Instructions to use enferAI/DeepSeek-R1-Distill-Qwen-14B-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use enferAI/DeepSeek-R1-Distill-Qwen-14B-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="enferAI/DeepSeek-R1-Distill-Qwen-14B-FP8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("enferAI/DeepSeek-R1-Distill-Qwen-14B-FP8")
model = AutoModelForCausalLM.from_pretrained("enferAI/DeepSeek-R1-Distill-Qwen-14B-FP8", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use enferAI/DeepSeek-R1-Distill-Qwen-14B-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "enferAI/DeepSeek-R1-Distill-Qwen-14B-FP8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "enferAI/DeepSeek-R1-Distill-Qwen-14B-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/enferAI/DeepSeek-R1-Distill-Qwen-14B-FP8

SGLang

How to use enferAI/DeepSeek-R1-Distill-Qwen-14B-FP8 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 "enferAI/DeepSeek-R1-Distill-Qwen-14B-FP8" \
    --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": "enferAI/DeepSeek-R1-Distill-Qwen-14B-FP8",
		"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 "enferAI/DeepSeek-R1-Distill-Qwen-14B-FP8" \
        --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": "enferAI/DeepSeek-R1-Distill-Qwen-14B-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use enferAI/DeepSeek-R1-Distill-Qwen-14B-FP8 with Docker Model Runner:
```
docker model run hf.co/enferAI/DeepSeek-R1-Distill-Qwen-14B-FP8
```

DeepSeek-R1-Distill-Qwen-14B-FP8

FP8-quantized version of DeepSeek-R1-Distill-Qwen-14B, optimized for inference with vLLM. The quantization reduces the model's memory footprint by approximately 50%.

Model Overview

Base Model: DeepSeek-R1-Distill-Qwen-14B
Quantization: FP8 (weights and activations)
Memory Reduction: ~50% (from 16-bit to 8-bit)
License: MIT License (following original model's license)

Compression Details

Compressed using LLM Compressor with:

512 calibration samples from UltraChat
Symmetric per-tensor quantization
Applied to linear operators within transformer blocks

The compression script is available in compress.py.

Requirements

vLLM
transformers
torch
accelerate

Note

This is an experimental compression of the model. Performance metrics and optimal usage parameters have not been thoroughly tested yet.

Downloads last month: 12

Safetensors

Model size

15B params

Tensor type

BF16

F8_E4M3

Model tree for enferAI/DeepSeek-R1-Distill-Qwen-14B-FP8

Base model

deepseek-ai/DeepSeek-R1-Distill-Qwen-14B

Quantized

(141)

this model