Downloads · 30 days
193
25% of all-time downloads
PPCM
Xinmu7/PPCM
PPCM is a text generation model from Xinmu7. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
PPCM is a ~9M three-layer encoder (CCEL → CTIL → CPRL) over Top-7 candidates. It ranks causally consistent paths in one pass, then the target model verifies the top path.
All-time downloads
760
Public
Parameters
1.1B
2.1 GB on disk
Likes
3
Public
Repo makeup
Click a slice to open those files.
.safetensors2.1 GB · 100%
Parameter types
How the weights are stored.
BF161B · 99%
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3-8B-PPCM
PPCM is a ~9M three-layer encoder (CCEL → CTIL → CPRL) over Top-7 candidates. It ranks causally consistent paths in one pass, then the target model verifies the top path.
This repo is not a standalone chat model. Load Qwen3-8B as the target.
| Code | github.com/Xinmu-Tantai/PPCM |
| Target | Qwen/Qwen3-8B |
| Speculative length | 7 (block_size = 8), Top-7 candidates |
| Extra params | 8.8M |
On Qwen3-8B / GSM8K (T = 0, L = 7): τ = 5.97, 5.18× speedup.
Files
model.safetensors— 5-layer causal draft +ppcm.ccel/ppcm.ctil/ppcm.cprl/ppcm.scoreconfig.json—PPCMDraftModel,num_speculative_tokens: 7ppcm.py— Hugging FaceAutoModelclass
Usage
Serve with the PPCM vLLM code:
TARGET_MODEL=Qwen/Qwen3-8B
DRAFT_MODEL=Xinmu7/PPCM
NUM_SPECULATIVE_TOKENS=7
License
Apache License 2.0.
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3
- License
- apache-2.0
- Created
- Sep 2, 2026
- Updated
- Sep 3, 2026