Instructions to use aisuko/ft-openelm-270m-ultrafeedback with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aisuko/ft-openelm-270m-ultrafeedback with Transformers:

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

pipe = pipeline("text-generation", model="aisuko/ft-openelm-270m-ultrafeedback", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("aisuko/ft-openelm-270m-ultrafeedback", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use aisuko/ft-openelm-270m-ultrafeedback with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aisuko/ft-openelm-270m-ultrafeedback"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aisuko/ft-openelm-270m-ultrafeedback",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/aisuko/ft-openelm-270m-ultrafeedback

SGLang

How to use aisuko/ft-openelm-270m-ultrafeedback 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 "aisuko/ft-openelm-270m-ultrafeedback" \
    --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": "aisuko/ft-openelm-270m-ultrafeedback",
		"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 "aisuko/ft-openelm-270m-ultrafeedback" \
        --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": "aisuko/ft-openelm-270m-ultrafeedback",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use aisuko/ft-openelm-270m-ultrafeedback with Docker Model Runner:
```
docker model run hf.co/aisuko/ft-openelm-270m-ultrafeedback
```

ft-openelm-270m-ultrafeedback

This model is a fine-tuned version of apple/OpenELM-270M on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set:

Loss: 1.6455
Rewards/chosen: -0.1995
Rewards/rejected: -0.2029
Rewards/accuracies: 0.5050
Rewards/margins: 0.0035
Logps/rejected: -2.0293
Logps/chosen: -1.9941
Logits/rejected: -5.7383
Logits/chosen: -6.1055
Nll Loss: 1.5752
Log Odds Ratio: -0.7037
Log Odds Chosen: 0.0445

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: 8e-06
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen	Nll Loss	Log Odds Ratio	Log Odds Chosen
1.7595	0.53	100	1.6455	-0.1995	-0.2029	0.5050	0.0035	-2.0293	-1.9941	-5.7383	-6.1055	1.5752	-0.7037	0.0445

Framework versions

Transformers 4.39.3
Pytorch 2.1.2
Datasets 2.18.0
Tokenizers 0.15.2

Downloads last month: 5

Safetensors

Model size

0.3B params

Tensor type

F16

Model tree for aisuko/ft-openelm-270m-ultrafeedback

Base model

apple/OpenELM-270M

Finetuned

(5)

this model