Instructions to use Alignment-Lab-AI/GPT-2-optim with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Alignment-Lab-AI/GPT-2-optim with Transformers:

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

pipe = pipeline("text-generation", model="Alignment-Lab-AI/GPT-2-optim")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Alignment-Lab-AI/GPT-2-optim")
model = AutoModelForCausalLM.from_pretrained("Alignment-Lab-AI/GPT-2-optim")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Alignment-Lab-AI/GPT-2-optim with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Alignment-Lab-AI/GPT-2-optim"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Alignment-Lab-AI/GPT-2-optim",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Alignment-Lab-AI/GPT-2-optim

SGLang

How to use Alignment-Lab-AI/GPT-2-optim 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 "Alignment-Lab-AI/GPT-2-optim" \
    --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": "Alignment-Lab-AI/GPT-2-optim",
		"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 "Alignment-Lab-AI/GPT-2-optim" \
        --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": "Alignment-Lab-AI/GPT-2-optim",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Alignment-Lab-AI/GPT-2-optim with Docker Model Runner:
```
docker model run hf.co/Alignment-Lab-AI/GPT-2-optim
```

Alignment-Lab-AI commited on Oct 11, 2024

Commit

afa516b

verified ·

1 Parent(s): ff2062f

Update config.json

Browse files

Files changed (1) hide show

config.json +2 -2

config.json CHANGED Viewed

@@ -10,12 +10,12 @@
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
-  "n_ctx": 2024,
   "n_embd": 768,
   "n_head": 12,
   "n_inner": null,
   "n_layer": 12,
-  "n_positions": 2024,
   "reorder_and_upcast_attn": true,
   "resid_pdrop": 0.0,
   "scale_attn_by_inverse_layer_idx": true,

   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
+  "n_ctx": 2048,
   "n_embd": 768,
   "n_head": 12,
   "n_inner": null,
   "n_layer": 12,
+  "n_positions": 2048,
   "reorder_and_upcast_attn": true,
   "resid_pdrop": 0.0,
   "scale_attn_by_inverse_layer_idx": true,