Instructions to use nm-testing/DeepSeek-Coder-V2-Lite-Instruct-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nm-testing/DeepSeek-Coder-V2-Lite-Instruct-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="nm-testing/DeepSeek-Coder-V2-Lite-Instruct-FP8", 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("nm-testing/DeepSeek-Coder-V2-Lite-Instruct-FP8", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nm-testing/DeepSeek-Coder-V2-Lite-Instruct-FP8", 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

vLLM

How to use nm-testing/DeepSeek-Coder-V2-Lite-Instruct-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nm-testing/DeepSeek-Coder-V2-Lite-Instruct-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": "nm-testing/DeepSeek-Coder-V2-Lite-Instruct-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nm-testing/DeepSeek-Coder-V2-Lite-Instruct-FP8

SGLang

How to use nm-testing/DeepSeek-Coder-V2-Lite-Instruct-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 "nm-testing/DeepSeek-Coder-V2-Lite-Instruct-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": "nm-testing/DeepSeek-Coder-V2-Lite-Instruct-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 "nm-testing/DeepSeek-Coder-V2-Lite-Instruct-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": "nm-testing/DeepSeek-Coder-V2-Lite-Instruct-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nm-testing/DeepSeek-Coder-V2-Lite-Instruct-FP8 with Docker Model Runner:
```
docker model run hf.co/nm-testing/DeepSeek-Coder-V2-Lite-Instruct-FP8
```

Created using llm-compressor for use with vLLM:

from datasets import load_dataset
from transformers import AutoModelForCausalLM, AutoTokenizer

from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.transformers import oneshot

# NOTE: transformers 4.48.0 has an import error with DeepSeek.
# Please consider either downgrading your transformers version to a
# previous version or upgrading to a version where this bug is fixed

# select a Mixture of Experts model for quantization
MODEL_ID = "deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct"

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

# Select calibration dataset.
# its recommended to use more calibration samples for MoE models so each expert is hit
DATASET_ID = "HuggingFaceH4/ultrachat_200k"
DATASET_SPLIT = "train_sft"
NUM_CALIBRATION_SAMPLES = 2048
MAX_SEQUENCE_LENGTH = 2048


# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42).select(range(NUM_CALIBRATION_SAMPLES))


def preprocess(example):
    return {
        "text": tokenizer.apply_chat_template(
            example["messages"],
            tokenize=False,
        )
    }


ds = ds.map(preprocess)


# Tokenize inputs.
def tokenize(sample):
    return tokenizer(
        sample["text"],
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
        add_special_tokens=False,
    )


ds = ds.map(tokenize, remove_columns=ds.column_names)

# define a llmcompressor recipe for FP8 W8A8 quantization
# since the MoE gate layers are sensitive to quantization, we add them to the ignore
# list so they remain at full precision
recipe = [
    QuantizationModifier(
        targets="Linear",
        scheme="FP8",
        ignore=["lm_head", "re:.*mlp.gate$"],
    ),
]

SAVE_DIR = MODEL_ID.split("/")[1] + "-FP8"

oneshot(
    model=model,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    save_compressed=True,
    output_dir=SAVE_DIR,
)

print("========== SAMPLE GENERATION ==============")
SAMPLE_INPUT = ["I love quantization because"]
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
inputs = tokenizer(SAMPLE_INPUT, return_tensors="pt", padding=True).to(model.device)
output = model.generate(**inputs, max_length=50)
text_output = tokenizer.batch_decode(output)
print(text_output)

Downloads last month: 491

Safetensors

Model size

16B params

Tensor type

BF16

F8_E4M3

Model tree for nm-testing/DeepSeek-Coder-V2-Lite-Instruct-FP8

Base model

deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct

Quantized

(64)

this model