Instructions to use NobodyExistsOnTheInternet/bigseek_3p2t with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NobodyExistsOnTheInternet/bigseek_3p2t with Transformers:

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

pipe = pipeline("text-generation", model="NobodyExistsOnTheInternet/bigseek_3p2t")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NobodyExistsOnTheInternet/bigseek_3p2t")
model = AutoModelForCausalLM.from_pretrained("NobodyExistsOnTheInternet/bigseek_3p2t", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NobodyExistsOnTheInternet/bigseek_3p2t with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NobodyExistsOnTheInternet/bigseek_3p2t"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NobodyExistsOnTheInternet/bigseek_3p2t",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/NobodyExistsOnTheInternet/bigseek_3p2t

SGLang

How to use NobodyExistsOnTheInternet/bigseek_3p2t 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 "NobodyExistsOnTheInternet/bigseek_3p2t" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NobodyExistsOnTheInternet/bigseek_3p2t",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "NobodyExistsOnTheInternet/bigseek_3p2t" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NobodyExistsOnTheInternet/bigseek_3p2t",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use NobodyExistsOnTheInternet/bigseek_3p2t with Docker Model Runner:
```
docker model run hf.co/NobodyExistsOnTheInternet/bigseek_3p2t
```

bigseek_3p2t / rowwise_kv_variant_report.json

NobodyExistsOnTheInternet

Add files using upload-large-folder tool

c6f0223 verified 3 months ago

Raw

History Blame

2.67 kB

	{
	"base_model": "/home/shared/models/DeepSeek-V4-Pro-Base",
	"created_utc": "2026-06-03T14:51:11Z",
	"eps": 1e-12,
	"instruct_model": "/home/shared/models/DeepSeek-V4-Pro",
	"out": "/home/ggb/mergehell/outputs/deepseek_v4_pro_base_instruct_widthwise_headstack_3p2t_factorized_rowwise_kv",
	"rewrite_reports": [
	{
	"changed_count": 183,
	"changed_sample": [
	"layers.0.attn.compressor.wgate.weight",
	"layers.0.attn.compressor.wkv.weight",
	"layers.0.attn.wkv.weight",
	"layers.1.attn.compressor.wgate.weight",
	"layers.1.attn.compressor.wkv.weight",
	"layers.1.attn.wkv.weight",
	"layers.10.attn.compressor.wgate.weight",
	"layers.10.attn.compressor.wkv.weight",
	"layers.10.attn.wkv.weight",
	"layers.11.attn.compressor.wgate.weight"
	],
	"dtype_counts": {
	"torch.bfloat16": 427,
	"torch.float32": 305,
	"torch.float8_e4m3fn": 183
	},
	"elapsed_s": 87.53589153289795,
	"file": "model-00063-main-attention.safetensors",
	"output_file_size": 37940382360,
	"source_file_size": 37940385264,
	"tensor_count": 915
	},
	{
	"changed_count": 1,
	"changed_sample": [
	"mtp.0.attn.wkv.weight"
	],
	"dtype_counts": {
	"torch.bfloat16": 12,
	"torch.float32": 19,
	"torch.float8_e4m3fn": 8
	},
	"elapsed_s": 9.863497018814087,
	"file": "model-00069-mtp-non-experts.safetensors",
	"output_file_size": 4558636948,
	"source_file_size": 4558636948,
	"tensor_count": 39
	}
	],
	"slerp_dot_threshold": 0.9995,
	"slerp_t": 0.5,
	"source": "/home/ggb/mergehell/outputs/deepseek_v4_pro_base_instruct_widthwise_headstack_3p2t_factorized",
	"symlinked_safetensor_count": 68,
	"target_key_count": 184,
	"target_suffixes": [
	".attn.wkv.weight",
	".attn.compressor.wkv.weight",
	".attn.compressor.wgate.weight"
	],
	"targets_by_file": {
	"model-00063-main-attention.safetensors": 183,
	"model-00069-mtp-non-experts.safetensors": 1
	},
	"verify": {
	"missing_targets": [],
	"regular_files": [
	"model-00063-main-attention.safetensors",
	"model-00069-mtp-non-experts.safetensors"
	],
	"rewrite_files": [
	"model-00063-main-attention.safetensors",
	"model-00069-mtp-non-experts.safetensors"
	],
	"safetensor_files_indexed": 70,
	"safetensor_regular_count": 2,
	"safetensor_symlink_count": 68,
	"target_files": {
	"model-00063-main-attention.safetensors": 183,
	"model-00069-mtp-non-experts.safetensors": 1
	},
	"target_key_count": 184,
	"wrong_file_targets": []
	}
	}