Downloads · 30 days
37
16% of all-time downloads
Qwen2.5-3B-KV-Compressed-50
amjd-ai/Qwen2.5-3B-KV-Compressed-50
Qwen2.5-3B-KV-Compressed-50 is a text generation model from amjd-ai. 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.
An optimized, fully-fused version of Qwen2.5-3B featuring real-time 50% Key-Value (KV) Cache Compression using Bipartite Cosine Similarity token merging inside the self-attention mechanism.
All-time downloads
228
Public
Parameters
3.1B
10.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6.2 GB · 60%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen2
- Access
- Public
- Created
- Aug 23, 2026
- Updated
- Aug 23, 2026
- SHA
- e235d41d
Try a prompt
Model card
From the Hugging Face model README
Qwen2.5-3B KV-Compressed (50% Memory Reduction)
An optimized, fully-fused version of Qwen2.5-3B featuring real-time 50% Key-Value (KV) Cache Compression using Bipartite Cosine Similarity token merging inside the self-attention mechanism.
Benchmark & Key Achievements
- 50.0% Direct KV Memory Reduction: Halves KV cache footprint during long-context generation.
- Bilingual & Coding Competence: Preserves full conversational reasoning in Arabic, English, and Python.
- Zero Generation Latency Overhead: Highly efficient runtime execution with full gradient alignment.
Model Details
- Base Architecture: Qwen2.5-3B
- Compression Mechanism: Dynamic KV Chunk Merging ($K$ & $V$ projection alignment)
- Parameters: 3.09B
- Task
- Text Generation
- Library
- transformers
- Type
- qwen2
- License
- apache-2.0
- Languages
- en, ar
- Created
- Aug 23, 2026
- Updated
- Aug 23, 2026