tiny-d1-2B-for-testing

This is a modified, damaged copy of LiquidAI/d1-2B, made only to test software. Its output is gibberish. Do not use it for anything else.

It keeps the architecture, tokenizer, chat template and calibration of d1-2B, so it runs the same code paths as the real model in llama.cpp (lfm3-d1 decision type: non-causal attention, packed questions, image input), but it is small enough for CI.

GGUF version: ggml-org-dev/tiny-d1-2B-for-testing-GGUF

Changes from the original model

Sliced from the safetensors with slice_d1.py, which follows the slice-model skill of llama.cpp:

  • Text model: 4 of 24 layers (0, 2, 3, 4), hidden size 2048 -> 64, heads 16 -> 2, KV heads 4 -> 1, FFN 7680 -> 256 (head_dim 128 kept)
  • Vision encoder: 2 of 14 layers (0, 2), hidden size 1024 -> 128, heads 16 -> 2, KV heads 8 -> 1, FFN 2560 -> 256, projector 4096 -> 256
  • The Python code of the original repo is not included

License

Derived from d1-2B by Liquid AI, under the LFM Open License v1.0.

Downloads last month
31
Safetensors
Model size
9.18M params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for ggml-org-dev/tiny-d1-2B-for-testing

Finetuned
LiquidAI/d1-2B
Finetuned
(12)
this model
Quantizations
1 model