tiny-Qwen3.5-4B-for-testing
This is a modified, damaged copy of Qwen/Qwen3.5-4B (revision
851bf6e), made only to test software. Its output is gibberish. Do not use it for anything else.
It keeps the architecture (hybrid linear attention / gated full attention, MTP layer, vision encoder), tokenizer and configs of Qwen3.5-4B, but it is small enough for CI. It is the base model of the tiny LoRA decision adapter ggml-org-dev/tiny-lev-for-testing: the llama.cpp converter downloads it and merges the adapter into it.
Changes from the original model
Sliced from the safetensors with slice_qwen35_lora.py, which follows the slice-model skill of llama.cpp:
- Text model: 4 of 32 layers (0, 1, 2, 3: 3 linear attention + 1 full attention), hidden size 2560 -> 32, FFN 9216 -> 128, heads 16 -> 2, KV heads 4 -> 1 (head_dim 256 kept), linear attention key heads 16 -> 2, value heads 32 -> 6 (head dims 128 kept)
- Token embedding: full vocabulary kept, narrowed to the hidden size (tied embeddings kept)
- MTP layer: kept, narrowed the same way
- Vision encoder: 24 -> 2 blocks, hidden size 1024 -> 128, heads 16 -> 2, FFN 4096 -> 256, output 2560 -> 32
License
Derived from Qwen3.5-4B by the Qwen team, under the Apache License 2.0.
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support