---
language:
- en
license: apache-2.0
base_model: Qwen/Qwen3-0.6B
tags:
- qwen3
- distillation
- on-policy-distillation
- math
- gsm8k
- npu
- ascend
---

# Haidass OPD Step 200

On-Policy Distillation (OPD) checkpoint of Haidass (Qwen3-0.6B) distilled from Qwen3.6-35B-A3B on GSM8K, trained for 200 steps on Ascend 910B3 NPUs.

## Model Details

| | |
|---|---|
| **Base model** | [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) (Haidass, 596M params) |
| **Teacher model** | Qwen3.6-35B-A3B (MoE, 35B total / 3B active) |
| **Architecture** | Qwen3ForCausalLM |
| **Training data** | GSM8K (7,473 train samples) |
| **Training steps** | 200 |
| **Hardware** | 8× Ascend 910B3 (64GB HBM) |
| **Framework** | [verl](https://github.com/verl-project/verl) + vLLM 0.18.0 + vllm-ascend 0.18.0 |

### Architecture

| Parameter | Value |
|-----------|-------|
| hidden_size | 1024 |
| num_hidden_layers | 28 |
| num_attention_heads | 16 |
| num_key_value_heads | 8 (GQA) |
| intermediate_size | 3072 |
| vocab_size | 151936 |
| max_position_embeddings | 40960 |
| tie_word_embeddings | true |

## Training Configuration

- **Distillation loss**: k1 KL divergence + policy gradient
- **Student**: DP=4, TP=1, NPU graph capture enabled, sleep mode disabled
- **Teacher**: TP=4, graph capture enabled
- **Batch size**: 48 (micro_batch=16 per GPU)
- **Learning rate**: 1e-6
- **Max prompt length**: 512 tokens
- **Max response length**: 1024 tokens
- **Performance**: 29.8s/step, 109 tok/s throughput

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "caoyao/haidass_qwen3.6-35b-a3b_opd_step_200"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")

messages = [
    {"role": "user", "content": "Natalia sold clips to 48 of her friends in April, and then she sold half as many clips in May. How many clips did Natalia sell altogether in April and May? Let's think step by step and output the final answer after \"####\"."}
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

## Repository

Training code and scripts: [github.com/yuancaoyaoHW/verl-npu](https://github.com/yuancaoyaoHW/verl-npu)

## Acknowledgements

- [Qwen team](https://github.com/QwenLM) for Qwen3-0.6B and Qwen3.6-35B-A3B
- [verl project](https://github.com/verl-project/verl) for the RL training framework with OPD support
- [Ascend](https://www.hiascend.com/) for NPU hardware and vllm-ascend