Instructions to use qing-yao/loose_default_seed-21_1e-3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use qing-yao/loose_default_seed-21_1e-3 with Transformers:

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

pipe = pipeline("text-generation", model="qing-yao/loose_default_seed-21_1e-3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("qing-yao/loose_default_seed-21_1e-3")
model = AutoModelForCausalLM.from_pretrained("qing-yao/loose_default_seed-21_1e-3", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use qing-yao/loose_default_seed-21_1e-3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "qing-yao/loose_default_seed-21_1e-3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "qing-yao/loose_default_seed-21_1e-3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/qing-yao/loose_default_seed-21_1e-3

SGLang

How to use qing-yao/loose_default_seed-21_1e-3 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 "qing-yao/loose_default_seed-21_1e-3" \
    --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": "qing-yao/loose_default_seed-21_1e-3",
		"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 "qing-yao/loose_default_seed-21_1e-3" \
        --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": "qing-yao/loose_default_seed-21_1e-3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use qing-yao/loose_default_seed-21_1e-3 with Docker Model Runner:
```
docker model run hf.co/qing-yao/loose_default_seed-21_1e-3
```

loose_default_seed-21_1e-3

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 3.1836
Accuracy: 0.4005

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: 0.001
train_batch_size: 32
eval_batch_size: 64
seed: 21
gradient_accumulation_steps: 8
total_train_batch_size: 256
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 32000
num_epochs: 20.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
5.9844	0.9994	1486	4.4074	0.2933
4.3022	1.9997	2973	3.9034	0.3327
3.697	2.9992	4459	3.6258	0.3561
3.53	3.9995	5946	3.4658	0.3714
3.3054	4.9997	7433	3.3659	0.3803
3.2341	5.9993	8919	3.3071	0.3865
3.1272	6.9996	10406	3.2656	0.3905
3.0899	7.9998	11893	3.2438	0.3925
3.0287	8.9994	13379	3.2261	0.3945
3.0027	9.9997	14866	3.2144	0.3960
2.9661	10.9992	16352	3.2085	0.3971
2.9466	11.9995	17839	3.2058	0.3974
2.9257	12.9997	19326	3.1978	0.3985
2.9051	13.9993	20812	3.1924	0.3993
2.8976	14.9996	22299	3.1898	0.3994
2.8773	15.9998	23786	3.1867	0.3999
2.8773	16.9994	25272	3.1824	0.4003
2.8598	17.9997	26759	3.1903	0.4000
2.8661	18.9992	28245	3.1883	0.4006
2.8457	19.9914	29720	3.1836	0.4005

Framework versions

Transformers 4.46.2
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.20.0

Downloads last month: 10

Safetensors

Model size

0.1B params

Tensor type

F32