Instructions to use cvnberk/nsql-350M-finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cvnberk/nsql-350M-finetuned with Transformers:

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

pipe = pipeline("text-generation", model="cvnberk/nsql-350M-finetuned")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cvnberk/nsql-350M-finetuned")
model = AutoModelForCausalLM.from_pretrained("cvnberk/nsql-350M-finetuned")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use cvnberk/nsql-350M-finetuned with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cvnberk/nsql-350M-finetuned"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cvnberk/nsql-350M-finetuned",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/cvnberk/nsql-350M-finetuned

SGLang

How to use cvnberk/nsql-350M-finetuned 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 "cvnberk/nsql-350M-finetuned" \
    --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": "cvnberk/nsql-350M-finetuned",
		"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 "cvnberk/nsql-350M-finetuned" \
        --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": "cvnberk/nsql-350M-finetuned",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use cvnberk/nsql-350M-finetuned with Docker Model Runner:
```
docker model run hf.co/cvnberk/nsql-350M-finetuned
```

YAML Metadata Warning:The pipeline tag "text2text-generation" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, audio-text-to-text, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-ranking, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, image-text-to-image, image-text-to-video, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, visual-document-retrieval, any-to-any, video-to-video, other

nsql-350M-finetuned

This model is a fine-tuned version of NumbersStation/nsql-350M on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.0114

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: 5e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
0.1122	1.0	22	0.0555
0.0564	2.0	44	0.0263
0.0368	3.0	66	0.0222
0.0266	4.0	88	0.0161
0.0267	5.0	110	0.0175
0.0195	6.0	132	0.0153
0.0165	7.0	154	0.0119
0.0145	8.0	176	0.0116
0.0127	9.0	198	0.0123
0.0131	10.0	220	0.0127
0.0122	11.0	242	0.0108
0.0114	12.0	264	0.0112
0.0103	13.0	286	0.0113
0.0099	14.0	308	0.0114

Framework versions

Transformers 4.33.3
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.13.3

Downloads last month: 5

Model tree for cvnberk/nsql-350M-finetuned

Base model

NumbersStation/nsql-350M

Finetuned

(1)

this model