Instructions to use vitaliy-sharandin/wiseai with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vitaliy-sharandin/wiseai with Transformers:

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

pipe = pipeline("text-generation", model="vitaliy-sharandin/wiseai")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("vitaliy-sharandin/wiseai")
model = AutoModelForCausalLM.from_pretrained("vitaliy-sharandin/wiseai", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use vitaliy-sharandin/wiseai with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/vitaliy-sharandin/wiseai

SGLang

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

Docker Model Runner
How to use vitaliy-sharandin/wiseai with Docker Model Runner:
```
docker model run hf.co/vitaliy-sharandin/wiseai
```

wiseai / README.md

vitaliy-sharandin

Update README.md

c6cc9b0 over 2 years ago

preview code

Raw

History Blame Contribute Delete

837 Bytes

metadata

language:
  - en
tags:
  - text-generation
  - mental-health
  - psychology
  - llm
datasets:
  - vitaliy-sharandin/depression-instruct
metrics:
  - BLEU
  - ROUGE
license: apache-2.0
model-index:
  - name: WisAI
    results:
      - task:
          name: Text Generation
          type: text-generation
        dataset:
          name: depression-instruct
          type: vitaliy-sharandin/depression-instruct
        metrics:
          - name: BLEU
            type: bleu
            value: 0.3
          - name: ROUGE
            type: rouge
            value: 0.45
          - name: F1
            type: f1
            value: 0.36

Become wiser with WisAI

This is a wise AI model trained on philosophical and psychological data. It is intended to answer mental health questions and give some deep advice.