---
license: apache-2.0
base_model: Dream-org/Dream-v0-Instruct-7B
tags:
  - fp8
  - quantized
  - llmcompressor
  - tevunahai
  - professional-grade
  - diffusion-lm
  - dream
  - dllm
---

# Dream-v0-Instruct-7B-FP8

## TevunahAi Professional Quantization

**🏆 First FP8 quantized Dream model for native PyTorch/transformers inference.**

This is an FP8 quantized version of [Dream-v0-Instruct-7B](https://huggingface.co/Dream-org/Dream-v0-Instruct-7B), 
a diffusion-based large language model from HKU NLP Group.

### What is Dream?

Dream 7B is a **Diffusion Large Language Model (dLLM)** - unlike traditional autoregressive models 
(GPT, LLaMA, Claude) that generate text left-to-right one token at a time, Dream uses 
**parallel denoising** to refine the entire sequence simultaneously.

Key advantages:
- 🔄 **Bidirectional context modeling** - considers full context in both directions
- 🎯 **Flexible text generation order** - not constrained to left-to-right
- 🧠 **Superior planning abilities** - excels at tasks requiring multi-step reasoning
- ⚡ **Adjustable quality-speed tradeoff** - control inference steps for your needs

### Quantization Details

| Property | Value |
|----------|-------|
| **Base Model** | Dream-v0-Instruct-7B |
| **Quantization** | FP8 Dynamic (Weight-only) |
| **Method** | llmcompressor FP8_DYNAMIC |
| **Calibration** | Data-free |
| **Storage Size** | ~8.7GB |
| **VRAM Required** | ~10GB |
| **Quantization Time** | 1.7 minutes |

### Quantization Infrastructure

Professional hardware ensures consistent, high-quality quantization:

- **CPUs:** Dual Intel Xeon Max 9480 (112 cores / 224 threads, 128GB HBM2e)
- **GPU:** NVIDIA RTX 5000 Ada Generation (32GB VRAM, native FP8 support)
- **Memory:** 256GB DDR5 + 128GB HBM2e = 384GB total system memory
- **Software Stack:** Ubuntu 25.10 | Python 3.12 | PyTorch 2.8 | CUDA 13.0 | llm-compressor

### Memory Comparison

| Precision | Size | VRAM Required |
|-----------|------|---------------|
| BF16 | ~14 GB | ~16 GB |
| **FP8** | **~8.7 GB** | **~10 GB** |

## Usage

### With Transformers (Required for Diffusion Models)

**Note:** Dream uses a custom diffusion architecture that requires transformers with `trust_remote_code=True`. It is not compatible with standard inference frameworks like vLLM.

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

model_path = "TevunahAi/Dream-v0-Instruct-7B-FP8"

# Load FP8 model - will decompress to BF16 during inference
model = AutoModel.from_pretrained(
    model_path,
    torch_dtype="auto",  # Auto-detects FP8, decompresses to BF16
    trust_remote_code=True,  # Required for diffusion architecture
    device_map="auto",
    low_cpu_mem_usage=True,
)
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

# Prepare input
messages = [
    {"role": "user", "content": "Explain quantum computing in simple terms."}
]

inputs = tokenizer.apply_chat_template(
    messages,
    return_tensors="pt",
    return_dict=True,
    add_generation_prompt=True
)

input_ids = inputs.input_ids.to(model.device)
attention_mask = inputs.attention_mask.to(model.device)

# Dream uses diffusion_generate, not generate!
output = model.diffusion_generate(
    input_ids,
    attention_mask=attention_mask,
    max_new_tokens=512,
    steps=256,  # More steps = better quality
    temperature=0.7,
    top_p=0.9,
    alg="entropy",
    alg_temp=0.,
)

# Decode and clean up response
response = tokenizer.decode(output[0][input_ids.shape[1]:].tolist())
response = response.split("<|endoftext|>")[0].strip()
print(response)
```

### Requirements

```bash
pip install torch>=2.1.0 transformers>=4.40.0 accelerate compressed-tensors
```

**System Requirements:**
- **~10GB VRAM** (FP8 weights decompress to BF16 during inference)
- CUDA 11.8 or newer
- PyTorch 2.1+ with CUDA support

### Generation Parameters

| Parameter | Description | Recommended Values |
|-----------|-------------|-------------------|
| `steps` | Number of diffusion steps | 128-512 (more = better quality) |
| `max_new_tokens` | Maximum tokens to generate | 256-1024 |
| `temperature` | Randomness (higher = creative) | 0.7-1.0 |
| `top_p` | Nucleus sampling threshold | 0.9-0.95 |
| `alg` | Decoding algorithm | "entropy" |
| `alg_temp` | Algorithm temperature | 0.0 |

**Quality vs Speed:**
- **Fast (128 steps):** Quick responses, good for simple queries
- **Balanced (256 steps):** Default setting, good quality
- **High Quality (512 steps):** Best output, slower generation

## Important Notes

1. ⚠️ **Use `diffusion_generate()`** not `generate()` - Dream is a diffusion model!
2. ⚠️ **Requires `trust_remote_code=True`** for custom diffusion architecture
3. 📦 **FP8 decompresses to BF16** during inference (~10GB VRAM)
4. 🔍 **Stop token cleanup**: split response on `<|endoftext|>`
5. 📏 **Context length**: 2048 tokens
6. 🚫 **Not compatible with vLLM** - requires transformers with custom code

## Why FP8 for Dream?

### Benefits:
- ✅ **Smaller download size** (~8.7GB vs ~14GB BF16)
- ✅ **Faster model loading** from disk
- ✅ **Storage efficiency** for model archives
- ✅ **Compatible** with standard transformers workflow

### Trade-offs:
- ⚠️ **Decompresses to BF16** during inference (~10GB VRAM)
- ⚠️ **No runtime memory benefit** (diffusion models need full precision)
- ⚠️ **Not vLLM compatible** (custom architecture)

**FP8 primarily benefits storage and download speed for this model.**

## Diffusion vs Autoregressive

**Traditional Autoregressive (GPT-style):**
```
The quick | → | brown | → | fox | → | jumps | → | ...
```
Generates left-to-right, one token at a time.

**Diffusion (Dream):**
```
[noise] → [rough text] → [refined text] → [final output]
```
Generates entire sequence through iterative refinement.

**Result:** Better at:
- Long-range planning and coherence
- Complex reasoning tasks
- Bidirectional context understanding
- Flexible generation strategies

## Use Cases

Dream excels at tasks requiring:
- 📝 **Long-form writing** with complex structure
- 🧮 **Multi-step reasoning** and problem solving
- 🔄 **Text revision** and refinement
- 🎯 **Planning-heavy tasks** like stories, essays, arguments
- 🧠 **Tasks requiring global coherence**

## 📚 Original Model

This quantization is based on [Dream-org/Dream-v0-Instruct-7B](https://huggingface.co/Dream-org/Dream-v0-Instruct-7B) by HKU NLP Group.

For comprehensive information about:
- Diffusion LM architecture
- Training methodology
- Evaluation benchmarks
- Research papers

Please refer to the [original model card](https://huggingface.co/Dream-org/Dream-v0-Instruct-7B).

## 📄 License

This model inherits the **Apache 2.0 License** from the original Dream model.

## 🙏 Acknowledgments

- **Original Model:** [Dream-org / HKU NLP Group](https://huggingface.co/Dream-org) - Pioneering diffusion-based language models
- **Quantization Framework:** Neural Magic's llm-compressor
- **Quantized by:** [TevunahAi](https://huggingface.co/TevunahAi)

## 📝 Citation

If you use Dream, please cite the original paper:

```bibtex
@article{dream2025,
  title={Dream 7B: Diffusion Large Language Models},
  author={Ye, Jiacheng and Xie, Zhihui and others},
  journal={arXiv preprint},
  year={2025}
}
```

---

<div align="center">

**Professional AI Model Quantization by TevunahAi**

*Enterprise-grade quantization on specialized hardware*

[View all models](https://huggingface.co/TevunahAi) | [Contact for custom quantization](https://huggingface.co/TevunahAi)

</div>