shibing624 / text-generation updated 10 months ago

macbert4csc-base-chinese

Name: macbert4csc-base-chinese
Author: shibing624

Correct-Precision Correct-Recall Correct-F1 -------- Chararcter-level 93.72 86.40 89.91 Sentence-level 82.64 73.66 77.89

Params

100 M

Context

512

Downloads 30d

542 K

Likes

119

Commercial use: allowed apache-2.0 Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

547 K533 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	f32	0.4 GB	1.0 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/macbert4csc-base-chinese
{
  "hf_id": "shibing624/macbert4csc-base-chinese",
  "params_b": 0.10,
  "context_length": 512,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 541710,
  "vram_estimates": [
    { "quant": "f32", "gb": 1.0 }
  ],
  "updated_at": "2026-07-28T18:04:57Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: BertForMaskedLM
Parameters: 100 M
Tensor type: F32
Context length: 512
Vocabulary: 21,128
Layers / heads: 12 / 12
Licence: apache-2.0
First seen on the Hub: 2022-03-02
Training datasets: shibing624/CSC
Added to our catalog: 2026-07-28

Compare with

gpt2 13.7 M distilgpt2 2.6 M pythia-160m 2.5 M gemma-3-270m 2.1 M SmolLM2-135M-Instruct 2.0 M SmolLM2-135M 1.8 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB