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

Libraries

How to use Harshatheeswar/gpt2-scratch with Transformers:

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

pipe = pipeline("text-generation", model="Harshatheeswar/gpt2-scratch")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Harshatheeswar/gpt2-scratch")
model = AutoModelForCausalLM.from_pretrained("Harshatheeswar/gpt2-scratch")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Harshatheeswar/gpt2-scratch with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Harshatheeswar/gpt2-scratch

SGLang

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

Docker Model Runner
How to use Harshatheeswar/gpt2-scratch with Docker Model Runner:
```
docker model run hf.co/Harshatheeswar/gpt2-scratch
```

Harshatheeswar commited on Oct 19, 2024

Commit

2bbca5e

verified ·

1 Parent(s): 178a9f9

Training in progress, step 4500

Browse files

Files changed (2) hide show

model.safetensors +1 -1
runs/Oct19_15-46-37_22a6a41c53da/events.out.tfevents.1729352801.22a6a41c53da.2967.1 +2 -2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:330e3f0c44267c3ea34e3d8184744c96720526bc3272afa8cd34b3ee85e68c9e
 size 497774208

 version https://git-lfs.github.com/spec/v1
+oid sha256:87a2d552c2cd0e39b59132be5c79a7b7eaba205c2d292b5d4f5aa8527649cb0b
 size 497774208

runs/Oct19_15-46-37_22a6a41c53da/events.out.tfevents.1729352801.22a6a41c53da.2967.1 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f7bcc16cc32ad0b807395f11d5690b19557cd4f7f15a01be2d7ff5020a5a55d
-size 90014

 version https://git-lfs.github.com/spec/v1
+oid sha256:13a32dd1d4d76dc599a9fb1ee8f91c16f1f2b10bd1b4aada7c6ad0ca907b1b1b
+size 100835