Instructions to use hf-tiny-model-private/tiny-random-OpenAIGPTLMHeadModel with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hf-tiny-model-private/tiny-random-OpenAIGPTLMHeadModel with Transformers:

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

pipe = pipeline("text-generation", model="hf-tiny-model-private/tiny-random-OpenAIGPTLMHeadModel")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hf-tiny-model-private/tiny-random-OpenAIGPTLMHeadModel")
model = AutoModelForCausalLM.from_pretrained("hf-tiny-model-private/tiny-random-OpenAIGPTLMHeadModel")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use hf-tiny-model-private/tiny-random-OpenAIGPTLMHeadModel with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/hf-tiny-model-private/tiny-random-OpenAIGPTLMHeadModel

SGLang

How to use hf-tiny-model-private/tiny-random-OpenAIGPTLMHeadModel 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 "hf-tiny-model-private/tiny-random-OpenAIGPTLMHeadModel" \
    --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": "hf-tiny-model-private/tiny-random-OpenAIGPTLMHeadModel",
		"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 "hf-tiny-model-private/tiny-random-OpenAIGPTLMHeadModel" \
        --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": "hf-tiny-model-private/tiny-random-OpenAIGPTLMHeadModel",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hf-tiny-model-private/tiny-random-OpenAIGPTLMHeadModel with Docker Model Runner:
```
docker model run hf.co/hf-tiny-model-private/tiny-random-OpenAIGPTLMHeadModel
```

tiny-random-OpenAIGPTLMHeadModel

File size: 654 Bytes

bc3ef31

{
  "_name_or_path": "tiny_models/openai-gpt/OpenAIGPTLMHeadModel",
  "afn": "gelu",
  "architectures": [
    "OpenAIGPTLMHeadModel"
  ],
  "attn_pdrop": 0.1,
  "embd_pdrop": 0.1,
  "initializer_range": 0.02,
  "is_decoder": true,
  "layer_norm_epsilon": 1e-05,
  "model_type": "openai-gpt",
  "n_embd": 32,
  "n_head": 4,
  "n_layer": 5,
  "n_positions": 512,
  "pad_token_id": 1406,
  "resid_pdrop": 0.1,
  "summary_activation": null,
  "summary_first_dropout": 0.1,
  "summary_proj_to_labels": true,
  "summary_type": "cls_index",
  "summary_use_proj": true,
  "torch_dtype": "float32",
  "transformers_version": "4.28.0.dev0",
  "vocab_size": 1407
}