Instructions to use kshitijthakkar/deepseek-v4-mini-3B-init with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kshitijthakkar/deepseek-v4-mini-3B-init with Transformers:

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

pipe = pipeline("text-generation", model="kshitijthakkar/deepseek-v4-mini-3B-init")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kshitijthakkar/deepseek-v4-mini-3B-init")
model = AutoModelForCausalLM.from_pretrained("kshitijthakkar/deepseek-v4-mini-3B-init")
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 kshitijthakkar/deepseek-v4-mini-3B-init with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kshitijthakkar/deepseek-v4-mini-3B-init"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kshitijthakkar/deepseek-v4-mini-3B-init",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kshitijthakkar/deepseek-v4-mini-3B-init

SGLang

How to use kshitijthakkar/deepseek-v4-mini-3B-init 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 "kshitijthakkar/deepseek-v4-mini-3B-init" \
    --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": "kshitijthakkar/deepseek-v4-mini-3B-init",
		"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 "kshitijthakkar/deepseek-v4-mini-3B-init" \
        --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": "kshitijthakkar/deepseek-v4-mini-3B-init",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kshitijthakkar/deepseek-v4-mini-3B-init with Docker Model Runner:
```
docker model run hf.co/kshitijthakkar/deepseek-v4-mini-3B-init
```

deepseek-v4-mini-3B-init / README.md

kshitijthakkar

Re-upload as 4x2GB sharded safetensors for parallel transfer

e1d16ef verified 25 days ago

preview code

raw

history blame contribute delete

3.19 kB

	---
	license: mit
	library_name: transformers
	tags:
	- deepseek-v4
	- mixture-of-experts
	- moe
	- mhc
	- csa
	- hca
	- scaffold
	- random-init
	pipeline_tag: text-generation
	---

	# DeepSeek-V4 Mini (3B) — randomly-initialized architecture replica

	Faithful small-scale (~3.2B total / ~1.10B activated per token)
	replica of the DeepSeek-V4 architecture, sized to be trainable on rented GPUs
	and to map cleanly onto the full-scale V4-Flash dimensions for weight slicing.

	This is a randomly-initialized scaffold — generates noise. Its purpose:
	- reference architecture for ablation / hyperparameter-search experiments
	- target for weight transfer / slicing from real V4-Pro / V4-Flash

	## Architecture summary

	\| \| Value \|
	\|---\|---\|
	\| hidden_size \| 1536 \|
	\| num_hidden_layers \| 28 \|
	\| num_attention_heads \| 24 \|
	\| num_key_value_heads \| 1 (MQA) \|
	\| head_dim \| 64 \|
	\| q_lora_rank / o_lora_rank \| 512 / 512 \|
	\| qk_rope_head_dim \| 32 \|
	\| o_groups \| 4 \|
	\| n_routed_experts \| 24 \|
	\| n_shared_experts \| 1 \|
	\| num_experts_per_tok \| 4 \|
	\| num_hash_layers \| 2 \|
	\| moe_intermediate_size \| 768 \|
	\| compress_ratios \| [0, 0, 4, 112, 4, 112, 4, 112, 4, 112, 4, 112, 4, 112, 4, 112, 4, 112, 4, 112, 4, 112, 4, 112, 4, 112, 4, 0] \|
	\| index_topk / heads / head_dim \| 192 / 16 / 96 \|
	\| sliding_window \| 64 \|
	\| max_position_embeddings \| 1,048,576 (YaRN factor=16) \|
	\| vocab_size \| 129280 (real V4-Flash tokenizer) \|
	\| num_nextn_predict_layers \| 1 (V3-style MTP) \|
	\| hc_mult (n_hc) \| 4 \|
	\| Storage dtype \| bfloat16 \|

	## Quick start

	```python
	from huggingface_hub import login, snapshot_download
	login() # private repo

	local = snapshot_download(repo_id="kshitijthakkar/deepseek-v4-mini-3B-init")

	import sys, os
	sys.path.insert(0, os.path.join(local, "code"))
	import deepseek_v4 # registers DeepseekV4{Config,ForCausalLM} with HF auto classes

	import torch
	from transformers import AutoModelForCausalLM, AutoTokenizer

	tok = AutoTokenizer.from_pretrained(local)
	model = AutoModelForCausalLM.from_pretrained(local, torch_dtype=torch.bfloat16)
	model.eval()

	ids = tok.apply_chat_template(
	[{"role": "user", "content": "Hello"}],
	return_tensors="pt", add_generation_prompt=True, return_dict=True,
	)
	with torch.no_grad():
	out = model(input_ids=ids["input_ids"])
	print(out.logits.shape)
	```

	## Components implemented

	mHC (Sinkhorn-Knopp) · CSA + Lightning Indexer · HCA · pure sliding-window ·
	Shared-KV MQA + grouped output projection (per-group `wo_a`) · partial RoPE +
	output `-i` rotation · attention sink · DeepseekMoE with `sqrt(softplus)`
	routing · hash-routed early layers · clamped SwiGLU · MTP head · YaRN.

	Every component is bit-equivalent in math to the official `inference/model.py`
	+ `kernel.py:hc_split_sinkhorn` (FP4/FP8 quantization and Hadamard rotation
	are skipped — those are inference optimizations, not architecture).

	## Citation

	```bibtex
	@misc{deepseek_v4_2026,
	author = {DeepSeek-AI},
	title = {DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence},
	year = {2026},
	url = {https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash}
	}
	```