DeepSeek-V4 Mini (6B) — randomly-initialized architecture replica
Faithful small-scale (~8.1B total / ~2.21B 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 | 2048 |
| num_hidden_layers | 32 |
| num_attention_heads | 32 |
| num_key_value_heads | 1 (MQA) |
| head_dim | 64 |
| q_lora_rank / o_lora_rank | 768 / 768 |
| qk_rope_head_dim | 32 |
| o_groups | 8 |
| n_routed_experts | 32 |
| n_shared_experts | 1 |
| num_experts_per_tok | 4 |
| num_hash_layers | 2 |
| moe_intermediate_size | 1024 |
| compress_ratios | [0, 0, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 0] |
| index_topk / heads / head_dim | 256 / 32 / 128 |
| sliding_window | 128 |
| 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
from huggingface_hub import login, snapshot_download
login() # private repo
local = snapshot_download(repo_id="kshitijthakkar/deepseek-v4-mini-6B-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
@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}
}