Text Generation
Transformers
GGUF
PyTorch
English
sage_1b
language-model
transformer
from-scratch
tiny-stories
Instructions to use itriedcoding/Sage-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use itriedcoding/Sage-1B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="itriedcoding/Sage-1B")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("itriedcoding/Sage-1B", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use itriedcoding/Sage-1B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "itriedcoding/Sage-1B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "itriedcoding/Sage-1B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/itriedcoding/Sage-1B
- SGLang
How to use itriedcoding/Sage-1B 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 "itriedcoding/Sage-1B" \ --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": "itriedcoding/Sage-1B", "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 "itriedcoding/Sage-1B" \ --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": "itriedcoding/Sage-1B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use itriedcoding/Sage-1B with Docker Model Runner:
docker model run hf.co/itriedcoding/Sage-1B
Upload config.json with huggingface_hub
Browse files- config.json +12 -0
config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"vocab_size": 50000,
|
| 3 |
+
"hidden_size": 1536,
|
| 4 |
+
"num_hidden_layers": 30,
|
| 5 |
+
"num_attention_heads": 12,
|
| 6 |
+
"head_dim": 128,
|
| 7 |
+
"intermediate_size": 6144,
|
| 8 |
+
"max_position_embeddings": 128,
|
| 9 |
+
"model_type": "sage_1b",
|
| 10 |
+
"total_params": 1286155776,
|
| 11 |
+
"torch_dtype": "float32"
|
| 12 |
+
}
|