Instructions to use zfz1/deepseek-8b-orpo-full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zfz1/deepseek-8b-orpo-full with Transformers:

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

pipe = pipeline("text-generation", model="zfz1/deepseek-8b-orpo-full")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("zfz1/deepseek-8b-orpo-full")
model = AutoModelForMultimodalLM.from_pretrained("zfz1/deepseek-8b-orpo-full")
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 zfz1/deepseek-8b-orpo-full with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zfz1/deepseek-8b-orpo-full"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zfz1/deepseek-8b-orpo-full",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zfz1/deepseek-8b-orpo-full

SGLang

How to use zfz1/deepseek-8b-orpo-full 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 "zfz1/deepseek-8b-orpo-full" \
    --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": "zfz1/deepseek-8b-orpo-full",
		"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 "zfz1/deepseek-8b-orpo-full" \
        --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": "zfz1/deepseek-8b-orpo-full",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zfz1/deepseek-8b-orpo-full with Docker Model Runner:
```
docker model run hf.co/zfz1/deepseek-8b-orpo-full
```

deepseek-8b-orpo-full

This model is a fine-tuned version of deepseek-ai/deepseek-math-7b-base on the zfz1/my_preference_gsm8k_deepseek dataset. It achieves the following results on the evaluation set:

Loss: 0.0797
Rewards/chosen: -0.0089
Rewards/rejected: -0.2196
Rewards/accuracies: 1.0
Rewards/margins: 0.2107
Logps/rejected: -2.1960
Logps/chosen: -0.0885
Logits/rejected: 13.8906
Logits/chosen: 8.5947
Nll Loss: 0.0786
Log Odds Ratio: -0.0204
Log Odds Chosen: 5.3533

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 4
eval_batch_size: 4
seed: 43
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 2
total_train_batch_size: 32
total_eval_batch_size: 16
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

Training results

Framework versions

Transformers 4.42.3
Pytorch 2.1.2
Datasets 2.20.0
Tokenizers 0.19.1

Downloads last month: 2

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for zfz1/deepseek-8b-orpo-full

Base model

deepseek-ai/deepseek-math-7b-base

Finetuned

(25)

this model

zfz1
/

deepseek-8b-orpo-full

deepseek-8b-orpo-full

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for zfz1/deepseek-8b-orpo-full

Dataset used to train zfz1/deepseek-8b-orpo-full