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, dtype="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 / README.md

MathGenie

Update README.md

c8da03c verified about 2 years ago

preview code

Raw

History Blame Contribute Delete

1.85 kB

metadata

base_model: InternLM2-SFT
tags:
  - math
model-index:
  - name: InternLM2-SFT-SCDPO
    results: []
license: apache-2.0
language:
  - en
metrics:
  - accuracy
pipeline_tag: text-generation

InternLM2-SFT-SCDPO

This model is a fine-tuned version of the InternLM2-20B model using SFT and SCDPO. It achieves the following results on the evaluation set:

Loss: 0.2572
Rewards/chosen: 0.7366
Rewards/rejected: -2.9817
Rewards/accuracies: 0.8929
Rewards/margins: 3.7183
Logps/rejected: -155.1884
Logps/chosen: -92.5904
Logits/rejected: -2.3032
Logits/chosen: -2.4880

Model description

This is a model fine-tuned for mathematical problem-solving.

Intended uses & limitations

The model is intended for solving math problems.

Training and evaluation data

	gsm8k	math	ape	cmath	mgsm_zh
InternLM2-SFT	86.4	55.8	77.1	88.4	74.8
InternLM2-SFT-DPO	87	57.6	78.7	89.9	76
InternLM2-SFT-DPO (data-equal)	88.2	57.5	78.8	89.3	76
InternLM2-SFT-SCDPO	88.5	58.1	79.3	90.3	80.4

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1.5e-07
train_batch_size: 2
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 16
total_train_batch_size: 32
total_eval_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 2

Framework versions

Transformers 4.38.2
Pytorch 2.1.2
Datasets 2.14.6
Tokenizers 0.15.2