callistro/qwen3-counselor

callistro/ qwen3-counselor

21 Downloads Updated 3 weeks ago

A compact yet highly capable model designed for on-device mental-health-related conversations. Qwen-3 Counselor leverages the Qwen3:8B model, with additional fine-tuning on a dataset of curated counseling conversations.

ollama run callistro/qwen3-counselor

curl http://localhost:11434/api/chat \
  -d '{
    "model": "callistro/qwen3-counselor",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='callistro/qwen3-counselor',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'callistro/qwen3-counselor',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Models

View all →

Name

1 model

Size / Usage

Context

Input

qwen3-counselor:latest

5.0GB · 40K context window · Text · 3 weeks ago

qwen3-counselor:latest

5.0GB

40K

Text

Readme

This model is built on the Qwen3:8B model and further fine-tuned on a curated dataset of counseling conversations.

The model is intended to support empathetic, structured, and context-aware dialogue in local or privacy-conscious environments. It aims to provide thoughtful responses for supportive conversations while remaining lightweight enough to run on consumer hardware. It is not a replacement for licensed mental health professionals, crisis services, or medical advice.