Instructions to use Bopalv/Qwen3-0.6B-quantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Bopalv/Qwen3-0.6B-quantized with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Bopalv/Qwen3-0.6B-quantized",
	filename="Qwen3-0.6B-GGUF/Qwen3-0.6B.Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Bopalv/Qwen3-0.6B-quantized with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Bopalv/Qwen3-0.6B-quantized:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Bopalv/Qwen3-0.6B-quantized:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Bopalv/Qwen3-0.6B-quantized:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Bopalv/Qwen3-0.6B-quantized: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 Bopalv/Qwen3-0.6B-quantized:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Bopalv/Qwen3-0.6B-quantized: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 Bopalv/Qwen3-0.6B-quantized:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Bopalv/Qwen3-0.6B-quantized:Q4_K_M

Use Docker

docker model run hf.co/Bopalv/Qwen3-0.6B-quantized:Q4_K_M

LM Studio
Jan
Ollama
How to use Bopalv/Qwen3-0.6B-quantized with Ollama:
```
ollama run hf.co/Bopalv/Qwen3-0.6B-quantized:Q4_K_M
```

Unsloth Studio

How to use Bopalv/Qwen3-0.6B-quantized 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 Bopalv/Qwen3-0.6B-quantized 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 Bopalv/Qwen3-0.6B-quantized to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Bopalv/Qwen3-0.6B-quantized to start chatting

How to use Bopalv/Qwen3-0.6B-quantized with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Bopalv/Qwen3-0.6B-quantized: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": "Bopalv/Qwen3-0.6B-quantized:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Bopalv/Qwen3-0.6B-quantized with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Bopalv/Qwen3-0.6B-quantized: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 Bopalv/Qwen3-0.6B-quantized:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use Bopalv/Qwen3-0.6B-quantized with Docker Model Runner:
```
docker model run hf.co/Bopalv/Qwen3-0.6B-quantized:Q4_K_M
```

Lemonade

How to use Bopalv/Qwen3-0.6B-quantized with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Bopalv/Qwen3-0.6B-quantized:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3-0.6B-quantized-Q4_K_M

List all available models

lemonade list

Bopalv commited on Mar 22

Commit

7caec73

verified ·

1 Parent(s): 390608c

Upload DGPO-Training/DGPO-Training-README.md with huggingface_hub

Browse files

Files changed (1) hide show

DGPO-Training/DGPO-Training-README.md +119 -0

DGPO-Training/DGPO-Training-README.md ADDED Viewed

	@@ -0,0 +1,119 @@

+# Qwen3-0.6B DGPO Training
+**Difficulty-Aware Group Policy Optimization (DGPO)** - ICLR 2026
+## What is DGPO?
+DGPO is an advanced reinforcement learning method that extends GRPO (Group Relative Policy Optimization) by adding difficulty-aware mechanisms. It's from the **MathForge** paper: "Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO".
+### Key Innovation
+Standard GRPO has an implicit imbalance where **harder questions get lower policy updates**. DGPO fixes this by:
+1. **Difficulty-Balanced Group Advantage Estimation**
+   - Uses Mean Absolute Deviation (MAD) instead of standard deviation
+   - Normalizes advantages based on question difficulty
+2. **Difficulty-Aware Question Weighting (DQW)**
+   - Prioritizes harder questions during training
+   - Uses softmax weighting with temperature parameter
+## DGPO vs DPO vs GRPO
+| Method | Type | Key Feature | Best For |
+|--------|------|-------------|----------|
+| **DPO** | Preference | Pairwise preferences | General alignment |
+| **GRPO** | RLVR | Group-based rewards | Math reasoning |
+| **DGPO** | RLVR | Difficulty-aware | Hard math problems |
+## Installation
+```bash
+# Install dependencies
+pip install torch transformers trl peft datasets accelerate
+# Clone MathForge (optional, for reference)
+git clone https://github.com/AMAP-ML/MathForge.git
+```
+## Quick Start
+### Basic DGPO Training
+```bash
+python train_dgpo_qwen3.py \
+    --model_name Qwen/Qwen3-0.6B \
+    --enable_dgpo \
+    --enable_dgpo_dqw \
+    --dgpo_dqw_temp 2.0
+```
+### With Custom Parameters
+```bash
+python train_dgpo_qwen3.py \
+    --model_name Qwen/Qwen3-0.6B \
+    --dataset_name DigitalLearningGmbH/MATH-lighteval \
+    --enable_dgpo \
+    --enable_dgpo_dqw \
+    --dgpo_dqw_temp 2.0 \
+    --num_generations 8 \
+    --max_completion_length 1024 \
+    --learning_rate 1e-6 \
+    --num_train_epochs 3
+```
+### Using Shell Script
+```bash
+chmod +x run_dgpo.sh
+./run_dgpo.sh
+```
+## DGPO Parameters
+| Parameter | Default | Description |
+|-----------|---------|-------------|
+| `--enable_dgpo` | True | Enable DGPO algorithm |
+| `--enable_dgpo_dqw` | True | Enable Difficulty-aware Question Weighting |
+| `--dgpo_dqw_temp` | 2.0 | Temperature for DQW (higher = more focus on hard questions) |
+## Training Parameters
+| Parameter | Default | Description |
+|-----------|---------|-------------|
+| `--num_generations` | 4 | Number of completions per prompt |
+| `--max_completion_length` | 512 | Maximum tokens in completion |
+| `--learning_rate` | 5e-7 | Learning rate (use small LR for DGPO) |
+| `--num_train_epochs` | 1 | Number of training epochs |
+| `--beta` | 0.0 | KL coefficient (0 = no reference model) |
+| `--temperature` | 0.7 | Sampling temperature |
+## Performance
+From the MathForge paper (Qwen2.5-Math-7B):
+| Method | AIME24 | AIME25 | AMC23 | MATH500 | Avg. |
+|--------|--------|--------|-------|---------|------|
+| GRPO | 20.94 | 8.44 | 58.98 | 72.20 | 37.61 |
+| **DGPO** | 23.85 | 10.21 | **61.02** | 74.25 | **39.79** |
+| MathForge | 24.58 | **12.60** | 59.84 | **79.95** | **42.17** |
+**DGPO improves over GRPO by +2.18% on average!**
+## References
+- **Paper**: [Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO](https://arxiv.org/abs/2601.20614)
+- **Code**: [AMAP-ML/MathForge](https://github.com/AMAP-ML/MathForge)
+- **Conference**: ICLR 2026
+## Citation
+```bibtex
+@article{dai2026harder,
+  title={Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation},
+  author={Dai, Yanqi and Ji, Yuxiang and Zhang, Xiao and Wang, Yong and Chu, Xiangxiang and Lu, Zhiwu},
+  journal={ICLR},
+  year={2026}
+}
+```