Text Generation
Transformers
Safetensors
English
tinygpt2
causal-lm
instruction-tuned
sft
rope
grouped-query-attention
rms-norm
custom_code
Instructions to use NotShrirang/tinygpt2-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NotShrirang/tinygpt2-it with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="NotShrirang/tinygpt2-it", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("NotShrirang/tinygpt2-it", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use NotShrirang/tinygpt2-it with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "NotShrirang/tinygpt2-it" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "NotShrirang/tinygpt2-it", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/NotShrirang/tinygpt2-it
- SGLang
How to use NotShrirang/tinygpt2-it 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 "NotShrirang/tinygpt2-it" \ --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": "NotShrirang/tinygpt2-it", "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 "NotShrirang/tinygpt2-it" \ --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": "NotShrirang/tinygpt2-it", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use NotShrirang/tinygpt2-it with Docker Model Runner:
docker model run hf.co/NotShrirang/tinygpt2-it
| """HuggingFace-compatible configuration for TinyGPT2 models.""" | |
| from transformers import PretrainedConfig | |
| class TinyGPT2HFConfig(PretrainedConfig): | |
| model_type = "tinygpt2" | |
| def __init__( | |
| self, | |
| vocab_size=50304, | |
| block_size=512, | |
| n_embd=768, | |
| n_head=12, | |
| n_layer=12, | |
| gqa_kv_head=4, | |
| hidden_size=2048, | |
| dropout=0.1, | |
| pad_token_id=50257, | |
| eos_token_id=50256, | |
| bos_token_id=None, | |
| **kwargs, | |
| ): | |
| self.vocab_size = vocab_size | |
| self.block_size = block_size | |
| self.n_embd = n_embd | |
| self.n_head = n_head | |
| self.n_layer = n_layer | |
| self.gqa_kv_head = gqa_kv_head | |
| self.hidden_size = hidden_size | |
| self.dropout = dropout | |
| super().__init__( | |
| pad_token_id=pad_token_id, | |
| eos_token_id=eos_token_id, | |
| bos_token_id=bos_token_id, | |
| **kwargs, | |
| ) | |