Instructions to use qing-yao/strict_default_seed-42_1e-3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use qing-yao/strict_default_seed-42_1e-3 with Transformers:

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

pipe = pipeline("text-generation", model="qing-yao/strict_default_seed-42_1e-3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("qing-yao/strict_default_seed-42_1e-3")
model = AutoModelForCausalLM.from_pretrained("qing-yao/strict_default_seed-42_1e-3")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use qing-yao/strict_default_seed-42_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/strict_default_seed-42_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/strict_default_seed-42_1e-3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/qing-yao/strict_default_seed-42_1e-3

SGLang

How to use qing-yao/strict_default_seed-42_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/strict_default_seed-42_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/strict_default_seed-42_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/strict_default_seed-42_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/strict_default_seed-42_1e-3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use qing-yao/strict_default_seed-42_1e-3 with Docker Model Runner:
```
docker model run hf.co/qing-yao/strict_default_seed-42_1e-3
```

strict_default_seed-42_1e-3

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

Loss: 3.1745
Accuracy: 0.4018

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: 42
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
6.0064	0.9999	1487	4.4126	0.2930
4.3103	1.9998	2974	3.9046	0.3325
3.6991	2.9997	4461	3.6229	0.3568
3.5294	3.9997	5948	3.4607	0.3715
3.3076	4.9996	7435	3.3641	0.3808
3.2332	5.9995	8922	3.3050	0.3861
3.1276	6.9994	10409	3.2629	0.3906
3.0896	8.0	11897	3.2390	0.3928
3.0274	8.9999	13384	3.2226	0.3948
3.0011	9.9998	14871	3.2100	0.3964
2.9651	10.9997	16358	3.2051	0.3974
2.9434	11.9997	17845	3.1928	0.3986
2.923	12.9996	19332	3.1911	0.3990
2.9066	13.9995	20819	3.1861	0.3999
2.8952	14.9994	22306	3.1889	0.4001
2.8778	16.0	23794	3.1797	0.4002
2.8761	16.9999	25281	3.1794	0.4008
2.8585	17.9998	26768	3.1805	0.4009
2.8646	18.9997	28255	3.1781	0.4016
2.8442	19.9983	29740	3.1745	0.4018

Framework versions

Transformers 4.46.2
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.20.0

Downloads last month: -

Safetensors

Model size

0.1B params

Tensor type

F32