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

Libraries

How to use miguelvictor/python-gpt2-large with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use miguelvictor/python-gpt2-large with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "miguelvictor/python-gpt2-large"
# 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-gpt2-large",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/miguelvictor/python-gpt2-large

SGLang

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

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

miguelvictor commited on Apr 29, 2021

Commit

45b5d97

1 Parent(s): 66948ac

added tokenizer config

Browse files

Files changed (4) hide show

config.json +3 -9
merges.txt +0 -0
tokenizer.json +0 -0
vocab.json +0 -0

config.json CHANGED Viewed

@@ -1,15 +1,11 @@
 {
-  "_name_or_path": "gpt2-large",
   "_num_labels": 1,
   "activation_function": "gelu_new",
-  "architectures": [
-    "GPT2LMHeadModel"
-  ],
   "attn_pdrop": 0.1,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
-  "gradient_checkpointing": true,
   "id2label": {
     "0": "LABEL_0"
   },
@@ -17,12 +13,11 @@
   "label2id": {
     "LABEL_0": 0
   },
-  "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 1024,
   "n_embd": 1280,
   "n_head": 20,
-  "n_inner": null,
   "n_layer": 36,
   "n_positions": 1024,
   "resid_pdrop": 0.1,
@@ -33,11 +28,10 @@
   "summary_use_proj": true,
   "task_specific_params": {
     "text-generation": {
-      "do_sample": true,
       "max_length": 50
     }
   },
   "transformers_version": "4.5.1",
-  "use_cache": false,
   "vocab_size": 50257
 }

 {
   "_num_labels": 1,
   "activation_function": "gelu_new",
+  "architectures": ["GPT2LMHeadModel"],
   "attn_pdrop": 0.1,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "id2label": {
     "0": "LABEL_0"
   },
   "label2id": {
     "LABEL_0": 0
   },
+  "layer_norm_epsilon": 1e-5,
   "model_type": "gpt2",
   "n_ctx": 1024,
   "n_embd": 1280,
   "n_head": 20,
   "n_layer": 36,
   "n_positions": 1024,
   "resid_pdrop": 0.1,
   "summary_use_proj": true,
   "task_specific_params": {
     "text-generation": {
+      "do_sample": false,
       "max_length": 50
     }
   },
   "transformers_version": "4.5.1",
   "vocab_size": 50257
 }

merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff