Instructions to use gitcoreai/gpt-2-small-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gitcoreai/gpt-2-small-sft with Transformers:

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

pipe = pipeline("text-generation", model="gitcoreai/gpt-2-small-sft")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("gitcoreai/gpt-2-small-sft")
model = AutoModelForCausalLM.from_pretrained("gitcoreai/gpt-2-small-sft", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use gitcoreai/gpt-2-small-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gitcoreai/gpt-2-small-sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gitcoreai/gpt-2-small-sft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/gitcoreai/gpt-2-small-sft

SGLang

How to use gitcoreai/gpt-2-small-sft 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 "gitcoreai/gpt-2-small-sft" \
    --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": "gitcoreai/gpt-2-small-sft",
		"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 "gitcoreai/gpt-2-small-sft" \
        --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": "gitcoreai/gpt-2-small-sft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use gitcoreai/gpt-2-small-sft with Docker Model Runner:
```
docker model run hf.co/gitcoreai/gpt-2-small-sft
```

gitcoreai commited on Jul 15

Commit

ffaf9e8

verified ·

1 Parent(s): 21b9be4

Update README.md

Browse files

Files changed (1) hide show

README.md +32 -0

README.md CHANGED Viewed

@@ -1,3 +1,35 @@
 ---
 license: mit
 ---

 ---
 license: mit
+base_model: openai-community/gpt2
+datasets:
+- OpenAssistant/oasst1
+language:
+- en
 ---
+# GPT-2 SFT on OASST1
+This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on the [OpenAssistant/oasst1](https://huggingface.co/datasets/OpenAssistant/oasst1) dataset.
+## Training Procedure
+- **Base Model:** GPT-2 Small (124M parameters)
+- **Dataset:** OpenAssistant OASST1 (English only)
+- **Format:** `user: ... assistant: <s> ... </s>`
+- **Epochs:** 15
+- **Learning Rate:** 5e-5
+- **Batch Size:** 4 (effective 16 with gradient accumulation)
+## Usage
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+model_name = "gitcoreai/gpt-2-small-sft"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+prompt = "user: hello, how are you?\nassistant: <s>"
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=60)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))