Instructions to use milwright/qwen-8b-dialog-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use milwright/qwen-8b-dialog-v1 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="milwright/qwen-8b-dialog-v1",
	filename="qwen3-stage1.q4_k_m.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use milwright/qwen-8b-dialog-v1 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf milwright/qwen-8b-dialog-v1:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf milwright/qwen-8b-dialog-v1:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf milwright/qwen-8b-dialog-v1:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf milwright/qwen-8b-dialog-v1:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf milwright/qwen-8b-dialog-v1:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf milwright/qwen-8b-dialog-v1:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf milwright/qwen-8b-dialog-v1:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf milwright/qwen-8b-dialog-v1:Q4_K_M

Use Docker

docker model run hf.co/milwright/qwen-8b-dialog-v1:Q4_K_M

LM Studio
Jan

vLLM

How to use milwright/qwen-8b-dialog-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "milwright/qwen-8b-dialog-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "milwright/qwen-8b-dialog-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/milwright/qwen-8b-dialog-v1:Q4_K_M

Ollama
How to use milwright/qwen-8b-dialog-v1 with Ollama:
```
ollama run hf.co/milwright/qwen-8b-dialog-v1:Q4_K_M
```

Unsloth Studio

How to use milwright/qwen-8b-dialog-v1 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for milwright/qwen-8b-dialog-v1 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for milwright/qwen-8b-dialog-v1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for milwright/qwen-8b-dialog-v1 to start chatting

How to use milwright/qwen-8b-dialog-v1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf milwright/qwen-8b-dialog-v1:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "milwright/qwen-8b-dialog-v1:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use milwright/qwen-8b-dialog-v1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf milwright/qwen-8b-dialog-v1:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default milwright/qwen-8b-dialog-v1:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use milwright/qwen-8b-dialog-v1 with Docker Model Runner:
```
docker model run hf.co/milwright/qwen-8b-dialog-v1:Q4_K_M
```

Lemonade

How to use milwright/qwen-8b-dialog-v1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull milwright/qwen-8b-dialog-v1:Q4_K_M

Run and chat with the model

lemonade run user.qwen-8b-dialog-v1-Q4_K_M

List all available models

lemonade list

qwen-8b-dialog-v1

Snapshot: On‑policy pedagogical variant of Qwen‑3‑8B tuned to lead with conversational inquiry, multi‑turn scaffolding, and question-asking dialogue. The model prioritizes question‑asking, co‑investigation, and adaptive depth over direct instruction. It is intended to be tunable across dialogic and pedagogical contexts (e.g., ESL, academic writing, exam prep, K‑12, conversation practice) via prompting or downstream adapters.

HuggingFaceH4/ultrachat_200k (train_sft; pilot run)

LoRA / continued pre‑training specs

Method: Low‑Rank Adaptation (LoRA) via Tinker SDK
Base model: Qwen/Qwen3‑8B
Rank (r): 16
Alpha: 32
Target modules: all linear layers (all‑linear)

Format

This release is provided as a GGUF model for llama.cpp/Ollama workflows.

Intended use

Dialogue‑forward tutoring
Socratic, inquiry‑led teaching
Scaffolding reasoning and language in multi‑turn conversations

Example (Ollama)

# Modelfile
FROM ./qwen3-stage1.q4_k_m.gguf

ollama create qwen-8b-dialog-v1 -f Modelfile
ollama run qwen-8b-dialog-v1

Downloads last month: 7

GGUF

Model size

8B params

Architecture

qwen3

Hardware compatibility

4-bit

Model tree for milwright/qwen-8b-dialog-v1

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-8B

Quantized

(287)

this model

Dataset used to train milwright/qwen-8b-dialog-v1

Collections including milwright/qwen-8b-dialog-v1

Academic Models, Dataset, & Spaces

Collection

25 items • Updated Mar 2 • 1

Critical AI Literacy Institute (CALI), GC, CUNY

Collection

12 items • Updated Mar 23 • 2