-SCDPO" \
    --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": "MathGenie/InternLM2-SFT-SCDPO",
		"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 "MathGenie/InternLM2-SFT-SCDPO" \
        --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": "MathGenie/InternLM2-SFT-SCDPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MathGenie/InternLM2-SFT-SCDPO with Docker Model Runner:
```
docker model run hf.co/MathGenie/InternLM2-SFT-SCDPO
```

InternLM2-SFT-SCDPO / all_results.json

luzimu

first commit

cca2d4e about 2 years ago

Raw

History Blame Contribute Delete

742 Bytes

	{
	"epoch": 2.0,
	"eval_logits/chosen": -2.4878430366516113,
	"eval_logits/rejected": -2.303501605987549,
	"eval_logps/chosen": -92.59371185302734,
	"eval_logps/rejected": -155.12913513183594,
	"eval_loss": 0.2571355104446411,
	"eval_rewards/accuracies": 0.8928571343421936,
	"eval_rewards/chosen": 0.7362550497055054,
	"eval_rewards/margins": 3.712023973464966,
	"eval_rewards/rejected": -2.975768804550171,
	"eval_runtime": 71.4209,
	"eval_samples": 890,
	"eval_samples_per_second": 12.461,
	"eval_steps_per_second": 0.196,
	"train_loss": 0.2711078498627443,
	"train_runtime": 49070.973,
	"train_samples": 88135,
	"train_samples_per_second": 3.592,
	"train_steps_per_second": 0.112
	}