Instructions to use GunA-SD/gpt2_small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use GunA-SD/gpt2_small with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="GunA-SD/gpt2_small")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("GunA-SD/gpt2_small") model = AutoModelForCausalLM.from_pretrained("GunA-SD/gpt2_small") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use GunA-SD/gpt2_small with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "GunA-SD/gpt2_small" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "GunA-SD/gpt2_small", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/GunA-SD/gpt2_small
- SGLang
How to use GunA-SD/gpt2_small 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 "GunA-SD/gpt2_small" \ --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": "GunA-SD/gpt2_small", "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 "GunA-SD/gpt2_small" \ --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": "GunA-SD/gpt2_small", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use GunA-SD/gpt2_small with Docker Model Runner:
docker model run hf.co/GunA-SD/gpt2_small
gunasekar commited on
Commit ·
e1cfaac
1
Parent(s): 0f8dcb4
Upload model
Browse files- config.json +1 -1
- pytorch_model.bin +3 -0
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "/home/guna/projects/gpt/picoGPT/models/trained_82K",
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "/home/guna/projects/gpt/picoGPT/models/trained_82K/",
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e66f7a31a2a53568800711424c06b1ec7ea79438631fdcb7f59b919c4176cf54
|
| 3 |
+
size 497805149
|