Instructions to use dusersad12/BestRewardModel-TestRepo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dusersad12/BestRewardModel-TestRepo with Transformers:

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

pipe = pipeline("text-generation", model="dusersad12/BestRewardModel-TestRepo")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dusersad12/BestRewardModel-TestRepo")
model = AutoModelForCausalLM.from_pretrained("dusersad12/BestRewardModel-TestRepo", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dusersad12/BestRewardModel-TestRepo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dusersad12/BestRewardModel-TestRepo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dusersad12/BestRewardModel-TestRepo",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/dusersad12/BestRewardModel-TestRepo

SGLang

How to use dusersad12/BestRewardModel-TestRepo 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 "dusersad12/BestRewardModel-TestRepo" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dusersad12/BestRewardModel-TestRepo",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "dusersad12/BestRewardModel-TestRepo" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dusersad12/BestRewardModel-TestRepo",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use dusersad12/BestRewardModel-TestRepo with Docker Model Runner:
```
docker model run hf.co/dusersad12/BestRewardModel-TestRepo
```

BestRewardModel

Model Description

This is a reward model trained for RLHF alignment, selected from multiple experimental runs based on validation accuracy and reward alignment quality.

Selection Criteria

The best checkpoint was chosen according to:

Highest val_accuracy among all final checkpoints
Minimum reward_alignment_score threshold of 0.80

Only checkpoints satisfying both conditions were eligible.

Training Runs Comparison

Run	Base Model	Learning Rate	Final Step	Val Accuracy	Reward Alignment	Train Loss
run_gpt2_base_lr1e4	GPT-2 Base	1e-4	1000	0.907	0.876	0.115
run_gpt2_base_lr5e5	GPT-2 Base	5e-5	1000	0.870	0.839	0.207
run_gpt2_large_lr1e4	GPT-2 Large	1e-4	1000	0.958	0.928	0.061
run_gpt2_large_lr5e5	GPT-2 Large	5e-5	1000	0.901	0.854	0.159
run_deberta_lr1e4	DeBERTa-v2	1e-4	1000	0.837	0.827	0.301

Best Run Metrics

Metric	Value
Run Name	run_gpt2_large_lr1e4
Val Accuracy	0.958
Reward Alignment Score	0.928
Final Train Loss	0.061

Intended Uses

This model is intended for use as a reward model in RLHF pipelines to score and rank model outputs based on human preference alignment.

How to Use

from transformers import AutoModelForSequenceClassification, AutoTokenizer

model = AutoModelForSequenceClassification.from_pretrained("BestRewardModel-TestRepo")
tokenizer = AutoTokenizer.from_pretrained("BestRewardModel-TestRepo")

inputs = tokenizer("prompt", "response", return_tensors="pt")
score = model(**inputs).logits[0].item()

License

Apache-2.0

Downloads last month: 48