Instructions to use sh0ck0r/L3.3-Damascus-R1-FP8-Dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sh0ck0r/L3.3-Damascus-R1-FP8-Dynamic with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="sh0ck0r/L3.3-Damascus-R1-FP8-Dynamic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sh0ck0r/L3.3-Damascus-R1-FP8-Dynamic")
model = AutoModelForCausalLM.from_pretrained("sh0ck0r/L3.3-Damascus-R1-FP8-Dynamic", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sh0ck0r/L3.3-Damascus-R1-FP8-Dynamic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sh0ck0r/L3.3-Damascus-R1-FP8-Dynamic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sh0ck0r/L3.3-Damascus-R1-FP8-Dynamic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sh0ck0r/L3.3-Damascus-R1-FP8-Dynamic

SGLang

How to use sh0ck0r/L3.3-Damascus-R1-FP8-Dynamic with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "sh0ck0r/L3.3-Damascus-R1-FP8-Dynamic" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sh0ck0r/L3.3-Damascus-R1-FP8-Dynamic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "sh0ck0r/L3.3-Damascus-R1-FP8-Dynamic" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sh0ck0r/L3.3-Damascus-R1-FP8-Dynamic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sh0ck0r/L3.3-Damascus-R1-FP8-Dynamic with Docker Model Runner:
```
docker model run hf.co/sh0ck0r/L3.3-Damascus-R1-FP8-Dynamic
```

L3.3-Damascus-R1-FP8-Dynamic / README.md

sh0ck0r

Upload FP8 quantized version of Steelskull/L3.3-Damascus-R1

2cf2f67 verified 10 months ago

preview code

Raw History Blame Contribute Delete

3.65 kB

---
base_model: Steelskull/L3.3-Damascus-R1
tags:
  - fp8
  - vllm
  - compressed-tensors
  - quantized
  - llmcompressor
license: apache-2.0
inference:
  parameters:
    temperature: 0.7
    top_p: 0.9
    max_new_tokens: 2048
library_name: transformers
pipeline_tag: text-generation
---
# L3.3-Damascus-R1 - FP8 Dynamic Quantization

This is an FP8 quantized version of [Steelskull/L3.3-Damascus-R1](https://huggingface.co/Steelskull/L3.3-Damascus-R1) using `llmcompressor` with the FP8_DYNAMIC scheme.
## Model Details
- **Base Model**: Steelskull/L3.3-Damascus-R1
- **Quantization**: FP8_DYNAMIC (W8A8)
- **Format**: compressed-tensors (SafeTensors)
- **Memory**: ~50% of original BF16 size
- **Quality**: <1-2% degradation on benchmarks (typical)

## Quick Start

### vLLM (Recommended)

```bash
pip install vllm
# Serve the model
vllm serve REPO_ID \
  --max-model-len 32768 \
  --gpu-memory-utilization 0.95
# Python API
from vllm import LLM
llm = LLM(model="REPO_ID")
outputs = llm.generate("Hello, how are you?")
print(outputs[0].outputs[0].text)
```

### Transformers

```python
from transformers import AutoTokenizer, AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained(
    "REPO_ID",
    device_map="auto",
    torch_dtype="auto"
)
tokenizer = AutoTokenizer.from_pretrained("REPO_ID")
messages = [{'role': 'user', 'content': 'Hello!'}]
inputs = tokenizer.apply_chat_template(messages, return_tensors='pt').to(model.device)
outputs = model.generate(inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0]))
```

## Quantization Details

This model was quantized using:
- **Tool**: [llmcompressor](https://github.com/vllm-project/llm-compressor)
- **Method**: FP8_DYNAMIC (Round-to-Nearest)
- **Targets**: All Linear layers except `lm_head`
- **Scheme**: W8A8 (8-bit weights and activations)


## Performance

### Memory Usage
- **Original BF16**: ~2× size of FP8
- **FP8 Quantized**: ~50% of original
- **Savings**: ~50% VRAM reduction

### Inference Speed
- Expect 1.3-1.8× faster inference vs BF16
- 2× higher throughput (more KV cache available)

## Use Cases

Perfect for:
- ✅ Production inference on limited VRAM
- ✅ Running larger models on single GPU
- ✅ Cost-effective API serving
- ✅ High-throughput applications
- ✅ Extended context lengths (more KV cache)

## Hardware Requirements

**Minimum VRAM** (approximate):
- 70B model: ~40 GB (RTX A6000, A100 40GB)
- 123B model: ~70 GB (A100 80GB, H100, H200)

**Recommended**:
- H100/H200 for best performance
- vLLM for optimized serving
- Enable FP8 KV cache for extended context

## Important Notes

⚠️ **Quantization Trade-offs**:
- Slight quality degradation (typically <1-2%)
- Not suitable for fine-tuning (inference only)
- Best with vLLM (has FP8 kernel optimizations)

✅ **Best Practices**:
- Use `--kv-cache-dtype fp8` for longer contexts
- Set `--gpu-memory-utilization 0.90-0.95`
- Add `--enforce-eager` if you encounter compilation issues

## Citation

If you use this model, please cite:

```bibtex
@misc{model_name-fp8,
  author = {author},
  title = {model_name FP8 Dynamic Quantization},
  year = {2025},
  publisher = {HuggingFace},
  url = {https://huggingface.co/repo_id}
}
```

## License

Inherits license from base model: [Steelskull/L3.3-Damascus-R1](https://huggingface.co/Steelskull/L3.3-Damascus-R1)

## Acknowledgments

- Base model by [Steelskull](https://huggingface.co/Steelskull)
- Quantization via [llmcompressor](https://github.com/vllm-project/llm-compressor)
- Serving optimized for [vLLM](https://github.com/vllm-project/vllm)



---

**Want more FP8 models?** Check out my other quantizations!

	---
	base_model: Steelskull/L3.3-Damascus-R1
	tags:
	- fp8
	- vllm
	- compressed-tensors
	- quantized
	- llmcompressor
	license: apache-2.0
	inference:
	parameters:
	temperature: 0.7
	top_p: 0.9
	max_new_tokens: 2048
	library_name: transformers
	pipeline_tag: text-generation
	---

	# L3.3-Damascus-R1 - FP8 Dynamic Quantization

	This is an FP8 quantized version of [Steelskull/L3.3-Damascus-R1](https://huggingface.co/Steelskull/L3.3-Damascus-R1) using `llmcompressor` with the FP8_DYNAMIC scheme.

	## Model Details

	- Base Model: Steelskull/L3.3-Damascus-R1
	- Quantization: FP8_DYNAMIC (W8A8)
	- Format: compressed-tensors (SafeTensors)
	- Memory: ~50% of original BF16 size
	- Quality: <1-2% degradation on benchmarks (typical)

	## Quick Start

	### vLLM (Recommended)

	```bash
	pip install vllm

	# Serve the model
	vllm serve REPO_ID \
	--max-model-len 32768 \
	--gpu-memory-utilization 0.95

	# Python API
	from vllm import LLM
	llm = LLM(model="REPO_ID")
	outputs = llm.generate("Hello, how are you?")
	print(outputs[0].outputs[0].text)
	```

	### Transformers

	```python
	from transformers import AutoTokenizer, AutoModelForCausalLM

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

	messages = [{'role': 'user', 'content': 'Hello!'}]
	inputs = tokenizer.apply_chat_template(messages, return_tensors='pt').to(model.device)
	outputs = model.generate(inputs, max_new_tokens=512)
	print(tokenizer.decode(outputs[0]))
	```

	## Quantization Details

	This model was quantized using:
	- Tool: [llmcompressor](https://github.com/vllm-project/llm-compressor)
	- Method: FP8_DYNAMIC (Round-to-Nearest)
	- Targets: All Linear layers except `lm_head`
	- Scheme: W8A8 (8-bit weights and activations)


	## Performance

	### Memory Usage
	- Original BF16: ~2× size of FP8
	- FP8 Quantized: ~50% of original
	- Savings: ~50% VRAM reduction

	### Inference Speed
	- Expect 1.3-1.8× faster inference vs BF16
	- 2× higher throughput (more KV cache available)

	## Use Cases

	Perfect for:
	- ✅ Production inference on limited VRAM
	- ✅ Running larger models on single GPU
	- ✅ Cost-effective API serving
	- ✅ High-throughput applications
	- ✅ Extended context lengths (more KV cache)

	## Hardware Requirements

	Minimum VRAM (approximate):
	- 70B model: ~40 GB (RTX A6000, A100 40GB)
	- 123B model: ~70 GB (A100 80GB, H100, H200)

	Recommended:
	- H100/H200 for best performance
	- vLLM for optimized serving
	- Enable FP8 KV cache for extended context

	## Important Notes

	⚠️ Quantization Trade-offs:
	- Slight quality degradation (typically <1-2%)
	- Not suitable for fine-tuning (inference only)
	- Best with vLLM (has FP8 kernel optimizations)

	✅ Best Practices:
	- Use `--kv-cache-dtype fp8` for longer contexts
	- Set `--gpu-memory-utilization 0.90-0.95`
	- Add `--enforce-eager` if you encounter compilation issues

	## Citation

	If you use this model, please cite:

	```bibtex
	@misc{model_name-fp8,
	author = {author},
	title = {model_name FP8 Dynamic Quantization},
	year = {2025},
	publisher = {HuggingFace},
	url = {https://huggingface.co/repo_id}
	}
	```

	## License

	Inherits license from base model: [Steelskull/L3.3-Damascus-R1](https://huggingface.co/Steelskull/L3.3-Damascus-R1)

	## Acknowledgments

	- Base model by [Steelskull](https://huggingface.co/Steelskull)
	- Quantization via [llmcompressor](https://github.com/vllm-project/llm-compressor)
	- Serving optimized for [vLLM](https://github.com/vllm-project/vllm)



	---

	Want more FP8 models? Check out my other quantizations!