Instructions to use DeathReaper0965/gpt2-large-code-generator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DeathReaper0965/gpt2-large-code-generator with Transformers:

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

pipe = pipeline("text-generation", model="DeathReaper0965/gpt2-large-code-generator")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DeathReaper0965/gpt2-large-code-generator")
model = AutoModelForCausalLM.from_pretrained("DeathReaper0965/gpt2-large-code-generator", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DeathReaper0965/gpt2-large-code-generator with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DeathReaper0965/gpt2-large-code-generator"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DeathReaper0965/gpt2-large-code-generator",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/DeathReaper0965/gpt2-large-code-generator

SGLang

How to use DeathReaper0965/gpt2-large-code-generator 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 "DeathReaper0965/gpt2-large-code-generator" \
    --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": "DeathReaper0965/gpt2-large-code-generator",
		"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 "DeathReaper0965/gpt2-large-code-generator" \
        --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": "DeathReaper0965/gpt2-large-code-generator",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use DeathReaper0965/gpt2-large-code-generator with Docker Model Runner:
```
docker model run hf.co/DeathReaper0965/gpt2-large-code-generator
```

DeathReaper0965 commited on Aug 28, 2023

Commit

223d8fa

1 Parent(s): 4147583

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -2

README.md CHANGED Viewed

@@ -16,7 +16,6 @@ widget:
 inference:
   parameters:
     max_new_tokens: 30
-    temperature: 0.5
     num_return_sequences: 1
 ---
@@ -49,7 +48,6 @@ inputs = tokenizer("def hello_world():", return_tensors="pt").to("cuda" if torch
 outputs = model.generate(**inputs,
                          max_new_tokens= 30,
-                         temperature= 0.5,
                          num_return_sequences= 1)
 print(tokenizer.batch_decode(outputs)[0])

 inference:
   parameters:
     max_new_tokens: 30
     num_return_sequences: 1
 ---
 outputs = model.generate(**inputs,
                          max_new_tokens= 30,
                          num_return_sequences= 1)
 print(tokenizer.batch_decode(outputs)[0])