Instructions to use hsultanbey/pycodegpt_trainer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hsultanbey/pycodegpt_trainer with Transformers:

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

pipe = pipeline("text-generation", model="hsultanbey/pycodegpt_trainer")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hsultanbey/pycodegpt_trainer")
model = AutoModelForCausalLM.from_pretrained("hsultanbey/pycodegpt_trainer")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use hsultanbey/pycodegpt_trainer with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/hsultanbey/pycodegpt_trainer

SGLang

How to use hsultanbey/pycodegpt_trainer 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 "hsultanbey/pycodegpt_trainer" \
    --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": "hsultanbey/pycodegpt_trainer",
		"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 "hsultanbey/pycodegpt_trainer" \
        --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": "hsultanbey/pycodegpt_trainer",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hsultanbey/pycodegpt_trainer with Docker Model Runner:
```
docker model run hf.co/hsultanbey/pycodegpt_trainer
```

hsultanbey commited on Jul 22, 2023

Commit

a2894b6

1 Parent(s): 9fa4baa

Upload GPTNeoForCausalLM

Browse files

Files changed (3) hide show

config.json +1 -1
generation_config.json +1 -1
pytorch_model.bin +1 -1

config.json CHANGED Viewed

@@ -48,7 +48,7 @@
   "summary_type": "cls_index",
   "summary_use_proj": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.30.2",
   "use_cache": true,
   "vocab_size": 32000,
   "window_size": 256

   "summary_type": "cls_index",
   "summary_use_proj": true,
   "torch_dtype": "float32",
+  "transformers_version": "4.31.0.dev0",
   "use_cache": true,
   "vocab_size": 32000,
   "window_size": 256

generation_config.json CHANGED Viewed

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 0,
-  "transformers_version": "4.30.2"
 }

   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 0,
+  "transformers_version": "4.31.0.dev0"
 }

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b408bd064e39755238fb4c8960aac1bf4b136dca369b96543b6b5624f100f212
 size 495101293

 version https://git-lfs.github.com/spec/v1
+oid sha256:5230f931a24918cf38dd478bdd7800574094eac0642caa9a980d41daf902423c
 size 495101293