---
base_model: 1024m/OLMoE-1B-7B-0924-Base
library_name: transformers
pipeline_tag: text-generation
license: apache-2.0
tags:
- dpo
- dora
- qlora
- olmoe
- alignment
- preference-learning
- merged
datasets:
- teknium/OpenHermes-2.5
- HuggingFaceH4/ultrafeedback_binarized
language:
- en
---

# OLMoE-1B-7B DPO with DoRA (Merged)

This is the **merged** version of [demonlxrd/olmoe-openhermes-ultrafeedback-dora-dpo](https://huggingface.co/demonlxrd/olmoe-openhermes-ultrafeedback-dora-dpo) - a preference-aligned OLMoE model trained with DoRA and DPO.

## What's This?

A fully merged model ready for production deployment. The DoRA adapter has been merged into the base [OLMoE-1B-7B](https://huggingface.co/1024m/OLMoE-1B-7B-0924-Base) weights for:
- ✅ Faster inference (no adapter overhead)
- ✅ vLLM compatibility  
- ✅ Simpler deployment
- ✅ Production-ready

Training pipeline:
1. **SFT** on 20K examples from [OpenHermes-2.5](https://huggingface.co/datasets/teknium/OpenHermes-2.5)
2. **DPO** on 10K preference pairs from [UltraFeedback](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized)
3. **Merged** DoRA adapter into base weights

## Quick Start

### vLLM (Recommended)

```bash
# Serve
vllm serve demonlxrd/olmoe-openhermes-ultrafeedback-dora-dpo-merged \
  --max-model-len 4096 \
  --dtype bfloat16

# Inference
curl -s http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "demonlxrd/olmoe-openhermes-ultrafeedback-dora-dpo-merged",
    "messages": [
      {"role": "user", "content": "Explain machine learning in simple terms."}
    ],
    "max_tokens": 200,
    "temperature": 0.7
  }' | jq -r '.choices[0].message.content'
```

### Python with Transformers

```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("demonlxrd/olmoe-openhermes-ultrafeedback-dora-dpo-merged")
model = AutoModelForCausalLM.from_pretrained(
    "demonlxrd/olmoe-openhermes-ultrafeedback-dora-dpo-merged",
    device_map="auto",
    torch_dtype=torch.bfloat16
)

messages = [{"role": "user", "content": "What is quantum computing?"}]
prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

with torch.inference_mode():
    outputs = model.generate(**inputs, max_tokens=200, temperature=0.7)
    
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

### Python with OpenAI Client

```python
from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:8000/v1",
    api_key="dummy"
)

response = client.chat.completions.create(
    model="demonlxrd/olmoe-openhermes-ultrafeedback-dora-dpo-merged",
    messages=[
        {"role": "user", "content": "Write a Python function to calculate fibonacci numbers."}
    ],
    max_tokens=300,
    temperature=0.7
)

print(response.choices[0].message.content)
```

## Model Details

| Parameter | Value |
|-----------|-------|
| Architecture | OLMoE (Mixture of Experts) |
| Parameters | ~1B active, 7B total |
| Precision | bfloat16 |
| Context Length | 4096 tokens |
| Training | SFT + DPO with DoRA adapters |
| Base Model | 1024m/OLMoE-1B-7B-0924-Base |

## Training Details

- **Adapter Type**: DoRA (Weight-Decomposed LoRA)
- **LoRA Rank**: 16
- **Target Modules**: q_proj, v_proj
- **Quantization during training**: 4-bit NF4
- **DPO Beta**: 0.1
- **Learning Rate**: 5e-5
- **Hardware**: 2× NVIDIA A40 80GB

## Chat Template

```
User:
<message>


Assistant:
<response>
```

Roles supported: `system`, `user`, `assistant`

## Why Use the Merged Version?

- **Performance**: No adapter overhead during inference
- **Compatibility**: Works with vLLM, TGI, and other optimized serving frameworks
- **Simplicity**: Single model file, no need to load base + adapter separately
- **Production-Ready**: Optimized for deployment at scale

## Adapter Version

Looking for the lightweight adapter weights? Check out [demonlxrd/olmoe-openhermes-ultrafeedback-dora-dpo](https://huggingface.co/demonlxrd/olmoe-openhermes-ultrafeedback-dora-dpo) (~8.3MB)

## License

Apache 2.0. Please also check the license of the [base model](https://huggingface.co/1024m/OLMoE-1B-7B-0924-Base).

## Citation

If you use this model, please cite:

- **Base Model**: [1024m/OLMoE-1B-7B-0924-Base](https://huggingface.co/1024m/OLMoE-1B-7B-0924-Base)
- **OpenHermes-2.5**: [teknium/OpenHermes-2.5](https://huggingface.co/datasets/teknium/OpenHermes-2.5)
- **UltraFeedback**: [HuggingFaceH4/ultrafeedback_binarized](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized)
- **TRL**: [HuggingFace TRL](https://github.com/huggingface/trl)