Update Moondream v2

[cryptoquick]

Excellent work on this project, the moondream example works great. One thing I'd like to try is the latest version of moondream. In the current readme, that's for "2025-01-09" in "vikhyatk/moondream2".

I've tried to update it myself, but I reached my limit. The furthest I got, and hopefully this is helpful information, is printing the new vars:

avx: true, neon: false, simd128: false, f16c: true
temp: -1.25 repeat-penalty: 1.00 repeat-last-n: 64
retrieved the files in 27.875484ms
model_file: "/home/hunter/.cache/huggingface/hub/models--vikhyatk--moondream2/snapshots/adcbcd1a6d27fc19974b18dc128eb51ef6837879/model.safetensors"
Tensors found in safetensors file:
  model.vision.blocks.9.mlp.fc1.bias => shape: [4304], dtype: F16
  model.vision.proj_mlp.fc1.bias => shape: [8192], dtype: F16
  model.region.coord_encoder.weight => shape: [2048, 256], dtype: F16
  model.text.blocks.0.attn.qkv.bias => shape: [6144], dtype: F16
  model.vision.blocks.16.mlp.fc1.bias => shape: [4304], dtype: F16
  model.text.blocks.2.mlp.fc1.bias => shape: [8192], dtype: F16
  model.vision.blocks.23.ln2.bias => shape: [1152], dtype: F16
  model.vision.blocks.24.mlp.fc2.weight => shape: [1152, 4304], dtype: F16
  model.vision.blocks.3.ln1.bias => shape: [1152], dtype: F16
  model.vision.post_ln.weight => shape: [1152], dtype: F16
  model.vision.blocks.23.mlp.fc2.weight => shape: [1152, 4304], dtype: F16
  model.text.blocks.0.attn.proj.weight => shape: [2048, 2048], dtype: F16
  model.text.blocks.3.attn.qkv.bias => shape: [6144], dtype: F16
  model.text.blocks.1.mlp.fc2.bias => shape: [2048], dtype: F16
  model.vision.blocks.16.attn.qkv.bias => shape: [3456], dtype: F16
  model.text.blocks.16.attn.qkv.bias => shape: [6144], dtype: F16
  model.vision.blocks.12.ln1.bias => shape: [1152], dtype: F16
  model.vision.blocks.1.attn.proj.bias => shape: [1152], dtype: F16
  model.vision.blocks.26.ln1.bias => shape: [1152], dtype: F16
  model.vision.blocks.26.mlp.fc2.bias => shape: [1152], dtype: F16
  model.text.blocks.23.mlp.fc1.bias => shape: [8192], dtype: F16
  model.text.blocks.14.attn.proj.weight => shape: [2048, 2048], dtype: F16
  model.vision.blocks.0.attn.qkv.bias => shape: [3456], dtype: F16
  model.vision.blocks.19.mlp.fc1.weight => shape: [4304, 1152], dtype: F16
  model.text.blocks.16.mlp.fc1.weight => shape: [8192, 2048], dtype: F16
  model.vision.proj_mlp.fc2.bias => shape: [2048], dtype: F16
  model.text.blocks.16.attn.qkv.weight => shape: [6144, 2048], dtype: F16
  model.vision.blocks.18.mlp.fc1.bias => shape: [4304], dtype: F16
  model.text.blocks.4.ln.weight => shape: [2048], dtype: F16
  model.vision.blocks.21.mlp.fc1.bias => shape: [4304], dtype: F16
  model.vision.blocks.10.mlp.fc1.bias => shape: [4304], dtype: F16
  model.text.blocks.16.attn.proj.bias => shape: [2048], dtype: F16
  model.text.blocks.17.mlp.fc1.weight => shape: [8192, 2048], dtype: F16
  model.vision.blocks.18.attn.proj.bias => shape: [1152], dtype: F16
  model.text.blocks.20.attn.proj.bias => shape: [2048], dtype: F16
  model.text.blocks.9.mlp.fc2.weight => shape: [2048, 8192], dtype: F16
  model.vision.blocks.8.ln1.weight => shape: [1152], dtype: F16
  model.text.blocks.18.mlp.fc2.weight => shape: [2048, 8192], dtype: F16
  model.vision.blocks.17.attn.proj.bias => shape: [1152], dtype: F16
  model.text.blocks.11.mlp.fc1.bias => shape: [8192], dtype: F16
  model.text.blocks.3.attn.proj.weight => shape: [2048, 2048], dtype: F16
  model.vision.blocks.17.mlp.fc2.weight => shape: [1152, 4304], dtype: F16
  model.vision.blocks.6.ln1.bias => shape: [1152], dtype: F16
  model.vision.blocks.24.mlp.fc2.bias => shape: [1152], dtype: F16
  model.text.blocks.7.mlp.fc1.weight => shape: [8192, 2048], dtype: F16
  model.vision.blocks.24.attn.proj.weight => shape: [1152, 1152], dtype: F16
  model.text.blocks.14.mlp.fc2.bias => shape: [2048], dtype: F16
  model.text.blocks.15.attn.proj.bias => shape: [2048], dtype: F16
  model.text.blocks.3.mlp.fc1.weight => shape: [8192, 2048], dtype: F16
  model.text.blocks.1.attn.qkv.bias => shape: [6144], dtype: F16
  model.text.blocks.5.mlp.fc2.weight => shape: [2048, 8192], dtype: F16
  model.text.blocks.21.attn.qkv.weight => shape: [6144, 2048], dtype: F16
  model.vision.blocks.22.mlp.fc1.bias => shape: [4304], dtype: F16
  model.vision.blocks.7.attn.proj.weight => shape: [1152, 1152], dtype: F16
  model.vision.blocks.16.attn.qkv.weight => shape: [3456, 1152], dtype: F16
  model.vision.blocks.23.attn.qkv.bias => shape: [3456], dtype: F16
  model.text.blocks.13.ln.weight => shape: [2048], dtype: F16
  model.vision.blocks.17.ln2.weight => shape: [1152], dtype: F16
  model.vision.blocks.20.mlp.fc2.bias => shape: [1152], dtype: F16
  model.text.blocks.13.mlp.fc2.bias => shape: [2048], dtype: F16
  model.vision.blocks.26.ln2.bias => shape: [1152], dtype: F16
  model.text.blocks.11.attn.proj.weight => shape: [2048, 2048], dtype: F16
  model.text.blocks.2.ln.weight => shape: [2048], dtype: F16
  model.text.blocks.17.attn.proj.weight => shape: [2048, 2048], dtype: F16
  model.text.blocks.20.attn.proj.weight => shape: [2048, 2048], dtype: F16
  model.text.blocks.22.attn.qkv.weight => shape: [6144, 2048], dtype: F16
  model.vision.blocks.1.mlp.fc1.bias => shape: [4304], dtype: F16
  model.vision.blocks.12.attn.proj.weight => shape: [1152, 1152], dtype: F16
  model.text.blocks.2.mlp.fc2.bias => shape: [2048], dtype: F16
  model.vision.blocks.10.mlp.fc1.weight => shape: [4304, 1152], dtype: F16
  model.vision.blocks.12.mlp.fc2.bias => shape: [1152], dtype: F16
  model.vision.blocks.13.attn.qkv.weight => shape: [3456, 1152], dtype: F16
  model.vision.blocks.15.attn.proj.bias => shape: [1152], dtype: F16
  model.vision.blocks.8.mlp.fc1.weight => shape: [4304, 1152], dtype: F16
  model.text.blocks.2.attn.proj.weight => shape: [2048, 2048], dtype: F16
  model.text.blocks.4.mlp.fc1.weight => shape: [8192, 2048], dtype: F16
  model.text.blocks.18.attn.proj.bias => shape: [2048], dtype: F16
  model.vision.blocks.8.ln2.weight => shape: [1152], dtype: F16
  model.text.blocks.3.mlp.fc2.weight => shape: [2048, 8192], dtype: F16
  model.text.post_ln.bias => shape: [2048], dtype: F16
  model.vision.blocks.18.ln2.weight => shape: [1152], dtype: F16
  model.vision.blocks.6.mlp.fc1.weight => shape: [4304, 1152], dtype: F16
  model.text.blocks.1.mlp.fc1.bias => shape: [8192], dtype: F16
  model.text.blocks.10.attn.proj.weight => shape: [2048, 2048], dtype: F16
  model.vision.blocks.10.mlp.fc2.weight => shape: [1152, 4304], dtype: F16
  model.vision.blocks.12.ln2.weight => shape: [1152], dtype: F16
  model.vision.blocks.19.attn.proj.bias => shape: [1152], dtype: F16
  model.text.blocks.4.attn.proj.bias => shape: [2048], dtype: F16
  model.vision.blocks.25.mlp.fc2.bias => shape: [1152], dtype: F16
  model.text.blocks.4.attn.qkv.weight => shape: [6144, 2048], dtype: F16
  model.text.blocks.20.attn.qkv.bias => shape: [6144], dtype: F16
  model.vision.blocks.1.mlp.fc2.bias => shape: [1152], dtype: F16
  model.vision.blocks.22.attn.proj.bias => shape: [1152], dtype: F16
  model.vision.blocks.18.attn.qkv.bias => shape: [3456], dtype: F16
  model.text.blocks.21.mlp.fc1.weight => shape: [8192, 2048], dtype: F16
  model.text.blocks.12.attn.qkv.bias => shape: [6144], dtype: F16
  model.text.blocks.14.attn.proj.bias => shape: [2048], dtype: F16
  model.text.blocks.2.attn.proj.bias => shape: [2048], dtype: F16
  model.vision.blocks.0.mlp.fc2.weight => shape: [1152, 4304], dtype: F16
  model.text.blocks.7.ln.bias => shape: [2048], dtype: F16
  model.vision.blocks.7.mlp.fc2.weight => shape: [1152, 4304], dtype: F16
  model.text.blocks.12.attn.qkv.weight => shape: [6144, 2048], dtype: F16
  model.vision.blocks.21.attn.qkv.bias => shape: [3456], dtype: F16
  model.vision.blocks.22.attn.qkv.weight => shape: [3456, 1152], dtype: F16
  model.vision.blocks.3.mlp.fc2.bias => shape: [1152], dtype: F16
  model.vision.blocks.22.attn.qkv.bias => shape: [3456], dtype: F16
  model.text.blocks.4.mlp.fc1.bias => shape: [8192], dtype: F16
  model.vision.blocks.5.ln1.weight => shape: [1152], dtype: F16
  model.vision.blocks.8.mlp.fc2.bias => shape: [1152], dtype: F16
  model.vision.blocks.13.mlp.fc2.weight => shape: [1152, 4304], dtype: F16
  model.text.blocks.1.attn.proj.weight => shape: [2048, 2048], dtype: F16
  model.vision.blocks.23.mlp.fc1.weight => shape: [4304, 1152], dtype: F16
  model.text.blocks.19.mlp.fc1.bias => shape: [8192], dtype: F16
  model.vision.blocks.11.ln1.bias => shape: [1152], dtype: F16
  model.vision.blocks.17.ln2.bias => shape: [1152], dtype: F16
  model.text.blocks.16.ln.bias => shape: [2048], dtype: F16
  model.vision.blocks.0.mlp.fc2.bias => shape: [1152], dtype: F16
  model.vision.blocks.2.ln2.weight => shape: [1152], dtype: F16
  model.text.blocks.2.mlp.fc2.weight => shape: [2048, 8192], dtype: F16
  model.vision.blocks.24.mlp.fc1.bias => shape: [4304], dtype: F16
  model.text.blocks.23.ln.bias => shape: [2048], dtype: F16
  model.text.blocks.10.attn.qkv.weight => shape: [6144, 2048], dtype: F16
  model.text.blocks.14.ln.weight => shape: [2048], dtype: F16
  model.text.blocks.10.ln.weight => shape: [2048], dtype: F16
  model.vision.blocks.4.mlp.fc1.weight => shape: [4304, 1152], dtype: F16
  model.text.blocks.6.attn.qkv.weight => shape: [6144, 2048], dtype: F16
  model.text.blocks.0.ln.bias => shape: [2048], dtype: F16
  model.text.blocks.10.mlp.fc2.weight => shape: [2048, 8192], dtype: F16
  model.text.blocks.22.mlp.fc2.bias => shape: [2048], dtype: F16
  model.vision.blocks.0.mlp.fc1.bias => shape: [4304], dtype: F16
  model.vision.blocks.9.attn.proj.bias => shape: [1152], dtype: F16
  model.text.blocks.13.attn.proj.weight => shape: [2048, 2048], dtype: F16
  model.text.blocks.6.ln.bias => shape: [2048], dtype: F16
  model.vision.blocks.24.ln1.bias => shape: [1152], dtype: F16
  model.vision.blocks.12.attn.qkv.bias => shape: [3456], dtype: F16
  model.vision.blocks.15.mlp.fc2.weight => shape: [1152, 4304], dtype: F16
  model.vision.blocks.3.mlp.fc2.weight => shape: [1152, 4304], dtype: F16
  model.vision.blocks.25.ln2.bias => shape: [1152], dtype: F16
  model.vision.blocks.19.mlp.fc2.weight => shape: [1152, 4304], dtype: F16
  model.region.size_encoder.bias => shape: [2048], dtype: F16
  model.text.blocks.9.mlp.fc2.bias => shape: [2048], dtype: F16
  model.text.blocks.0.mlp.fc2.weight => shape: [2048, 8192], dtype: F16
  model.vision.blocks.5.attn.qkv.bias => shape: [3456], dtype: F16
  model.vision.blocks.22.ln1.bias => shape: [1152], dtype: F16
  model.vision.blocks.26.attn.qkv.bias => shape: [3456], dtype: F16
  model.vision.blocks.11.attn.qkv.weight => shape: [3456, 1152], dtype: F16
  model.vision.blocks.7.ln1.bias => shape: [1152], dtype: F16
  model.vision.blocks.17.ln1.bias => shape: [1152], dtype: F16
  model.vision.blocks.1.ln1.bias => shape: [1152], dtype: F16
  model.text.blocks.19.mlp.fc2.bias => shape: [2048], dtype: F16
  model.text.blocks.7.mlp.fc1.bias => shape: [8192], dtype: F16
  model.vision.blocks.24.ln1.weight => shape: [1152], dtype: F16
  model.vision.blocks.7.attn.qkv.bias => shape: [3456], dtype: F16
  model.vision.blocks.5.attn.proj.weight => shape: [1152, 1152], dtype: F16
  model.vision.blocks.12.attn.proj.bias => shape: [1152], dtype: F16
  model.text.blocks.1.mlp.fc2.weight => shape: [2048, 8192], dtype: F16
  model.text.blocks.17.ln.weight => shape: [2048], dtype: F16
  model.vision.blocks.10.ln2.weight => shape: [1152], dtype: F16
  model.vision.blocks.21.ln1.bias => shape: [1152], dtype: F16
  model.vision.blocks.7.mlp.fc1.weight => shape: [4304, 1152], dtype: F16
  model.text.blocks.22.mlp.fc1.weight => shape: [8192, 2048], dtype: F16
  model.vision.blocks.9.ln2.weight => shape: [1152], dtype: F16
  model.text.blocks.19.mlp.fc2.weight => shape: [2048, 8192], dtype: F16
  model.text.blocks.6.mlp.fc1.bias => shape: [8192], dtype: F16
  model.vision.blocks.13.mlp.fc1.weight => shape: [4304, 1152], dtype: F16
  model.text.blocks.13.mlp.fc2.weight => shape: [2048, 8192], dtype: F16
  model.vision.blocks.14.ln2.weight => shape: [1152], dtype: F16
  model.vision.blocks.19.attn.qkv.weight => shape: [3456, 1152], dtype: F16
  model.text.blocks.11.mlp.fc2.weight => shape: [2048, 8192], dtype: F16
  model.vision.blocks.14.mlp.fc1.bias => shape: [4304], dtype: F16
  model.vision.blocks.2.ln1.weight => shape: [1152], dtype: F16
  model.text.blocks.14.mlp.fc1.weight => shape: [8192, 2048], dtype: F16
  model.vision.blocks.10.attn.proj.bias => shape: [1152], dtype: F16
  model.text.blocks.17.ln.bias => shape: [2048], dtype: F16
  model.text.blocks.17.attn.qkv.bias => shape: [6144], dtype: F16
  model.region.coord_decoder.fc2.bias => shape: [1024], dtype: F16
  model.region.size_decoder.fc2.weight => shape: [2048, 8192], dtype: F16
  model.text.blocks.17.attn.qkv.weight => shape: [6144, 2048], dtype: F16
  model.vision.blocks.0.ln1.weight => shape: [1152], dtype: F16
  model.text.blocks.10.ln.bias => shape: [2048], dtype: F16
  model.text.blocks.17.attn.proj.bias => shape: [2048], dtype: F16
  model.vision.blocks.21.mlp.fc2.bias => shape: [1152], dtype: F16
  model.vision.blocks.3.attn.qkv.bias => shape: [3456], dtype: F16
  model.text.blocks.14.mlp.fc2.weight => shape: [2048, 8192], dtype: F16
  model.vision.blocks.5.attn.qkv.weight => shape: [3456, 1152], dtype: F16
  model.text.blocks.9.mlp.fc1.bias => shape: [8192], dtype: F16
  model.vision.blocks.5.mlp.fc2.weight => shape: [1152, 4304], dtype: F16
  model.vision.blocks.8.ln1.bias => shape: [1152], dtype: F16
  model.vision.blocks.15.mlp.fc1.weight => shape: [4304, 1152], dtype: F16
  model.vision.blocks.8.mlp.fc1.bias => shape: [4304], dtype: F16
  model.vision.proj_mlp.fc1.weight => shape: [8192, 2304], dtype: F16
  model.vision.blocks.21.attn.qkv.weight => shape: [3456, 1152], dtype: F16
  model.vision.blocks.24.attn.qkv.bias => shape: [3456], dtype: F16
  model.vision.blocks.15.attn.qkv.bias => shape: [3456], dtype: F16
  model.vision.proj_mlp.fc2.weight => shape: [2048, 8192], dtype: F16
  model.vision.blocks.11.mlp.fc2.bias => shape: [1152], dtype: F16
  model.vision.blocks.2.attn.proj.bias => shape: [1152], dtype: F16
  model.vision.blocks.11.ln2.weight => shape: [1152], dtype: F16
  model.vision.blocks.20.mlp.fc1.weight => shape: [4304, 1152], dtype: F16
  model.vision.blocks.20.mlp.fc1.bias => shape: [4304], dtype: F16
  model.text.blocks.3.ln.weight => shape: [2048], dtype: F16
  model.text.blocks.8.attn.qkv.bias => shape: [6144], dtype: F16
  model.vision.blocks.16.ln2.bias => shape: [1152], dtype: F16
  model.text.blocks.22.attn.proj.weight => shape: [2048, 2048], dtype: F16
  model.region.coord_encoder.bias => shape: [2048], dtype: F16
  model.text.blocks.16.mlp.fc1.bias => shape: [8192], dtype: F16
  model.text.blocks.18.mlp.fc1.weight => shape: [8192, 2048], dtype: F16
  model.vision.blocks.12.mlp.fc2.weight => shape: [1152, 4304], dtype: F16
  model.vision.blocks.0.attn.proj.weight => shape: [1152, 1152], dtype: F16
  model.text.blocks.18.mlp.fc1.bias => shape: [8192], dtype: F16
  model.text.blocks.21.mlp.fc1.bias => shape: [8192], dtype: F16
  model.text.blocks.3.attn.qkv.weight => shape: [6144, 2048], dtype: F16
  model.text.blocks.4.attn.proj.weight => shape: [2048, 2048], dtype: F16
  model.vision.blocks.1.mlp.fc1.weight => shape: [4304, 1152], dtype: F16
  model.text.blocks.7.attn.proj.weight => shape: [2048, 2048], dtype: F16
  model.vision.blocks.14.attn.proj.bias => shape: [1152], dtype: F16
  model.vision.blocks.14.ln2.bias => shape: [1152], dtype: F16
  model.vision.blocks.15.attn.qkv.weight => shape: [3456, 1152], dtype: F16
  model.vision.blocks.16.mlp.fc2.weight => shape: [1152, 4304], dtype: F16
  model.vision.blocks.17.mlp.fc2.bias => shape: [1152], dtype: F16
  model.text.blocks.12.ln.weight => shape: [2048], dtype: F16
  model.vision.blocks.4.attn.proj.bias => shape: [1152], dtype: F16
  model.text.blocks.4.mlp.fc2.bias => shape: [2048], dtype: F16
  model.vision.blocks.19.ln1.bias => shape: [1152], dtype: F16
  model.vision.blocks.0.ln2.bias => shape: [1152], dtype: F16
  model.vision.blocks.6.attn.qkv.bias => shape: [3456], dtype: F16
  model.vision.blocks.26.ln2.weight => shape: [1152], dtype: F16
  model.vision.blocks.9.ln2.bias => shape: [1152], dtype: F16
  model.vision.blocks.4.attn.qkv.weight => shape: [3456, 1152], dtype: F16
  model.text.blocks.0.ln.weight => shape: [2048], dtype: F16
  model.vision.blocks.11.ln2.bias => shape: [1152], dtype: F16
  model.vision.blocks.17.attn.proj.weight => shape: [1152, 1152], dtype: F16
  model.vision.blocks.3.mlp.fc1.bias => shape: [4304], dtype: F16
  model.text.blocks.6.attn.proj.weight => shape: [2048, 2048], dtype: F16
  model.vision.blocks.23.ln1.weight => shape: [1152], dtype: F16
  model.vision.blocks.15.ln2.weight => shape: [1152], dtype: F16
  model.vision.blocks.15.ln1.weight => shape: [1152], dtype: F16
  model.text.blocks.8.attn.proj.bias => shape: [2048], dtype: F16
  model.vision.blocks.23.attn.proj.bias => shape: [1152], dtype: F16
  model.text.blocks.12.mlp.fc2.weight => shape: [2048, 8192], dtype: F16
  model.vision.blocks.6.ln1.weight => shape: [1152], dtype: F16
  model.vision.blocks.7.mlp.fc2.bias => shape: [1152], dtype: F16
  model.vision.blocks.8.attn.qkv.weight => shape: [3456, 1152], dtype: F16
  model.text.blocks.11.ln.weight => shape: [2048], dtype: F16
  model.vision.blocks.7.ln2.weight => shape: [1152], dtype: F16
  model.text.blocks.4.attn.qkv.bias => shape: [6144], dtype: F16
  model.vision.blocks.10.attn.qkv.weight => shape: [3456, 1152], dtype: F16
  model.text.blocks.3.ln.bias => shape: [2048], dtype: F16
  model.text.blocks.14.attn.qkv.weight => shape: [6144, 2048], dtype: F16
  model.text.blocks.20.mlp.fc1.bias => shape: [8192], dtype: F16
  model.text.blocks.3.mlp.fc2.bias => shape: [2048], dtype: F16
  model.vision.blocks.25.attn.qkv.bias => shape: [3456], dtype: F16
  model.text.blocks.5.attn.proj.weight => shape: [2048, 2048], dtype: F16
  model.vision.blocks.11.mlp.fc2.weight => shape: [1152, 4304], dtype: F16
  model.text.blocks.5.ln.weight => shape: [2048], dtype: F16
  model.text.wte => shape: [51200, 2048], dtype: F16
  model.vision.blocks.4.mlp.fc1.bias => shape: [4304], dtype: F16
  model.vision.blocks.5.ln1.bias => shape: [1152], dtype: F16
  model.text.blocks.6.mlp.fc1.weight => shape: [8192, 2048], dtype: F16
  model.vision.blocks.11.attn.qkv.bias => shape: [3456], dtype: F16
  model.vision.blocks.16.ln1.weight => shape: [1152], dtype: F16
  model.text.blocks.9.attn.qkv.bias => shape: [6144], dtype: F16
  model.vision.blocks.6.mlp.fc1.bias => shape: [4304], dtype: F16
  model.text.blocks.12.ln.bias => shape: [2048], dtype: F16
  model.vision.blocks.8.ln2.bias => shape: [1152], dtype: F16
  model.text.blocks.11.mlp.fc2.bias => shape: [2048], dtype: F16
  model.text.blocks.3.mlp.fc1.bias => shape: [8192], dtype: F16
  model.text.blocks.8.attn.qkv.weight => shape: [6144, 2048], dtype: F16
  model.vision.blocks.14.mlp.fc1.weight => shape: [4304, 1152], dtype: F16
  model.vision.blocks.24.mlp.fc1.weight => shape: [4304, 1152], dtype: F16
  model.vision.blocks.1.attn.proj.weight => shape: [1152, 1152], dtype: F16
  model.vision.blocks.7.mlp.fc1.bias => shape: [4304], dtype: F16
  model.text.blocks.3.attn.proj.bias => shape: [2048], dtype: F16
  model.region.size_encoder.weight => shape: [2048, 512], dtype: F16
  model.vision.blocks.6.ln2.weight => shape: [1152], dtype: F16
  model.vision.blocks.22.mlp.fc2.bias => shape: [1152], dtype: F16
  model.text.blocks.9.mlp.fc1.weight => shape: [8192, 2048], dtype: F16
  model.text.blocks.22.mlp.fc2.weight => shape: [2048, 8192], dtype: F16
  model.vision.blocks.16.attn.proj.bias => shape: [1152], dtype: F16
  model.vision.post_ln.bias => shape: [1152], dtype: F16
  model.text.blocks.1.ln.weight => shape: [2048], dtype: F16
  model.region.coord_decoder.fc1.bias => shape: [8192], dtype: F16
  model.vision.blocks.17.mlp.fc1.bias => shape: [4304], dtype: F16
  model.vision.blocks.5.ln2.weight => shape: [1152], dtype: F16
  model.vision.blocks.18.ln1.weight => shape: [1152], dtype: F16
  model.vision.blocks.10.attn.proj.weight => shape: [1152, 1152], dtype: F16
  model.vision.blocks.14.mlp.fc2.bias => shape: [1152], dtype: F16
  model.vision.blocks.14.attn.qkv.weight => shape: [3456, 1152], dtype: F16
  model.vision.blocks.5.ln2.bias => shape: [1152], dtype: F16
  model.text.blocks.22.attn.qkv.bias => shape: [6144], dtype: F16
  model.text.blocks.6.mlp.fc2.weight => shape: [2048, 8192], dtype: F16
  model.vision.blocks.25.attn.proj.weight => shape: [1152, 1152], dtype: F16
  model.text.blocks.7.attn.qkv.bias => shape: [6144], dtype: F16
  model.text.blocks.23.attn.proj.bias => shape: [2048], dtype: F16
  model.text.blocks.13.attn.qkv.weight => shape: [6144, 2048], dtype: F16
  model.text.blocks.19.attn.qkv.bias => shape: [6144], dtype: F16
  model.vision.blocks.14.mlp.fc2.weight => shape: [1152, 4304], dtype: F16
  model.vision.blocks.13.attn.qkv.bias => shape: [3456], dtype: F16
  model.vision.blocks.2.mlp.fc2.bias => shape: [1152], dtype: F16
  model.text.blocks.21.mlp.fc2.bias => shape: [2048], dtype: F16
  model.vision.blocks.10.ln2.bias => shape: [1152], dtype: F16
  model.vision.blocks.20.ln2.weight => shape: [1152], dtype: F16
  model.text.blocks.22.mlp.fc1.bias => shape: [8192], dtype: F16
  model.vision.blocks.14.attn.qkv.bias => shape: [3456], dtype: F16
  model.vision.blocks.20.ln1.bias => shape: [1152], dtype: F16
  model.text.blocks.10.attn.qkv.bias => shape: [6144], dtype: F16
  model.vision.blocks.13.mlp.fc1.bias => shape: [4304], dtype: F16
  model.text.blocks.5.ln.bias => shape: [2048], dtype: F16
  model.vision.blocks.13.ln1.bias => shape: [1152], dtype: F16
  model.text.blocks.8.mlp.fc1.weight => shape: [8192, 2048], dtype: F16
  model.vision.blocks.5.attn.proj.bias => shape: [1152], dtype: F16
  model.vision.blocks.18.ln1.bias => shape: [1152], dtype: F16
  model.text.blocks.15.mlp.fc1.bias => shape: [8192], dtype: F16
  model.text.blocks.17.mlp.fc1.bias => shape: [8192], dtype: F16
  model.text.blocks.23.mlp.fc2.bias => shape: [2048], dtype: F16
  model.vision.blocks.13.ln1.weight => shape: [1152], dtype: F16
  model.vision.blocks.13.ln2.bias => shape: [1152], dtype: F16
  model.vision.blocks.23.ln1.bias => shape: [1152], dtype: F16
  model.region.size_decoder.fc1.weight => shape: [8192, 2048], dtype: F16
  model.text.blocks.0.attn.proj.bias => shape: [2048], dtype: F16
  model.vision.blocks.23.mlp.fc1.bias => shape: [4304], dtype: F16
  model.text.blocks.5.attn.qkv.weight => shape: [6144, 2048], dtype: F16
  model.text.blocks.21.attn.proj.bias => shape: [2048], dtype: F16
  model.text.blocks.1.attn.proj.bias => shape: [2048], dtype: F16
  model.region.size_decoder.fc2.bias => shape: [2048], dtype: F16
  model.text.blocks.1.mlp.fc1.weight => shape: [8192, 2048], dtype: F16
  model.vision.blocks.26.attn.proj.weight => shape: [1152, 1152], dtype: F16
  model.vision.blocks.8.attn.qkv.bias => shape: [3456], dtype: F16
  model.vision.blocks.4.mlp.fc2.weight => shape: [1152, 4304], dtype: F16
  model.vision.blocks.11.attn.proj.weight => shape: [1152, 1152], dtype: F16
  model.text.blocks.15.ln.bias => shape: [2048], dtype: F16
  model.text.blocks.19.attn.proj.bias => shape: [2048], dtype: F16
  model.vision.blocks.22.ln2.bias => shape: [1152], dtype: F16
  model.text.blocks.13.mlp.fc1.weight => shape: [8192, 2048], dtype: F16
  model.text.blocks.20.ln.bias => shape: [2048], dtype: F16
  model.text.blocks.22.ln.bias => shape: [2048], dtype: F16
  model.text.blocks.7.mlp.fc2.weight => shape: [2048, 8192], dtype: F16
  model.text.blocks.9.ln.bias => shape: [2048], dtype: F16
  model.text.blocks.6.ln.weight => shape: [2048], dtype: F16
  model.text.blocks.23.mlp.fc1.weight => shape: [8192, 2048], dtype: F16
  model.text.blocks.6.attn.proj.bias => shape: [2048], dtype: F16
  model.text.post_ln.weight => shape: [2048], dtype: F16
  model.text.blocks.15.attn.proj.weight => shape: [2048, 2048], dtype: F16
  model.vision.blocks.15.attn.proj.weight => shape: [1152, 1152], dtype: F16
  model.vision.blocks.14.ln1.weight => shape: [1152], dtype: F16
  model.text.blocks.11.attn.qkv.bias => shape: [6144], dtype: F16
  model.vision.blocks.1.ln2.bias => shape: [1152], dtype: F16
  model.text.blocks.19.ln.bias => shape: [2048], dtype: F16
  model.text.blocks.12.mlp.fc2.bias => shape: [2048], dtype: F16
  model.text.blocks.18.attn.qkv.bias => shape: [6144], dtype: F16
  model.vision.blocks.1.mlp.fc2.weight => shape: [1152, 4304], dtype: F16
  model.text.blocks.13.ln.bias => shape: [2048], dtype: F16
  model.text.blocks.20.mlp.fc1.weight => shape: [8192, 2048], dtype: F16
  model.vision.blocks.18.attn.proj.weight => shape: [1152, 1152], dtype: F16
  model.text.blocks.4.ln.bias => shape: [2048], dtype: F16
  model.vision.blocks.20.attn.qkv.weight => shape: [3456, 1152], dtype: F16
  model.vision.blocks.3.ln2.weight => shape: [1152], dtype: F16
  model.text.blocks.5.attn.qkv.bias => shape: [6144], dtype: F16
  model.vision.blocks.11.ln1.weight => shape: [1152], dtype: F16
  model.vision.blocks.15.ln1.bias => shape: [1152], dtype: F16
  model.vision.blocks.22.attn.proj.weight => shape: [1152, 1152], dtype: F16
  model.vision.blocks.4.ln2.weight => shape: [1152], dtype: F16
  model.text.blocks.23.mlp.fc2.weight => shape: [2048, 8192], dtype: F16
  model.text.blocks.0.attn.qkv.weight => shape: [6144, 2048], dtype: F16
  model.text.blocks.17.mlp.fc2.weight => shape: [2048, 8192], dtype: F16
  model.text.blocks.22.attn.proj.bias => shape: [2048], dtype: F16
  model.vision.blocks.13.ln2.weight => shape: [1152], dtype: F16
  model.text.blocks.21.mlp.fc2.weight => shape: [2048, 8192], dtype: F16
  model.text.blocks.5.mlp.fc2.bias => shape: [2048], dtype: F16
  model.text.blocks.21.attn.qkv.bias => shape: [6144], dtype: F16
  model.text.blocks.10.attn.proj.bias => shape: [2048], dtype: F16
  model.text.blocks.12.attn.proj.bias => shape: [2048], dtype: F16
  model.text.blocks.15.mlp.fc2.bias => shape: [2048], dtype: F16
  model.text.blocks.20.attn.qkv.weight => shape: [6144, 2048], dtype: F16
  model.text.blocks.14.mlp.fc1.bias => shape: [8192], dtype: F16
  model.vision.blocks.3.attn.proj.weight => shape: [1152, 1152], dtype: F16
  model.region.size_decoder.fc1.bias => shape: [8192], dtype: F16
  model.vision.blocks.17.mlp.fc1.weight => shape: [4304, 1152], dtype: F16
  model.text.blocks.8.attn.proj.weight => shape: [2048, 2048], dtype: F16
  model.vision.blocks.22.ln1.weight => shape: [1152], dtype: F16
  model.text.blocks.23.attn.qkv.weight => shape: [6144, 2048], dtype: F16
  model.text.blocks.18.attn.proj.weight => shape: [2048, 2048], dtype: F16
  model.vision.blocks.25.attn.qkv.weight => shape: [3456, 1152], dtype: F16
  model.vision.blocks.3.attn.qkv.weight => shape: [3456, 1152], dtype: F16
  model.vision.blocks.3.mlp.fc1.weight => shape: [4304, 1152], dtype: F16
  model.text.blocks.12.mlp.fc1.bias => shape: [8192], dtype: F16
  model.text.blocks.20.mlp.fc2.bias => shape: [2048], dtype: F16
  model.text.blocks.8.mlp.fc1.bias => shape: [8192], dtype: F16
  model.vision.blocks.16.attn.proj.weight => shape: [1152, 1152], dtype: F16
  model.vision.blocks.16.ln2.weight => shape: [1152], dtype: F16
  model.vision.blocks.9.ln1.weight => shape: [1152], dtype: F16
  model.vision.blocks.9.mlp.fc2.bias => shape: [1152], dtype: F16
  model.vision.blocks.0.mlp.fc1.weight => shape: [4304, 1152], dtype: F16
  model.vision.pos_emb => shape: [1, 729, 1152], dtype: F16
  model.vision.blocks.25.attn.proj.bias => shape: [1152], dtype: F16
  model.vision.blocks.7.ln1.weight => shape: [1152], dtype: F16
  model.text.blocks.2.mlp.fc1.weight => shape: [8192, 2048], dtype: F16
  model.vision.blocks.19.ln2.bias => shape: [1152], dtype: F16
  model.vision.blocks.18.mlp.fc2.bias => shape: [1152], dtype: F16
  model.vision.blocks.16.mlp.fc1.weight => shape: [4304, 1152], dtype: F16
  model.vision.blocks.19.attn.qkv.bias => shape: [3456], dtype: F16
  model.vision.blocks.2.attn.qkv.weight => shape: [3456, 1152], dtype: F16
  model.vision.blocks.21.ln2.weight => shape: [1152], dtype: F16
  model.vision.patch_emb.bias => shape: [1152], dtype: F16
  model.text.blocks.14.attn.qkv.bias => shape: [6144], dtype: F16
  model.text.blocks.8.mlp.fc2.weight => shape: [2048, 8192], dtype: F16
  model.vision.blocks.14.ln1.bias => shape: [1152], dtype: F16
  model.vision.blocks.12.mlp.fc1.bias => shape: [4304], dtype: F16
  model.text.blocks.0.mlp.fc2.bias => shape: [2048], dtype: F16
  model.vision.blocks.20.ln1.weight => shape: [1152], dtype: F16
  model.vision.blocks.24.attn.qkv.weight => shape: [3456, 1152], dtype: F16
  model.vision.blocks.10.attn.qkv.bias => shape: [3456], dtype: F16
  model.vision.blocks.23.attn.proj.weight => shape: [1152, 1152], dtype: F16
  model.vision.blocks.0.ln1.bias => shape: [1152], dtype: F16
  model.text.blocks.4.mlp.fc2.weight => shape: [2048, 8192], dtype: F16
  model.vision.blocks.14.attn.proj.weight => shape: [1152, 1152], dtype: F16
  model.vision.blocks.11.attn.proj.bias => shape: [1152], dtype: F16
  model.text.blocks.5.mlp.fc1.bias => shape: [8192], dtype: F16
  model.vision.blocks.7.attn.qkv.weight => shape: [3456, 1152], dtype: F16
  model.vision.blocks.7.ln2.bias => shape: [1152], dtype: F16
  model.text.blocks.15.attn.qkv.weight => shape: [6144, 2048], dtype: F16
  model.vision.blocks.19.mlp.fc1.bias => shape: [4304], dtype: F16
  model.text.blocks.11.attn.proj.bias => shape: [2048], dtype: F16
  model.vision.blocks.12.attn.qkv.weight => shape: [3456, 1152], dtype: F16
  model.vision.blocks.15.mlp.fc2.bias => shape: [1152], dtype: F16
  model.text.blocks.0.mlp.fc1.bias => shape: [8192], dtype: F16
  model.text.blocks.21.ln.weight => shape: [2048], dtype: F16
  model.text.blocks.6.attn.qkv.bias => shape: [6144], dtype: F16
  model.vision.blocks.25.mlp.fc1.weight => shape: [4304, 1152], dtype: F16
  model.vision.patch_emb.weight => shape: [1152, 588], dtype: F16
  model.vision.blocks.23.attn.qkv.weight => shape: [3456, 1152], dtype: F16
  model.vision.blocks.19.ln2.weight => shape: [1152], dtype: F16
  model.vision.blocks.25.ln1.bias => shape: [1152], dtype: F16
  model.text.blocks.9.attn.proj.weight => shape: [2048, 2048], dtype: F16
  model.text.blocks.15.attn.qkv.bias => shape: [6144], dtype: F16
  model.vision.blocks.4.mlp.fc2.bias => shape: [1152], dtype: F16
  model.text.blocks.5.mlp.fc1.weight => shape: [8192, 2048], dtype: F16
  model.vision.blocks.1.ln2.weight => shape: [1152], dtype: F16
  model.text.blocks.7.mlp.fc2.bias => shape: [2048], dtype: F16
  model.vision.blocks.24.attn.proj.bias => shape: [1152], dtype: F16
  model.vision.blocks.15.mlp.fc1.bias => shape: [4304], dtype: F16
  model.vision.blocks.2.mlp.fc2.weight => shape: [1152, 4304], dtype: F16
  model.text.lm_head.weight => shape: [51200, 2048], dtype: F16
  model.vision.blocks.2.ln2.bias => shape: [1152], dtype: F16
  model.vision.blocks.3.ln2.bias => shape: [1152], dtype: F16
  model.vision.blocks.2.ln1.bias => shape: [1152], dtype: F16
  model.text.blocks.10.mlp.fc2.bias => shape: [2048], dtype: F16
  model.vision.blocks.12.ln1.weight => shape: [1152], dtype: F16
  model.vision.blocks.26.mlp.fc1.bias => shape: [4304], dtype: F16
  model.vision.blocks.25.mlp.fc1.bias => shape: [4304], dtype: F16
  model.vision.blocks.8.attn.proj.weight => shape: [1152, 1152], dtype: F16
  model.text.blocks.23.attn.proj.weight => shape: [2048, 2048], dtype: F16
  model.text.blocks.12.mlp.fc1.weight => shape: [8192, 2048], dtype: F16
  model.vision.blocks.11.mlp.fc1.bias => shape: [4304], dtype: F16
  model.vision.blocks.25.ln1.weight => shape: [1152], dtype: F16
  model.vision.blocks.21.ln2.bias => shape: [1152], dtype: F16
  model.vision.blocks.4.attn.qkv.bias => shape: [3456], dtype: F16
  model.text.blocks.19.attn.proj.weight => shape: [2048, 2048], dtype: F16
  model.vision.blocks.8.mlp.fc2.weight => shape: [1152, 4304], dtype: F16
  model.vision.blocks.6.ln2.bias => shape: [1152], dtype: F16
  model.vision.blocks.21.mlp.fc1.weight => shape: [4304, 1152], dtype: F16
  model.vision.blocks.12.ln2.bias => shape: [1152], dtype: F16
  model.text.lm_head.bias => shape: [51200], dtype: F16
  model.text.blocks.18.ln.bias => shape: [2048], dtype: F16
  model.vision.blocks.16.mlp.fc2.bias => shape: [1152], dtype: F16
  model.vision.blocks.19.mlp.fc2.bias => shape: [1152], dtype: F16
  model.text.blocks.16.mlp.fc2.bias => shape: [2048], dtype: F16
  model.vision.blocks.9.ln1.bias => shape: [1152], dtype: F16
  model.vision.blocks.10.mlp.fc2.bias => shape: [1152], dtype: F16
  model.text.blocks.2.ln.bias => shape: [2048], dtype: F16
  model.vision.blocks.8.attn.proj.bias => shape: [1152], dtype: F16
  model.text.blocks.10.mlp.fc1.bias => shape: [8192], dtype: F16
  model.vision.blocks.1.ln1.weight => shape: [1152], dtype: F16
  model.text.blocks.23.ln.weight => shape: [2048], dtype: F16
  model.vision.blocks.13.attn.proj.weight => shape: [1152, 1152], dtype: F16
  model.text.blocks.2.attn.qkv.bias => shape: [6144], dtype: F16
  model.text.blocks.8.ln.weight => shape: [2048], dtype: F16
  model.vision.blocks.5.mlp.fc1.weight => shape: [4304, 1152], dtype: F16
  model.vision.blocks.9.attn.proj.weight => shape: [1152, 1152], dtype: F16
  model.vision.blocks.20.attn.proj.weight => shape: [1152, 1152], dtype: F16
  model.vision.blocks.9.attn.qkv.weight => shape: [3456, 1152], dtype: F16
  model.text.blocks.11.attn.qkv.weight => shape: [6144, 2048], dtype: F16
  model.vision.blocks.3.attn.proj.bias => shape: [1152], dtype: F16
  model.text.blocks.19.attn.qkv.weight => shape: [6144, 2048], dtype: F16
  model.vision.blocks.18.ln2.bias => shape: [1152], dtype: F16
  model.text.blocks.11.ln.bias => shape: [2048], dtype: F16
  model.vision.blocks.6.mlp.fc2.bias => shape: [1152], dtype: F16
  model.text.blocks.13.attn.proj.bias => shape: [2048], dtype: F16
  model.text.blocks.6.mlp.fc2.bias => shape: [2048], dtype: F16
  model.vision.blocks.26.mlp.fc1.weight => shape: [4304, 1152], dtype: F16
  model.vision.blocks.4.ln2.bias => shape: [1152], dtype: F16
  model.vision.blocks.18.attn.qkv.weight => shape: [3456, 1152], dtype: F16
  model.vision.blocks.5.mlp.fc2.bias => shape: [1152], dtype: F16
  model.vision.blocks.22.mlp.fc1.weight => shape: [4304, 1152], dtype: F16
  model.region.coord_decoder.fc2.weight => shape: [1024, 8192], dtype: F16
  model.vision.blocks.26.ln1.weight => shape: [1152], dtype: F16
  model.text.blocks.8.ln.bias => shape: [2048], dtype: F16
  model.vision.blocks.18.mlp.fc2.weight => shape: [1152, 4304], dtype: F16
  model.vision.blocks.20.attn.proj.bias => shape: [1152], dtype: F16
  model.vision.blocks.20.ln2.bias => shape: [1152], dtype: F16
  model.vision.blocks.26.attn.qkv.weight => shape: [3456, 1152], dtype: F16
  model.text.blocks.9.attn.qkv.weight => shape: [6144, 2048], dtype: F16
  model.vision.blocks.19.ln1.weight => shape: [1152], dtype: F16
  model.vision.blocks.23.mlp.fc2.bias => shape: [1152], dtype: F16
  model.vision.blocks.6.attn.proj.bias => shape: [1152], dtype: F16
  model.text.blocks.19.ln.weight => shape: [2048], dtype: F16
  model.text.blocks.18.attn.qkv.weight => shape: [6144, 2048], dtype: F16
  model.text.blocks.21.ln.bias => shape: [2048], dtype: F16
  model.vision.blocks.0.attn.proj.bias => shape: [1152], dtype: F16
  model.vision.blocks.25.ln2.weight => shape: [1152], dtype: F16
  model.region.coord_features => shape: [1, 128], dtype: F16
  model.vision.blocks.0.ln2.weight => shape: [1152], dtype: F16
  model.vision.blocks.3.ln1.weight => shape: [1152], dtype: F16
  model.text.blocks.13.attn.qkv.bias => shape: [6144], dtype: F16
  model.vision.blocks.23.ln2.weight => shape: [1152], dtype: F16
  model.text.blocks.18.mlp.fc2.bias => shape: [2048], dtype: F16
  model.text.blocks.7.attn.qkv.weight => shape: [6144, 2048], dtype: F16
  model.vision.blocks.13.mlp.fc2.bias => shape: [1152], dtype: F16
  model.vision.blocks.24.ln2.weight => shape: [1152], dtype: F16
  model.vision.blocks.4.attn.proj.weight => shape: [1152, 1152], dtype: F16
  model.text.blocks.13.mlp.fc1.bias => shape: [8192], dtype: F16
  model.text.blocks.14.ln.bias => shape: [2048], dtype: F16
  model.text.blocks.23.attn.qkv.bias => shape: [6144], dtype: F16
  model.text.blocks.18.ln.weight => shape: [2048], dtype: F16
  model.text.blocks.7.attn.proj.bias => shape: [2048], dtype: F16
  model.vision.blocks.10.ln1.weight => shape: [1152], dtype: F16
  model.text.blocks.11.mlp.fc1.weight => shape: [8192, 2048], dtype: F16
  model.vision.blocks.2.mlp.fc1.weight => shape: [4304, 1152], dtype: F16
  model.vision.blocks.25.mlp.fc2.weight => shape: [1152, 4304], dtype: F16
  model.text.blocks.5.attn.proj.bias => shape: [2048], dtype: F16
  model.vision.blocks.13.attn.proj.bias => shape: [1152], dtype: F16
  model.vision.blocks.4.ln1.bias => shape: [1152], dtype: F16
  model.vision.blocks.21.attn.proj.bias => shape: [1152], dtype: F16
  model.text.blocks.20.mlp.fc2.weight => shape: [2048, 8192], dtype: F16
  model.vision.blocks.20.mlp.fc2.weight => shape: [1152, 4304], dtype: F16
  model.text.blocks.17.mlp.fc2.bias => shape: [2048], dtype: F16
  model.vision.blocks.26.attn.proj.bias => shape: [1152], dtype: F16
  model.vision.blocks.15.ln2.bias => shape: [1152], dtype: F16
  model.vision.blocks.6.attn.proj.weight => shape: [1152, 1152], dtype: F16
  model.text.blocks.16.mlp.fc2.weight => shape: [2048, 8192], dtype: F16
  model.region.coord_decoder.fc1.weight => shape: [8192, 2048], dtype: F16
  model.vision.blocks.24.ln2.bias => shape: [1152], dtype: F16
  model.vision.blocks.17.attn.qkv.weight => shape: [3456, 1152], dtype: F16
  model.vision.blocks.7.attn.proj.bias => shape: [1152], dtype: F16
  model.vision.blocks.18.mlp.fc1.weight => shape: [4304, 1152], dtype: F16
  model.text.blocks.16.ln.weight => shape: [2048], dtype: F16
  model.vision.blocks.22.mlp.fc2.weight => shape: [1152, 4304], dtype: F16
  model.text.blocks.16.attn.proj.weight => shape: [2048, 2048], dtype: F16
  model.vision.blocks.1.attn.qkv.bias => shape: [3456], dtype: F16
  model.vision.blocks.6.mlp.fc2.weight => shape: [1152, 4304], dtype: F16
  model.vision.blocks.26.mlp.fc2.weight => shape: [1152, 4304], dtype: F16
  model.vision.blocks.21.ln1.weight => shape: [1152], dtype: F16
  model.text.blocks.15.ln.weight => shape: [2048], dtype: F16
  model.text.blocks.19.mlp.fc1.weight => shape: [8192, 2048], dtype: F16
  model.text.blocks.12.attn.proj.weight => shape: [2048, 2048], dtype: F16
  model.text.blocks.9.ln.weight => shape: [2048], dtype: F16
  model.vision.blocks.17.ln1.weight => shape: [1152], dtype: F16
  model.text.blocks.15.mlp.fc1.weight => shape: [8192, 2048], dtype: F16
  model.text.blocks.8.mlp.fc2.bias => shape: [2048], dtype: F16
  model.vision.blocks.2.attn.proj.weight => shape: [1152, 1152], dtype: F16
  model.text.blocks.1.attn.qkv.weight => shape: [6144, 2048], dtype: F16
  model.text.blocks.22.ln.weight => shape: [2048], dtype: F16
  model.vision.blocks.9.mlp.fc2.weight => shape: [1152, 4304], dtype: F16
  model.vision.blocks.11.mlp.fc1.weight => shape: [4304, 1152], dtype: F16
  model.vision.blocks.6.attn.qkv.weight => shape: [3456, 1152], dtype: F16
  model.vision.blocks.2.attn.qkv.bias => shape: [3456], dtype: F16
  model.vision.blocks.10.ln1.bias => shape: [1152], dtype: F16
  model.vision.blocks.12.mlp.fc1.weight => shape: [4304, 1152], dtype: F16
  model.text.blocks.20.ln.weight => shape: [2048], dtype: F16
  model.text.blocks.2.attn.qkv.weight => shape: [6144, 2048], dtype: F16
  model.text.blocks.1.ln.bias => shape: [2048], dtype: F16
  model.vision.blocks.22.ln2.weight => shape: [1152], dtype: F16
  model.text.blocks.15.mlp.fc2.weight => shape: [2048, 8192], dtype: F16
  model.text.blocks.21.attn.proj.weight => shape: [2048, 2048], dtype: F16
  model.text.blocks.0.mlp.fc1.weight => shape: [8192, 2048], dtype: F16
  model.vision.blocks.17.attn.qkv.bias => shape: [3456], dtype: F16
  model.text.blocks.7.ln.weight => shape: [2048], dtype: F16
  model.vision.blocks.19.attn.proj.weight => shape: [1152, 1152], dtype: F16
  model.vision.blocks.9.mlp.fc1.weight => shape: [4304, 1152], dtype: F16
  model.vision.blocks.0.attn.qkv.weight => shape: [3456, 1152], dtype: F16
  model.vision.blocks.16.ln1.bias => shape: [1152], dtype: F16
  model.text.blocks.10.mlp.fc1.weight => shape: [8192, 2048], dtype: F16
  model.vision.blocks.21.mlp.fc2.weight => shape: [1152, 4304], dtype: F16
  model.vision.blocks.4.ln1.weight => shape: [1152], dtype: F16
  model.vision.blocks.20.attn.qkv.bias => shape: [3456], dtype: F16
  model.vision.blocks.5.mlp.fc1.bias => shape: [4304], dtype: F16
  model.vision.blocks.2.mlp.fc1.bias => shape: [4304], dtype: F16
  model.text.blocks.9.attn.proj.bias => shape: [2048], dtype: F16
  model.region.size_features => shape: [2, 256], dtype: F16
  model.vision.blocks.9.attn.qkv.bias => shape: [3456], dtype: F16
  model.vision.blocks.1.attn.qkv.weight => shape: [3456, 1152], dtype: F16
  model.vision.blocks.21.attn.proj.weight => shape: [1152, 1152], dtype: F16
Error: cannot find tensor text_model.transformer.embd.wte.weight

Let me know if there's anything else I can try. Otherwise, I hope this helps whoever might be able to do this, like @LaurentMazare.

I used this code snippet:

        use safetensors::SafeTensors;

        let data = std::fs::read(&model_file)?;
        let tensors = SafeTensors::deserialize(&data)
            .map_err(|e| std::io::Error::new(std::io::ErrorKind::Other, e))?;

        println!("Tensors found in safetensors file:");
        for name in tensors.names() {
            let info = tensors.tensor(name).unwrap();
            println!(
                "  {} => shape: {:?}, dtype: {:?}",
                name,
                info.shape(),
                info.dtype()
            );
        }