Instructions to use SimuIation/CDM_Digital_Navigator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SimuIation/CDM_Digital_Navigator with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="SimuIation/CDM_Digital_Navigator")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SimuIation/CDM_Digital_Navigator")
model = AutoModelForCausalLM.from_pretrained("SimuIation/CDM_Digital_Navigator")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use SimuIation/CDM_Digital_Navigator with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SimuIation/CDM_Digital_Navigator"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SimuIation/CDM_Digital_Navigator",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SimuIation/CDM_Digital_Navigator

SGLang

How to use SimuIation/CDM_Digital_Navigator 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 "SimuIation/CDM_Digital_Navigator" \
    --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": "SimuIation/CDM_Digital_Navigator",
		"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 "SimuIation/CDM_Digital_Navigator" \
        --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": "SimuIation/CDM_Digital_Navigator",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use SimuIation/CDM_Digital_Navigator with Docker Model Runner:
```
docker model run hf.co/SimuIation/CDM_Digital_Navigator
```

SimuIation commited on Jul 9, 2024

Commit

6f51415

verified ·

1 Parent(s): 6844a22

Update README.md

Browse files

Files changed (1) hide show

README.md +7 -3

README.md CHANGED Viewed

@@ -31,8 +31,12 @@ The Digital Navigator model is designed to assist users by generating natural la
 ### Direct Use
-Users do not have much of a choice but only use it for experimental and educational purposes, since the model was fine-tuned for specific answers and question related to the Department of Communication and Digital Media website: https://cdm.uowm.gr/en/index/.
 ### Out-of-Scope Use
 - Generating harmful, biased, or misleading content
@@ -66,7 +70,7 @@ The model was trained using standard procedures for fine-tuning GPT-2 models.
 #### Training Hyperparameters
-- **Training regime:** [More Information Needed]
 - Learning Rate: 5e-5
 - Batch Size: 16
 - Epochs: 30
@@ -97,7 +101,7 @@ Due to the high complexity and small variety of the data:
 - **Hardware Type:** NVIDIA T4
 - **Hours used:** 18 minutes and 47 seconds
-- **Cloud Provider:** Google Collab

 ### Direct Use
+The Digital Navigator model can be directly used for generating conversational responses in English. It is intended for use in chatbots, virtual assistants, and other applications requiring natural language understanding and generation.
+- Conversational AI
+- Customer Support
+- Virtual Assistance
 ### Out-of-Scope Use
 - Generating harmful, biased, or misleading content
 #### Training Hyperparameters
+- **Training regime:** fp32
 - Learning Rate: 5e-5
 - Batch Size: 16
 - Epochs: 30
 - **Hardware Type:** NVIDIA T4
 - **Hours used:** 18 minutes and 47 seconds
+- **Cloud Provider:** Google Colab