Text Generation
Transformers
PyTorch
TensorFlow
code
gpt2
Code
GPyT
code generator
text-generation-inference
Instructions to use Sentdex/GPyT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Sentdex/GPyT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Sentdex/GPyT")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Sentdex/GPyT") model = AutoModelForCausalLM.from_pretrained("Sentdex/GPyT") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Sentdex/GPyT with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Sentdex/GPyT" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Sentdex/GPyT", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Sentdex/GPyT
- SGLang
How to use Sentdex/GPyT 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 "Sentdex/GPyT" \ --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": "Sentdex/GPyT", "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 "Sentdex/GPyT" \ --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": "Sentdex/GPyT", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Sentdex/GPyT with Docker Model Runner:
docker model run hf.co/Sentdex/GPyT
add model
Browse files- config.json +1 -1
- tf_model.h5 +3 -0
config.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
"_name_or_path": "GPyT_source/checkpoint-10600",
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
-
"
|
| 6 |
],
|
| 7 |
"attn_pdrop": 0.1,
|
| 8 |
"bos_token_id": 0,
|
|
|
|
| 2 |
"_name_or_path": "GPyT_source/checkpoint-10600",
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
],
|
| 7 |
"attn_pdrop": 0.1,
|
| 8 |
"bos_token_id": 0,
|
tf_model.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6aaeb338d7c4dffe5e1e0bba4d99fd6cc85a984117fe3d5a7eaeafde9ef7e73
|
| 3 |
+
size 503288144
|