Instructions to use coolmaksat/otuformer32 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use coolmaksat/otuformer32 with Transformers:

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

pipe = pipeline("text-generation", model="coolmaksat/otuformer32")

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

tokenizer = AutoTokenizer.from_pretrained("coolmaksat/otuformer32")
model = AutoModelForCausalLM.from_pretrained("coolmaksat/otuformer32", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use coolmaksat/otuformer32 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "coolmaksat/otuformer32"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "coolmaksat/otuformer32",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/coolmaksat/otuformer32

SGLang

How to use coolmaksat/otuformer32 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 "coolmaksat/otuformer32" \
    --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": "coolmaksat/otuformer32",
		"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 "coolmaksat/otuformer32" \
        --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": "coolmaksat/otuformer32",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use coolmaksat/otuformer32 with Docker Model Runner:
```
docker model run hf.co/coolmaksat/otuformer32
```

otuformer32

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

Loss: 3.6267

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: 2e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 32

Training results

Training Loss	Epoch	Step	Validation Loss
4.3522	1.0	19103	4.2848
4.1331	2.0	38206	4.0580
3.9926	3.0	57309	3.9385
3.8894	4.0	76412	3.8598
3.8241	5.0	95515	3.8064
3.7619	6.0	114618	3.7661
3.7111	7.0	133721	3.7354
3.6472	8.0	152824	3.7080
3.6201	9.0	171927	3.6930
3.5723	10.0	191030	3.6744
3.5426	11.0	210133	3.6611
3.4896	12.0	229236	3.6528
3.4649	13.0	248339	3.6462
3.4489	14.0	267442	3.6393
3.4087	15.0	286545	3.6331
3.3864	16.0	305648	3.6292
3.3619	17.0	324751	3.6267
3.3456	18.0	343854	3.6241
3.303	19.0	362957	3.6234
3.2988	20.0	382060	3.6202
3.2748	21.0	401163	3.6217
3.245	22.0	420266	3.6219
3.2191	23.0	439369	3.6204
3.2025	24.0	458472	3.6215
3.1865	25.0	477575	3.6220
3.1822	26.0	496678	3.6230
3.1517	27.0	515781	3.6226
3.1351	28.0	534884	3.6243
3.1255	29.0	553987	3.6253
3.1096	30.0	573090	3.6254
3.0966	31.0	592193	3.6264
3.0827	32.0	611296	3.6267

Framework versions

Transformers 4.37.2
Pytorch 2.0.1+cu117
Datasets 2.16.1
Tokenizers 0.15.1

Downloads last month: 10

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for coolmaksat/otuformer32

Base model

openai-community/gpt2

Finetuned

(2291)

this model