Instructions to use yujiepan/deepseek-v2-0628-tiny-random with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yujiepan/deepseek-v2-0628-tiny-random with Transformers:

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

pipe = pipeline("text-generation", model="yujiepan/deepseek-v2-0628-tiny-random", 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("yujiepan/deepseek-v2-0628-tiny-random", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("yujiepan/deepseek-v2-0628-tiny-random", 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 yujiepan/deepseek-v2-0628-tiny-random with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yujiepan/deepseek-v2-0628-tiny-random"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yujiepan/deepseek-v2-0628-tiny-random",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yujiepan/deepseek-v2-0628-tiny-random

SGLang

How to use yujiepan/deepseek-v2-0628-tiny-random 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 "yujiepan/deepseek-v2-0628-tiny-random" \
    --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": "yujiepan/deepseek-v2-0628-tiny-random",
		"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 "yujiepan/deepseek-v2-0628-tiny-random" \
        --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": "yujiepan/deepseek-v2-0628-tiny-random",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use yujiepan/deepseek-v2-0628-tiny-random with Docker Model Runner:
```
docker model run hf.co/yujiepan/deepseek-v2-0628-tiny-random
```

This model is for debugging. It is randomly initialized using the config from deepseek-ai/DeepSeek-V2-Chat-0628 but with smaller size.

Codes:

from huggingface_hub import create_repo, upload_folder
from transformers import (
    pipeline,
    set_seed,
    AutoConfig,
    AutoModelForCausalLM,
    AutoTokenizer,
    GenerationConfig,
)
import torch
import transformers
import os

model_id = "deepseek-ai/DeepSeek-V2-Chat-0628"
repo_id = "yujiepan/deepseek-v2-0628-tiny-random"
save_path = f"/tmp/{repo_id}"

config = AutoConfig.from_pretrained(model_id, trust_remote_code=True)
config._name_or_path = model_id
config.hidden_size = 8
config.intermediate_size = 16
config.moe_intermediate_size = 4
config.num_attention_heads = 2
config.num_key_value_heads = 2
config.num_hidden_layers = 2
config.kv_lora_rank = 2
config.q_lora_rank = 2
config.v_head_dim = 2
config.qk_nope_head_dim = 2
config.qk_rope_head_dim = 2
config.torch_dtype = "bfloat16"
print(config)

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
tokenizer.save_pretrained(save_path)

model = AutoModelForCausalLM.from_config(
    config, torch_dtype=torch.bfloat16, attn_implementation="eager", trust_remote_code=True
)
model.generation_config = GenerationConfig.from_pretrained(model_id, trust_remote_code=True)

set_seed(42)
with torch.no_grad():
    for _, p in sorted(model.named_parameters()):
        torch.nn.init.uniform_(p, -0.1, 0.1)

model.save_pretrained(save_path)

# pipe = pipeline("text-generation", model=save_path, device="cuda", trust_remote_code=True)
# print(pipe("Hello World!"))

# messages = [
#     {"role": "system", "content": "You are a robot."},
#     {"role": "user", "content": "Hi!"},
# ]
# chatbot = pipeline("text-generation", model=save_path, max_length=1000, max_new_tokens=16, trust_remote_code=True)
# print(chatbot(messages))

messages = [{"role": "user", "content": "Write a piece of quicksort code in C++"}]
input_tensor = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
outputs = model.generate(input_tensor.to(model.device), max_new_tokens=100)
result = tokenizer.decode(outputs[0][input_tensor.shape[1] :], skip_special_tokens=True)
print(result)

Downloads last month: 574

Safetensors

Model size

1.66M params

Tensor type

BF16

Collection including yujiepan/deepseek-v2-0628-tiny-random

Tiny dummy models

Collection

Randomly initialized tiny models for debugging/testing purpose • 176 items • Updated Apr 23 • 6