Instructions to use krplt/GPT-Sponge with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use krplt/GPT-Sponge with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="krplt/GPT-Sponge")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("krplt/GPT-Sponge") model = AutoModelForCausalLM.from_pretrained("krplt/GPT-Sponge") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use krplt/GPT-Sponge with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "krplt/GPT-Sponge" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "krplt/GPT-Sponge", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/krplt/GPT-Sponge
- SGLang
How to use krplt/GPT-Sponge 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 "krplt/GPT-Sponge" \ --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": "krplt/GPT-Sponge", "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 "krplt/GPT-Sponge" \ --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": "krplt/GPT-Sponge", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use krplt/GPT-Sponge with Docker Model Runner:
docker model run hf.co/krplt/GPT-Sponge
Update README.md
Browse files
README.md
CHANGED
|
@@ -19,8 +19,8 @@ It is capable of generating dialogues and scenarios similar to the original cart
|
|
| 19 |
|
| 20 |
- Model Name: GPT-sponge 🧽
|
| 21 |
- Base Model: GPT-neo 1.3B 🤖
|
| 22 |
-
- Training Steps:
|
| 23 |
-
- Training Time: ~
|
| 24 |
|
| 25 |
# <h3>📝 Example Outputs</h3>
|
| 26 |
|
|
|
|
| 19 |
|
| 20 |
- Model Name: GPT-sponge 🧽
|
| 21 |
- Base Model: GPT-neo 1.3B 🤖
|
| 22 |
+
- Training Steps: 10,000 ⏭️ *(as for current v2 model)*
|
| 23 |
+
- Training Time: ~7 hours (2x NVIDIA A40) ⏰ *(as for current v2 model)*
|
| 24 |
|
| 25 |
# <h3>📝 Example Outputs</h3>
|
| 26 |
|