Instructions to use Etelis/DeepSeek-V2-Lite-FP8-BLOCK-padded with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Etelis/DeepSeek-V2-Lite-FP8-BLOCK-padded with Transformers:

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

pipe = pipeline("text-generation", model="Etelis/DeepSeek-V2-Lite-FP8-BLOCK-padded", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Etelis/DeepSeek-V2-Lite-FP8-BLOCK-padded", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Etelis/DeepSeek-V2-Lite-FP8-BLOCK-padded", trust_remote_code=True)
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 Etelis/DeepSeek-V2-Lite-FP8-BLOCK-padded with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Etelis/DeepSeek-V2-Lite-FP8-BLOCK-padded"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Etelis/DeepSeek-V2-Lite-FP8-BLOCK-padded",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Etelis/DeepSeek-V2-Lite-FP8-BLOCK-padded

SGLang

How to use Etelis/DeepSeek-V2-Lite-FP8-BLOCK-padded 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 "Etelis/DeepSeek-V2-Lite-FP8-BLOCK-padded" \
    --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": "Etelis/DeepSeek-V2-Lite-FP8-BLOCK-padded",
		"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 "Etelis/DeepSeek-V2-Lite-FP8-BLOCK-padded" \
        --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": "Etelis/DeepSeek-V2-Lite-FP8-BLOCK-padded",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Etelis/DeepSeek-V2-Lite-FP8-BLOCK-padded with Docker Model Runner:
```
docker model run hf.co/Etelis/DeepSeek-V2-Lite-FP8-BLOCK-padded
```

DeepSeek-V2-Lite-FP8-BLOCK-padded

This model is a FP8 block-quantized version of deepseek-ai/DeepSeek-V2-Lite with padding support for non-divisible dimensions.

Overview

Base Model: deepseek-ai/DeepSeek-V2-Lite (16B parameters)
Quantization: FP8_BLOCK (128x128 block structure)
Purpose: Demonstrates FP8 block quantization with weight padding for models with dimensions not evenly divisible by block size

Key Feature: Block Quantization Padding

DeepSeek-V2-Lite has intermediate_size=10944, which is not divisible by the block size of 128. This model uses weight padding to handle this:

Original intermediate_size: 10944
Padded intermediate_size: 11008 (86 × 128)

The padding is applied during quantization and the config.json reflects the padded dimensions for vLLM compatibility.

Usage with vLLM

from vllm import LLM, SamplingParams

llm = LLM(
    model="Etelis/DeepSeek-V2-Lite-FP8-BLOCK-padded",
    trust_remote_code=True,
    tensor_parallel_size=1,
)

sampling_params = SamplingParams(max_tokens=100, temperature=0.7)
output = llm.generate(["Hello, world!"], sampling_params)
print(output[0].outputs[0].text)

Requirements: H100 or newer GPU (SM 8.9+) for FP8 block quantization support.

Quantization Recipe

from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor import oneshot
from llmcompressor.modifiers.quantization import QuantizationModifier

MODEL_ID = "deepseek-ai/DeepSeek-V2-Lite"

model = AutoModelForCausalLM.from_pretrained(
    MODEL_ID, 
    torch_dtype="auto", 
    trust_remote_code=True, 
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True)

# FP8 block quantization - ignore layers with composite dimensions
recipe = QuantizationModifier(
    targets="Linear",
    scheme="FP8_BLOCK",
    ignore=["lm_head", "re:.*kv_a_proj_with_mqa.*"]
)

oneshot(model=model, recipe=recipe)

model.save_pretrained("DeepSeek-V2-Lite-FP8-BLOCK-padded")
tokenizer.save_pretrained("DeepSeek-V2-Lite-FP8-BLOCK-padded")

Created With

llm-compressor (with padding support)
compressed-tensors (PR #547)

Ignored Layers

lm_head: Not quantized (standard practice)
kv_a_proj_with_mqa: Has composite dimensions (512 + 64 = 576) that cannot be safely padded

License

This model inherits the DeepSeek Model License from the base model.

Downloads last month: 22

Safetensors

Model size

16B params

Tensor type

I64

BF16

F8_E4M3

Model tree for Etelis/DeepSeek-V2-Lite-FP8-BLOCK-padded

Base model

deepseek-ai/DeepSeek-V2-Lite

Quantized

(23)

this model