Instructions to use SubhrajitSain/anwgpt2-355m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SubhrajitSain/anwgpt2-355m with Transformers:

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

pipe = pipeline("text-generation", model="SubhrajitSain/anwgpt2-355m")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SubhrajitSain/anwgpt2-355m")
model = AutoModelForCausalLM.from_pretrained("SubhrajitSain/anwgpt2-355m")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use SubhrajitSain/anwgpt2-355m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SubhrajitSain/anwgpt2-355m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SubhrajitSain/anwgpt2-355m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SubhrajitSain/anwgpt2-355m

SGLang

How to use SubhrajitSain/anwgpt2-355m 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 "SubhrajitSain/anwgpt2-355m" \
    --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": "SubhrajitSain/anwgpt2-355m",
		"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 "SubhrajitSain/anwgpt2-355m" \
        --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": "SubhrajitSain/anwgpt2-355m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use SubhrajitSain/anwgpt2-355m with Docker Model Runner:
```
docker model run hf.co/SubhrajitSain/anwgpt2-355m
```

anwgpt2-355m

My second attempt at a LLM.

Model Details

Model Type: GPT-2
Model Size: 354,823,168 parameters
Base Model: gpt2-medium
Dataset: Elriggs/openwebtext-100k
Training Framework: Hugging Face Transformers

Intended Use

This model is intended for text generation tasks.

Training

The model was fine-tuned on the Elriggs/openwebtext-100k dataset.

Evaluation

Evaluation was not recorded.

Limitations

May perform repetitions, but very not likely.

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 15

Framework versions

Transformers 4.56.0
Pytorch 2.8.0+cu126
Datasets 2.14.6
Tokenizers 0.22.0

Downloads last month: 2

Safetensors

Model size

0.4B params

Tensor type

F32

Model tree for SubhrajitSain/anwgpt2-355m

Base model

SubhrajitSain/anwgpt2-345m

Finetuned

(1)

this model

Finetunes

1 model

SubhrajitSain
/

anwgpt2-355m