Text Generation
Transformers
PyTorch
reasoning
Android
bilingual
opceanai
termux
flan
fine-tuned
lol
stupid
flan-t5
qDora
Instructions to use OpceanAI/SoTa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpceanAI/SoTa with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="OpceanAI/SoTa")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("OpceanAI/SoTa", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use OpceanAI/SoTa with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "OpceanAI/SoTa" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "OpceanAI/SoTa", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/OpceanAI/SoTa
- SGLang
How to use OpceanAI/SoTa 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 "OpceanAI/SoTa" \ --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": "OpceanAI/SoTa", "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 "OpceanAI/SoTa" \ --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": "OpceanAI/SoTa", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use OpceanAI/SoTa with Docker Model Runner:
docker model run hf.co/OpceanAI/SoTa
Update README.md
Browse files
README.md
CHANGED
|
@@ -41,4 +41,7 @@ datasets:
|
|
| 41 |
- PJMixers-Dev/nvidia-r1-code-1k-think-256-response-filtered-ShareGPT
|
| 42 |
- trjxter/Kimi-K2.6-Reasoning-3300x-WandB
|
| 43 |
- allenai/Dolci-Think-SFT-32B
|
|
|
|
|
|
|
|
|
|
| 44 |
---
|
|
|
|
| 41 |
- PJMixers-Dev/nvidia-r1-code-1k-think-256-response-filtered-ShareGPT
|
| 42 |
- trjxter/Kimi-K2.6-Reasoning-3300x-WandB
|
| 43 |
- allenai/Dolci-Think-SFT-32B
|
| 44 |
+
- OpceanAI/sota-hard
|
| 45 |
+
- OpceanAI/sota-general
|
| 46 |
+
- OpceanAI/sota-math
|
| 47 |
---
|