Instructions to use sarahyo941/UnifiedReward-Think-rejection_sampling_whole with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sarahyo941/UnifiedReward-Think-rejection_sampling_whole with Transformers:

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

pipe = pipeline("text-generation", model="sarahyo941/UnifiedReward-Think-rejection_sampling_whole", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("sarahyo941/UnifiedReward-Think-rejection_sampling_whole", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use sarahyo941/UnifiedReward-Think-rejection_sampling_whole with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sarahyo941/UnifiedReward-Think-rejection_sampling_whole"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sarahyo941/UnifiedReward-Think-rejection_sampling_whole",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sarahyo941/UnifiedReward-Think-rejection_sampling_whole

SGLang

How to use sarahyo941/UnifiedReward-Think-rejection_sampling_whole 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 "sarahyo941/UnifiedReward-Think-rejection_sampling_whole" \
    --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": "sarahyo941/UnifiedReward-Think-rejection_sampling_whole",
		"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 "sarahyo941/UnifiedReward-Think-rejection_sampling_whole" \
        --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": "sarahyo941/UnifiedReward-Think-rejection_sampling_whole",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sarahyo941/UnifiedReward-Think-rejection_sampling_whole with Docker Model Runner:
```
docker model run hf.co/sarahyo941/UnifiedReward-Think-rejection_sampling_whole
```

UnifiedReward-Think-rejection_sampling_whole

This model is a fine-tuned version of OpenGVLab/InternVL3-8B on an unknown dataset.

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: 1e-05
train_batch_size: 1
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 8
total_train_batch_size: 64
total_eval_batch_size: 64
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3.0

Training results

Framework versions

Transformers 4.56.0.dev0
Pytorch 2.8.0+cu126
Datasets 3.6.0
Tokenizers 0.21.1

Downloads last month: 1

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for sarahyo941/UnifiedReward-Think-rejection_sampling_whole

Base model

OpenGVLab/InternVL3-8B-Pretrained

Finetuned

OpenGVLab/InternVL3-8B-Instruct

Finetuned

OpenGVLab/InternVL3-8B

Finetuned

(30)

this model