Instructions to use underwater45/Oracle-Prototype with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use underwater45/Oracle-Prototype with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="underwater45/Oracle-Prototype")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("underwater45/Oracle-Prototype", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use underwater45/Oracle-Prototype with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "underwater45/Oracle-Prototype" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "underwater45/Oracle-Prototype", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/underwater45/Oracle-Prototype
- SGLang
How to use underwater45/Oracle-Prototype 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 "underwater45/Oracle-Prototype" \ --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": "underwater45/Oracle-Prototype", "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 "underwater45/Oracle-Prototype" \ --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": "underwater45/Oracle-Prototype", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use underwater45/Oracle-Prototype with Docker Model Runner:
docker model run hf.co/underwater45/Oracle-Prototype
Create config.json
Browse files- config.json +29 -0
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "oracle",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"OracleModel"
|
| 5 |
+
],
|
| 6 |
+
"hidden_size": 768,
|
| 7 |
+
"num_hidden_layers": 1,
|
| 8 |
+
"num_attention_heads": 12,
|
| 9 |
+
"intermediate_size": 3072,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"attention_probs_dropout_prob": 0.1,
|
| 13 |
+
"max_position_embeddings": 512,
|
| 14 |
+
"type_vocab_size": 2,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"layer_norm_eps": 1e-12,
|
| 17 |
+
"pad_token_id": 0,
|
| 18 |
+
"bos_token_id": 101,
|
| 19 |
+
"eos_token_id": 102,
|
| 20 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"use_cache": true,
|
| 22 |
+
"classifier_dropout": null,
|
| 23 |
+
"sub_models": [
|
| 24 |
+
"bert-base-uncased",
|
| 25 |
+
"roberta-base",
|
| 26 |
+
"distilbert-base-uncased"
|
| 27 |
+
],
|
| 28 |
+
"tokenizer_name": "bert-base-uncased"
|
| 29 |
+
}
|