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

Libraries

How to use Fmirra/gpt2-python-singleline with Transformers:

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

pipe = pipeline("text-generation", model="Fmirra/gpt2-python-singleline")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Fmirra/gpt2-python-singleline")
model = AutoModelForCausalLM.from_pretrained("Fmirra/gpt2-python-singleline")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Fmirra/gpt2-python-singleline with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Fmirra/gpt2-python-singleline

SGLang

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

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

Fmirra commited on Aug 1, 2023

Commit

25804b6

1 Parent(s): 277cd52

Upload model

Browse files

Files changed (2) hide show

config.json +9 -2
pytorch_model.bin +2 -2

config.json CHANGED Viewed

@@ -1,5 +1,6 @@
 {
-  "_name_or_path": "gpt2",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -8,14 +9,20 @@
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "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": 1024,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,

 {
+  "_name_or_path": "distilgpt2",
+  "_num_labels": 1,
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
+  "id2label": {
+    "0": "LABEL_0"
+  },
   "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 1024,
   "n_embd": 768,
   "n_head": 12,
   "n_inner": null,
+  "n_layer": 6,
   "n_positions": 1024,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a97aa2d5715a2a4a597e4f205acd651ae40a4498a93367a6be83c92c507d8071
-size 497807197

 version https://git-lfs.github.com/spec/v1
+oid sha256:dc307793216b53f00c44c15c24a9b48a7f1ddcfd8a71aeddab0653cd0df4bb7e
+size 327674773