Instructions to use mikegarts/distilgpt2-lotr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mikegarts/distilgpt2-lotr with Transformers:

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

pipe = pipeline("text-generation", model="mikegarts/distilgpt2-lotr")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mikegarts/distilgpt2-lotr")
model = AutoModelForCausalLM.from_pretrained("mikegarts/distilgpt2-lotr")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mikegarts/distilgpt2-lotr with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mikegarts/distilgpt2-lotr"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mikegarts/distilgpt2-lotr",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mikegarts/distilgpt2-lotr

SGLang

How to use mikegarts/distilgpt2-lotr 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 "mikegarts/distilgpt2-lotr" \
    --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": "mikegarts/distilgpt2-lotr",
		"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 "mikegarts/distilgpt2-lotr" \
        --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": "mikegarts/distilgpt2-lotr",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mikegarts/distilgpt2-lotr with Docker Model Runner:
```
docker model run hf.co/mikegarts/distilgpt2-lotr
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

distilgpt2-lotr

This model is a fine-tuned version of distilgpt2 on the None dataset. It achieves the following results on the evaluation set:

Loss: 3.3901

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: 64
eval_batch_size: 64
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 15
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	73	3.6392
No log	2.0	146	3.5466
No log	3.0	219	3.5038
No log	4.0	292	3.4761
No log	5.0	365	3.4546
No log	6.0	438	3.4379
3.6024	7.0	511	3.4265
3.6024	8.0	584	3.4160
3.6024	9.0	657	3.4096
3.6024	10.0	730	3.4025
3.6024	11.0	803	3.3969
3.6024	12.0	876	3.3933
3.6024	13.0	949	3.3916
3.4101	14.0	1022	3.3910
3.4101	15.0	1095	3.3901

Framework versions

Transformers 4.20.1
Pytorch 1.11.0
Datasets 2.1.0
Tokenizers 0.12.1

Downloads last month: 4

Safetensors

Model size

88.2M params

Tensor type

F32

Model tree for mikegarts/distilgpt2-lotr

Quantizations

2 models

mikegarts
/

distilgpt2-lotr

distilgpt2-lotr

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for mikegarts/distilgpt2-lotr

Spaces using mikegarts/distilgpt2-lotr 2