Instructions to use Felita/midi_nGram_model_1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Felita/midi_nGram_model_1 with Transformers:

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

pipe = pipeline("text-generation", model="Felita/midi_nGram_model_1")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Felita/midi_nGram_model_1")
model = AutoModelForCausalLM.from_pretrained("Felita/midi_nGram_model_1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Felita/midi_nGram_model_1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Felita/midi_nGram_model_1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Felita/midi_nGram_model_1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Felita/midi_nGram_model_1

SGLang

How to use Felita/midi_nGram_model_1 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 "Felita/midi_nGram_model_1" \
    --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": "Felita/midi_nGram_model_1",
		"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 "Felita/midi_nGram_model_1" \
        --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": "Felita/midi_nGram_model_1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Felita/midi_nGram_model_1 with Docker Model Runner:
```
docker model run hf.co/Felita/midi_nGram_model_1
```

midi_nGram_model_1

This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.4755

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: 0.0005
train_batch_size: 4
eval_batch_size: 2
seed: 1
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.01
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
0.6287	0.3319	300	0.6577
0.6573	0.6637	600	0.6499
0.6555	0.9956	900	0.6492
0.6367	1.3274	1200	0.6387
0.6376	1.6593	1500	0.6290
0.6321	1.9912	1800	0.6259
0.6125	2.3230	2100	0.6171
0.6129	2.6549	2400	0.6081
0.6055	2.9867	2700	0.5928
0.5802	3.3186	3000	0.5890
0.5831	3.6504	3300	0.5779
0.5735	3.9823	3600	0.5668
0.5448	4.3142	3900	0.5566
0.5443	4.6460	4200	0.5482
0.5357	4.9779	4500	0.5364
0.5068	5.3097	4800	0.5340
0.5028	5.6416	5100	0.5210
0.497	5.9735	5400	0.5125
0.4683	6.3053	5700	0.5069
0.4657	6.6372	6000	0.4984
0.4589	6.9690	6300	0.4911
0.4336	7.3009	6600	0.4904
0.4319	7.6327	6900	0.4849
0.4274	7.9646	7200	0.4802
0.4106	8.2965	7500	0.4808
0.4093	8.6283	7800	0.4775
0.4059	8.9602	8100	0.4760
0.3974	9.2920	8400	0.4755
0.3969	9.6239	8700	0.4756
0.3928	9.9558	9000	0.4755

Framework versions

Transformers 4.46.3
Pytorch 2.5.1+cu121
Datasets 3.2.0
Tokenizers 0.20.3

Downloads last month: 14

Safetensors

Model size

19.2M params

Tensor type

F32

Model tree for Felita/midi_nGram_model_1

Base model

openai-community/gpt2

Finetuned

(2299)

this model