Instructions to use lightonai/RITA_s with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lightonai/RITA_s with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="lightonai/RITA_s", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("lightonai/RITA_s", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use lightonai/RITA_s with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "lightonai/RITA_s" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "lightonai/RITA_s", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/lightonai/RITA_s
- SGLang
How to use lightonai/RITA_s 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 "lightonai/RITA_s" \ --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": "lightonai/RITA_s", "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 "lightonai/RITA_s" \ --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": "lightonai/RITA_s", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use lightonai/RITA_s with Docker Model Runner:
docker model run hf.co/lightonai/RITA_s
Commit ·
ef5cebc
1
Parent(s): e3e75dc
add model
Browse files- config.json +19 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RITAModel"
|
| 4 |
+
],
|
| 5 |
+
"bos_token_id": [
|
| 6 |
+
50256
|
| 7 |
+
],
|
| 8 |
+
"d_feedforward": 3072,
|
| 9 |
+
"d_model": 768,
|
| 10 |
+
"dropout": 0.0,
|
| 11 |
+
"eos_token_id": 50256,
|
| 12 |
+
"max_seq_len": 1024,
|
| 13 |
+
"model_type": "codegen",
|
| 14 |
+
"num_heads": 12,
|
| 15 |
+
"num_layers": 12,
|
| 16 |
+
"torch_dtype": "float32",
|
| 17 |
+
"transformers_version": "4.16.2",
|
| 18 |
+
"vocab_size": 128
|
| 19 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44dcdb6e5e45392331c5cf4c679af2a138aa8b4a2c3c88de0f98e051616e09d7
|
| 3 |
+
size 341084257
|