Instructions to use miguelvictor/python-fromzero-gpt2-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use miguelvictor/python-fromzero-gpt2-base with Transformers:

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

pipe = pipeline("text-generation", model="miguelvictor/python-fromzero-gpt2-base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("miguelvictor/python-fromzero-gpt2-base")
model = AutoModelForCausalLM.from_pretrained("miguelvictor/python-fromzero-gpt2-base")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use miguelvictor/python-fromzero-gpt2-base with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/miguelvictor/python-fromzero-gpt2-base

SGLang

How to use miguelvictor/python-fromzero-gpt2-base 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 "miguelvictor/python-fromzero-gpt2-base" \
    --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": "miguelvictor/python-fromzero-gpt2-base",
		"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 "miguelvictor/python-fromzero-gpt2-base" \
        --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": "miguelvictor/python-fromzero-gpt2-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use miguelvictor/python-fromzero-gpt2-base with Docker Model Runner:
```
docker model run hf.co/miguelvictor/python-fromzero-gpt2-base
```

miguelvictor commited on Apr 29, 2021

Commit

bdaa9c8

1 Parent(s): c8abba5

update confgi

Browse files

Files changed (1) hide show

config.json +2 -7

config.json CHANGED Viewed

@@ -1,20 +1,16 @@
 {
   "activation_function": "gelu_new",
-  "architectures": [
-    "GPT2LMHeadModel"
-  ],
   "attn_pdrop": 0.1,
   "bos_token_id": 2,
   "embd_pdrop": 0.1,
   "eos_token_id": 3,
-  "gradient_checkpointing": true,
   "initializer_range": 0.02,
-  "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 1024,
   "n_embd": 768,
   "n_head": 12,
-  "n_inner": null,
   "n_layer": 12,
   "n_positions": 512,
   "pad_token_id": 0,
@@ -26,6 +22,5 @@
   "summary_use_proj": true,
   "tokenizer": "default",
   "transformers_version": "4.5.1",
-  "use_cache": false,
   "vocab_size": 16000
 }

 {
   "activation_function": "gelu_new",
+  "architectures": ["GPT2LMHeadModel"],
   "attn_pdrop": 0.1,
   "bos_token_id": 2,
   "embd_pdrop": 0.1,
   "eos_token_id": 3,
   "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-5,
   "model_type": "gpt2",
   "n_ctx": 1024,
   "n_embd": 768,
   "n_head": 12,
   "n_layer": 12,
   "n_positions": 512,
   "pad_token_id": 0,
   "summary_use_proj": true,
   "tokenizer": "default",
   "transformers_version": "4.5.1",
   "vocab_size": 16000
 }