[GH-ISSUE #13527] i face an issue #70969

New Issue

GiteaMirror · 2026-05-04T23:36:19-05:00

GiteaMirror commented

2026-05-04 23:36:19 -05:00

Originally created by @Gurka-065 on GitHub (Dec 19, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/13527

What is the issue?

the GGUF model loads correctly in Ollama: the qwen3vl architecture, all weights, and the vision projector are detected and initialized.

When you send the first chat/generate request, the llama.cpp runtime hits an internal assertion:

GGML_ASSERT((n_outputs_prev + n_outputs)*n_embd <= (int64_t) embd_size) failed

This means: the runtime is trying to write more embedding/output data than the buffer size it allocated, which indicates:

A bug or incompatibility in the current llama.cpp/Ollama build with the qwen3vl architecture (especially with your converted GGUF), or

A mismatch between how the GGUF was produced and what this llama.cpp version expects.

and i test all the llama.cpp and also the build one that for qwen3 vl and it still fail and i test the old and the new one and it still same thing i even test the one for qwen3 only and qwen2 but still dos not working but the qwen3 vl when pulling it from ollama site it dos work fine but not that one from llama.cpp even specific version and i also test ollama 0.12.6 ,0.12.7, 0.12.10, 0.13.4 , 5

Relevant log output

...
clip_model_loader: n_tensors: 352 clip_model_loader: n_kv: 28 clip_model_loader: has vision encoder clip_model_loader: tensor[0]: n_dims = 1, name = mm.0.bias, tensor_size=18432, offset=0, shape:[4608, 1, 1, 1], type = f32 clip_model_loader: tensor[1]: n_dims = 2, name = mm.0.weight, tensor_size=11943936, offset=18432, shape:[4608, 4608, 1, 1], type = q4_K clip_model_loader: tensor[2]: n_dims = 1, name = mm.2.bias, tensor_size=20480, offset=11962368, shape:[5120, 1, 1, 1], type = f32 clip_model_loader: tensor[3]: n_dims = 2, name = mm.2.weight, tensor_size=13271040, offset=11982848, shape:[4608, 5120, 1, 1], type = q4_K clip_model_loader: tensor[4]: n_dims = 1, name = v.blk.0.attn_out.bias, tensor_size=4608, offset=25253888, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[5]: n_dims = 2, name = v.blk.0.attn_out.weight, tensor_size=912384, offset=25258496, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[6]: n_dims = 1, name = v.blk.0.attn_qkv.bias, tensor_size=13824, offset=26170880, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[7]: n_dims = 2, name = v.blk.0.attn_qkv.weight, tensor_size=2985984, offset=26184704, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[8]: n_dims = 1, name = v.blk.0.ffn_down.bias, tensor_size=4608, offset=29170688, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[9]: n_dims = 2, name = v.blk.0.ffn_down.weight, tensor_size=9916416, offset=29175296, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[10]: n_dims = 1, name = v.blk.0.ffn_up.bias, tensor_size=17216, offset=39091712, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[11]: n_dims = 2, name = v.blk.0.ffn_up.weight, tensor_size=3408768, offset=39108928, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[12]: n_dims = 1, name = v.blk.0.ln1.bias, tensor_size=4608, offset=42517696, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[13]: n_dims = 1, name = v.blk.0.ln1.weight, tensor_size=4608, offset=42522304, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[14]: n_dims = 1, name = v.blk.0.ln2.bias, tensor_size=4608, offset=42526912, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[15]: n_dims = 1, name = v.blk.0.ln2.weight, tensor_size=4608, offset=42531520, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[16]: n_dims = 1, name = v.blk.1.attn_out.bias, tensor_size=4608, offset=42536128, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[17]: n_dims = 2, name = v.blk.1.attn_out.weight, tensor_size=912384, offset=42540736, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[18]: n_dims = 1, name = v.blk.1.attn_qkv.bias, tensor_size=13824, offset=43453120, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[19]: n_dims = 2, name = v.blk.1.attn_qkv.weight, tensor_size=2985984, offset=43466944, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[20]: n_dims = 1, name = v.blk.1.ffn_down.bias, tensor_size=4608, offset=46452928, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[21]: n_dims = 2, name = v.blk.1.ffn_down.weight, tensor_size=9916416, offset=46457536, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[22]: n_dims = 1, name = v.blk.1.ffn_up.bias, tensor_size=17216, offset=56373952, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[23]: n_dims = 2, name = v.blk.1.ffn_up.weight, tensor_size=3408768, offset=56391168, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[24]: n_dims = 1, name = v.blk.1.ln1.bias, tensor_size=4608, offset=59799936, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[25]: n_dims = 1, name = v.blk.1.ln1.weight, tensor_size=4608, offset=59804544, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[26]: n_dims = 1, name = v.blk.1.ln2.bias, tensor_size=4608, offset=59809152, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[27]: n_dims = 1, name = v.blk.1.ln2.weight, tensor_size=4608, offset=59813760, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[28]: n_dims = 1, name = v.blk.10.attn_out.bias, tensor_size=4608, offset=59818368, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[29]: n_dims = 2, name = v.blk.10.attn_out.weight, tensor_size=912384, offset=59822976, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[30]: n_dims = 1, name = v.blk.10.attn_qkv.bias, tensor_size=13824, offset=60735360, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[31]: n_dims = 2, name = v.blk.10.attn_qkv.weight, tensor_size=2985984, offset=60749184, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[32]: n_dims = 1, name = v.blk.10.ffn_down.bias, tensor_size=4608, offset=63735168, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[33]: n_dims = 2, name = v.blk.10.ffn_down.weight, tensor_size=9916416, offset=63739776, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[34]: n_dims = 1, name = v.blk.10.ffn_up.bias, tensor_size=17216, offset=73656192, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[35]: n_dims = 2, name = v.blk.10.ffn_up.weight, tensor_size=3408768, offset=73673408, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[36]: n_dims = 1, name = v.blk.10.ln1.bias, tensor_size=4608, offset=77082176, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[37]: n_dims = 1, name = v.blk.10.ln1.weight, tensor_size=4608, offset=77086784, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[38]: n_dims = 1, name = v.blk.10.ln2.bias, tensor_size=4608, offset=77091392, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[39]: n_dims = 1, name = v.blk.10.ln2.weight, tensor_size=4608, offset=77096000, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[40]: n_dims = 1, name = v.blk.11.attn_out.bias, tensor_size=4608, offset=77100608, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[41]: n_dims = 2, name = v.blk.11.attn_out.weight, tensor_size=912384, offset=77105216, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[42]: n_dims = 1, name = v.blk.11.attn_qkv.bias, tensor_size=13824, offset=78017600, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[43]: n_dims = 2, name = v.blk.11.attn_qkv.weight, tensor_size=2985984, offset=78031424, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[44]: n_dims = 1, name = v.blk.11.ffn_down.bias, tensor_size=4608, offset=81017408, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[45]: n_dims = 2, name = v.blk.11.ffn_down.weight, tensor_size=9916416, offset=81022016, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[46]: n_dims = 1, name = v.blk.11.ffn_up.bias, tensor_size=17216, offset=90938432, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[47]: n_dims = 2, name = v.blk.11.ffn_up.weight, tensor_size=3408768, offset=90955648, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[48]: n_dims = 1, name = v.blk.11.ln1.bias, tensor_size=4608, offset=94364416, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[49]: n_dims = 1, name = v.blk.11.ln1.weight, tensor_size=4608, offset=94369024, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[50]: n_dims = 1, name = v.blk.11.ln2.bias, tensor_size=4608, offset=94373632, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[51]: n_dims = 1, name = v.blk.11.ln2.weight, tensor_size=4608, offset=94378240, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[52]: n_dims = 1, name = v.blk.12.attn_out.bias, tensor_size=4608, offset=94382848, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[53]: n_dims = 2, name = v.blk.12.attn_out.weight, tensor_size=912384, offset=94387456, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[54]: n_dims = 1, name = v.blk.12.attn_qkv.bias, tensor_size=13824, offset=95299840, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[55]: n_dims = 2, name = v.blk.12.attn_qkv.weight, tensor_size=2985984, offset=95313664, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[56]: n_dims = 1, name = v.blk.12.ffn_down.bias, tensor_size=4608, offset=98299648, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[57]: n_dims = 2, name = v.blk.12.ffn_down.weight, tensor_size=9916416, offset=98304256, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[58]: n_dims = 1, name = v.blk.12.ffn_up.bias, tensor_size=17216, offset=108220672, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[59]: n_dims = 2, name = v.blk.12.ffn_up.weight, tensor_size=3408768, offset=108237888, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[60]: n_dims = 1, name = v.blk.12.ln1.bias, tensor_size=4608, offset=111646656, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[61]: n_dims = 1, name = v.blk.12.ln1.weight, tensor_size=4608, offset=111651264, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[62]: n_dims = 1, name = v.blk.12.ln2.bias, tensor_size=4608, offset=111655872, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[63]: n_dims = 1, name = v.blk.12.ln2.weight, tensor_size=4608, offset=111660480, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[64]: n_dims = 1, name = v.blk.13.attn_out.bias, tensor_size=4608, offset=111665088, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[65]: n_dims = 2, name = v.blk.13.attn_out.weight, tensor_size=912384, offset=111669696, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[66]: n_dims = 1, name = v.blk.13.attn_qkv.bias, tensor_size=13824, offset=112582080, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[67]: n_dims = 2, name = v.blk.13.attn_qkv.weight, tensor_size=2985984, offset=112595904, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[68]: n_dims = 1, name = v.blk.13.ffn_down.bias, tensor_size=4608, offset=115581888, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[69]: n_dims = 2, name = v.blk.13.ffn_down.weight, tensor_size=9916416, offset=115586496, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[70]: n_dims = 1, name = v.blk.13.ffn_up.bias, tensor_size=17216, offset=125502912, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[71]: n_dims = 2, name = v.blk.13.ffn_up.weight, tensor_size=3408768, offset=125520128, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[72]: n_dims = 1, name = v.blk.13.ln1.bias, tensor_size=4608, offset=128928896, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[73]: n_dims = 1, name = v.blk.13.ln1.weight, tensor_size=4608, offset=128933504, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[74]: n_dims = 1, name = v.blk.13.ln2.bias, tensor_size=4608, offset=128938112, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[75]: n_dims = 1, name = v.blk.13.ln2.weight, tensor_size=4608, offset=128942720, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[76]: n_dims = 1, name = v.blk.14.attn_out.bias, tensor_size=4608, offset=128947328, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[77]: n_dims = 2, name = v.blk.14.attn_out.weight, tensor_size=912384, offset=128951936, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[78]: n_dims = 1, name = v.blk.14.attn_qkv.bias, tensor_size=13824, offset=129864320, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[79]: n_dims = 2, name = v.blk.14.attn_qkv.weight, tensor_size=2985984, offset=129878144, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[80]: n_dims = 1, name = v.blk.14.ffn_down.bias, tensor_size=4608, offset=132864128, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[81]: n_dims = 2, name = v.blk.14.ffn_down.weight, tensor_size=9916416, offset=132868736, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[82]: n_dims = 1, name = v.blk.14.ffn_up.bias, tensor_size=17216, offset=142785152, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[83]: n_dims = 2, name = v.blk.14.ffn_up.weight, tensor_size=3408768, offset=142802368, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[84]: n_dims = 1, name = v.blk.14.ln1.bias, tensor_size=4608, offset=146211136, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[85]: n_dims = 1, name = v.blk.14.ln1.weight, tensor_size=4608, offset=146215744, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[86]: n_dims = 1, name = v.blk.14.ln2.bias, tensor_size=4608, offset=146220352, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[87]: n_dims = 1, name = v.blk.14.ln2.weight, tensor_size=4608, offset=146224960, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[88]: n_dims = 1, name = v.blk.15.attn_out.bias, tensor_size=4608, offset=146229568, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[89]: n_dims = 2, name = v.blk.15.attn_out.weight, tensor_size=912384, offset=146234176, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[90]: n_dims = 1, name = v.blk.15.attn_qkv.bias, tensor_size=13824, offset=147146560, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[91]: n_dims = 2, name = v.blk.15.attn_qkv.weight, tensor_size=2985984, offset=147160384, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[92]: n_dims = 1, name = v.blk.15.ffn_down.bias, tensor_size=4608, offset=150146368, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[93]: n_dims = 2, name = v.blk.15.ffn_down.weight, tensor_size=9916416, offset=150150976, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[94]: n_dims = 1, name = v.blk.15.ffn_up.bias, tensor_size=17216, offset=160067392, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[95]: n_dims = 2, name = v.blk.15.ffn_up.weight, tensor_size=3408768, offset=160084608, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[96]: n_dims = 1, name = v.blk.15.ln1.bias, tensor_size=4608, offset=163493376, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[97]: n_dims = 1, name = v.blk.15.ln1.weight, tensor_size=4608, offset=163497984, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[98]: n_dims = 1, name = v.blk.15.ln2.bias, tensor_size=4608, offset=163502592, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[99]: n_dims = 1, name = v.blk.15.ln2.weight, tensor_size=4608, offset=163507200, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[100]: n_dims = 1, name = v.blk.16.attn_out.bias, tensor_size=4608, offset=163511808, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[101]: n_dims = 2, name = v.blk.16.attn_out.weight, tensor_size=912384, offset=163516416, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[102]: n_dims = 1, name = v.blk.16.attn_qkv.bias, tensor_size=13824, offset=164428800, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[103]: n_dims = 2, name = v.blk.16.attn_qkv.weight, tensor_size=2985984, offset=164442624, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[104]: n_dims = 1, name = v.blk.16.ffn_down.bias, tensor_size=4608, offset=167428608, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[105]: n_dims = 2, name = v.blk.16.ffn_down.weight, tensor_size=9916416, offset=167433216, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[106]: n_dims = 1, name = v.blk.16.ffn_up.bias, tensor_size=17216, offset=177349632, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[107]: n_dims = 2, name = v.blk.16.ffn_up.weight, tensor_size=3408768, offset=177366848, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[108]: n_dims = 1, name = v.blk.16.ln1.bias, tensor_size=4608, offset=180775616, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[109]: n_dims = 1, name = v.blk.16.ln1.weight, tensor_size=4608, offset=180780224, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[110]: n_dims = 1, name = v.blk.16.ln2.bias, tensor_size=4608, offset=180784832, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[111]: n_dims = 1, name = v.blk.16.ln2.weight, tensor_size=4608, offset=180789440, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[112]: n_dims = 1, name = v.blk.17.attn_out.bias, tensor_size=4608, offset=180794048, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[113]: n_dims = 2, name = v.blk.17.attn_out.weight, tensor_size=912384, offset=180798656, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[114]: n_dims = 1, name = v.blk.17.attn_qkv.bias, tensor_size=13824, offset=181711040, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[115]: n_dims = 2, name = v.blk.17.attn_qkv.weight, tensor_size=2985984, offset=181724864, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[116]: n_dims = 1, name = v.blk.17.ffn_down.bias, tensor_size=4608, offset=184710848, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[117]: n_dims = 2, name = v.blk.17.ffn_down.weight, tensor_size=9916416, offset=184715456, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[118]: n_dims = 1, name = v.blk.17.ffn_up.bias, tensor_size=17216, offset=194631872, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[119]: n_dims = 2, name = v.blk.17.ffn_up.weight, tensor_size=3408768, offset=194649088, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[120]: n_dims = 1, name = v.blk.17.ln1.bias, tensor_size=4608, offset=198057856, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[121]: n_dims = 1, name = v.blk.17.ln1.weight, tensor_size=4608, offset=198062464, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[122]: n_dims = 1, name = v.blk.17.ln2.bias, tensor_size=4608, offset=198067072, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[123]: n_dims = 1, name = v.blk.17.ln2.weight, tensor_size=4608, offset=198071680, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[124]: n_dims = 1, name = v.blk.18.attn_out.bias, tensor_size=4608, offset=198076288, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[125]: n_dims = 2, name = v.blk.18.attn_out.weight, tensor_size=912384, offset=198080896, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[126]: n_dims = 1, name = v.blk.18.attn_qkv.bias, tensor_size=13824, offset=198993280, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[127]: n_dims = 2, name = v.blk.18.attn_qkv.weight, tensor_size=2985984, offset=199007104, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[128]: n_dims = 1, name = v.blk.18.ffn_down.bias, tensor_size=4608, offset=201993088, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[129]: n_dims = 2, name = v.blk.18.ffn_down.weight, tensor_size=9916416, offset=201997696, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[130]: n_dims = 1, name = v.blk.18.ffn_up.bias, tensor_size=17216, offset=211914112, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[131]: n_dims = 2, name = v.blk.18.ffn_up.weight, tensor_size=3408768, offset=211931328, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[132]: n_dims = 1, name = v.blk.18.ln1.bias, tensor_size=4608, offset=215340096, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[133]: n_dims = 1, name = v.blk.18.ln1.weight, tensor_size=4608, offset=215344704, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[134]: n_dims = 1, name = v.blk.18.ln2.bias, tensor_size=4608, offset=215349312, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[135]: n_dims = 1, name = v.blk.18.ln2.weight, tensor_size=4608, offset=215353920, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[136]: n_dims = 1, name = v.blk.19.attn_out.bias, tensor_size=4608, offset=215358528, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[137]: n_dims = 2, name = v.blk.19.attn_out.weight, tensor_size=912384, offset=215363136, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[138]: n_dims = 1, name = v.blk.19.attn_qkv.bias, tensor_size=13824, offset=216275520, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[139]: n_dims = 2, name = v.blk.19.attn_qkv.weight, tensor_size=2985984, offset=216289344, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[140]: n_dims = 1, name = v.blk.19.ffn_down.bias, tensor_size=4608, offset=219275328, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[141]: n_dims = 2, name = v.blk.19.ffn_down.weight, tensor_size=9916416, offset=219279936, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[142]: n_dims = 1, name = v.blk.19.ffn_up.bias, tensor_size=17216, offset=229196352, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[143]: n_dims = 2, name = v.blk.19.ffn_up.weight, tensor_size=3408768, offset=229213568, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[144]: n_dims = 1, name = v.blk.19.ln1.bias, tensor_size=4608, offset=232622336, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[145]: n_dims = 1, name = v.blk.19.ln1.weight, tensor_size=4608, offset=232626944, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[146]: n_dims = 1, name = v.blk.19.ln2.bias, tensor_size=4608, offset=232631552, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[147]: n_dims = 1, name = v.blk.19.ln2.weight, tensor_size=4608, offset=232636160, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[148]: n_dims = 1, name = v.blk.2.attn_out.bias, tensor_size=4608, offset=232640768, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[149]: n_dims = 2, name = v.blk.2.attn_out.weight, tensor_size=912384, offset=232645376, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[150]: n_dims = 1, name = v.blk.2.attn_qkv.bias, tensor_size=13824, offset=233557760, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[151]: n_dims = 2, name = v.blk.2.attn_qkv.weight, tensor_size=2985984, offset=233571584, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[152]: n_dims = 1, name = v.blk.2.ffn_down.bias, tensor_size=4608, offset=236557568, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[153]: n_dims = 2, name = v.blk.2.ffn_down.weight, tensor_size=9916416, offset=236562176, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[154]: n_dims = 1, name = v.blk.2.ffn_up.bias, tensor_size=17216, offset=246478592, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[155]: n_dims = 2, name = v.blk.2.ffn_up.weight, tensor_size=3408768, offset=246495808, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[156]: n_dims = 1, name = v.blk.2.ln1.bias, tensor_size=4608, offset=249904576, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[157]: n_dims = 1, name = v.blk.2.ln1.weight, tensor_size=4608, offset=249909184, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[158]: n_dims = 1, name = v.blk.2.ln2.bias, tensor_size=4608, offset=249913792, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[159]: n_dims = 1, name = v.blk.2.ln2.weight, tensor_size=4608, offset=249918400, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[160]: n_dims = 1, name = v.blk.20.attn_out.bias, tensor_size=4608, offset=249923008, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[161]: n_dims = 2, name = v.blk.20.attn_out.weight, tensor_size=912384, offset=249927616, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[162]: n_dims = 1, name = v.blk.20.attn_qkv.bias, tensor_size=13824, offset=250840000, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[163]: n_dims = 2, name = v.blk.20.attn_qkv.weight, tensor_size=2985984, offset=250853824, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[164]: n_dims = 1, name = v.blk.20.ffn_down.bias, tensor_size=4608, offset=253839808, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[165]: n_dims = 2, name = v.blk.20.ffn_down.weight, tensor_size=9916416, offset=253844416, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[166]: n_dims = 1, name = v.blk.20.ffn_up.bias, tensor_size=17216, offset=263760832, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[167]: n_dims = 2, name = v.blk.20.ffn_up.weight, tensor_size=3408768, offset=263778048, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[168]: n_dims = 1, name = v.blk.20.ln1.bias, tensor_size=4608, offset=267186816, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[169]: n_dims = 1, name = v.blk.20.ln1.weight, tensor_size=4608, offset=267191424, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[170]: n_dims = 1, name = v.blk.20.ln2.bias, tensor_size=4608, offset=267196032, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[171]: n_dims = 1, name = v.blk.20.ln2.weight, tensor_size=4608, offset=267200640, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[172]: n_dims = 1, name = v.blk.21.attn_out.bias, tensor_size=4608, offset=267205248, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[173]: n_dims = 2, name = v.blk.21.attn_out.weight, tensor_size=912384, offset=267209856, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[174]: n_dims = 1, name = v.blk.21.attn_qkv.bias, tensor_size=13824, offset=268122240, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[175]: n_dims = 2, name = v.blk.21.attn_qkv.weight, tensor_size=2985984, offset=268136064, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[176]: n_dims = 1, name = v.blk.21.ffn_down.bias, tensor_size=4608, offset=271122048, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[177]: n_dims = 2, name = v.blk.21.ffn_down.weight, tensor_size=9916416, offset=271126656, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[178]: n_dims = 1, name = v.blk.21.ffn_up.bias, tensor_size=17216, offset=281043072, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[179]: n_dims = 2, name = v.blk.21.ffn_up.weight, tensor_size=3408768, offset=281060288, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[180]: n_dims = 1, name = v.blk.21.ln1.bias, tensor_size=4608, offset=284469056, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[181]: n_dims = 1, name = v.blk.21.ln1.weight, tensor_size=4608, offset=284473664, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[182]: n_dims = 1, name = v.blk.21.ln2.bias, tensor_size=4608, offset=284478272, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[183]: n_dims = 1, name = v.blk.21.ln2.weight, tensor_size=4608, offset=284482880, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[184]: n_dims = 1, name = v.blk.22.attn_out.bias, tensor_size=4608, offset=284487488, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[185]: n_dims = 2, name = v.blk.22.attn_out.weight, tensor_size=912384, offset=284492096, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[186]: n_dims = 1, name = v.blk.22.attn_qkv.bias, tensor_size=13824, offset=285404480, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[187]: n_dims = 2, name = v.blk.22.attn_qkv.weight, tensor_size=2985984, offset=285418304, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[188]: n_dims = 1, name = v.blk.22.ffn_down.bias, tensor_size=4608, offset=288404288, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[189]: n_dims = 2, name = v.blk.22.ffn_down.weight, tensor_size=9916416, offset=288408896, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[190]: n_dims = 1, name = v.blk.22.ffn_up.bias, tensor_size=17216, offset=298325312, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[191]: n_dims = 2, name = v.blk.22.ffn_up.weight, tensor_size=3408768, offset=298342528, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[192]: n_dims = 1, name = v.blk.22.ln1.bias, tensor_size=4608, offset=301751296, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[193]: n_dims = 1, name = v.blk.22.ln1.weight, tensor_size=4608, offset=301755904, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[194]: n_dims = 1, name = v.blk.22.ln2.bias, tensor_size=4608, offset=301760512, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[195]: n_dims = 1, name = v.blk.22.ln2.weight, tensor_size=4608, offset=301765120, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[196]: n_dims = 1, name = v.blk.23.attn_out.bias, tensor_size=4608, offset=301769728, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[197]: n_dims = 2, name = v.blk.23.attn_out.weight, tensor_size=912384, offset=301774336, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[198]: n_dims = 1, name = v.blk.23.attn_qkv.bias, tensor_size=13824, offset=302686720, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[199]: n_dims = 2, name = v.blk.23.attn_qkv.weight, tensor_size=2985984, offset=302700544, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[200]: n_dims = 1, name = v.blk.23.ffn_down.bias, tensor_size=4608, offset=305686528, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[201]: n_dims = 2, name = v.blk.23.ffn_down.weight, tensor_size=9916416, offset=305691136, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[202]: n_dims = 1, name = v.blk.23.ffn_up.bias, tensor_size=17216, offset=315607552, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[203]: n_dims = 2, name = v.blk.23.ffn_up.weight, tensor_size=3408768, offset=315624768, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[204]: n_dims = 1, name = v.blk.23.ln1.bias, tensor_size=4608, offset=319033536, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[205]: n_dims = 1, name = v.blk.23.ln1.weight, tensor_size=4608, offset=319038144, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[206]: n_dims = 1, name = v.blk.23.ln2.bias, tensor_size=4608, offset=319042752, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[207]: n_dims = 1, name = v.blk.23.ln2.weight, tensor_size=4608, offset=319047360, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[208]: n_dims = 1, name = v.blk.24.attn_out.bias, tensor_size=4608, offset=319051968, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[209]: n_dims = 2, name = v.blk.24.attn_out.weight, tensor_size=912384, offset=319056576, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[210]: n_dims = 1, name = v.blk.24.attn_qkv.bias, tensor_size=13824, offset=319968960, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[211]: n_dims = 2, name = v.blk.24.attn_qkv.weight, tensor_size=2985984, offset=319982784, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[212]: n_dims = 1, name = v.blk.24.ffn_down.bias, tensor_size=4608, offset=322968768, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[213]: n_dims = 2, name = v.blk.24.ffn_down.weight, tensor_size=9916416, offset=322973376, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[214]: n_dims = 1, name = v.blk.24.ffn_up.bias, tensor_size=17216, offset=332889792, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[215]: n_dims = 2, name = v.blk.24.ffn_up.weight, tensor_size=3408768, offset=332907008, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[216]: n_dims = 1, name = v.blk.24.ln1.bias, tensor_size=4608, offset=336315776, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[217]: n_dims = 1, name = v.blk.24.ln1.weight, tensor_size=4608, offset=336320384, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[218]: n_dims = 1, name = v.blk.24.ln2.bias, tensor_size=4608, offset=336324992, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[219]: n_dims = 1, name = v.blk.24.ln2.weight, tensor_size=4608, offset=336329600, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[220]: n_dims = 1, name = v.blk.25.attn_out.bias, tensor_size=4608, offset=336334208, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[221]: n_dims = 2, name = v.blk.25.attn_out.weight, tensor_size=912384, offset=336338816, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[222]: n_dims = 1, name = v.blk.25.attn_qkv.bias, tensor_size=13824, offset=337251200, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[223]: n_dims = 2, name = v.blk.25.attn_qkv.weight, tensor_size=2985984, offset=337265024, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[224]: n_dims = 1, name = v.blk.25.ffn_down.bias, tensor_size=4608, offset=340251008, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[225]: n_dims = 2, name = v.blk.25.ffn_down.weight, tensor_size=9916416, offset=340255616, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[226]: n_dims = 1, name = v.blk.25.ffn_up.bias, tensor_size=17216, offset=350172032, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[227]: n_dims = 2, name = v.blk.25.ffn_up.weight, tensor_size=3408768, offset=350189248, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[228]: n_dims = 1, name = v.blk.25.ln1.bias, tensor_size=4608, offset=353598016, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[229]: n_dims = 1, name = v.blk.25.ln1.weight, tensor_size=4608, offset=353602624, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[230]: n_dims = 1, name = v.blk.25.ln2.bias, tensor_size=4608, offset=353607232, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[231]: n_dims = 1, name = v.blk.25.ln2.weight, tensor_size=4608, offset=353611840, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[232]: n_dims = 1, name = v.blk.26.attn_out.bias, tensor_size=4608, offset=353616448, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[233]: n_dims = 2, name = v.blk.26.attn_out.weight, tensor_size=912384, offset=353621056, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[234]: n_dims = 1, name = v.blk.26.attn_qkv.bias, tensor_size=13824, offset=354533440, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[235]: n_dims = 2, name = v.blk.26.attn_qkv.weight, tensor_size=2985984, offset=354547264, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[236]: n_dims = 1, name = v.blk.26.ffn_down.bias, tensor_size=4608, offset=357533248, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[237]: n_dims = 2, name = v.blk.26.ffn_down.weight, tensor_size=9916416, offset=357537856, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[238]: n_dims = 1, name = v.blk.26.ffn_up.bias, tensor_size=17216, offset=367454272, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[239]: n_dims = 2, name = v.blk.26.ffn_up.weight, tensor_size=3408768, offset=367471488, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[240]: n_dims = 1, name = v.blk.26.ln1.bias, tensor_size=4608, offset=370880256, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[241]: n_dims = 1, name = v.blk.26.ln1.weight, tensor_size=4608, offset=370884864, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[242]: n_dims = 1, name = v.blk.26.ln2.bias, tensor_size=4608, offset=370889472, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[243]: n_dims = 1, name = v.blk.26.ln2.weight, tensor_size=4608, offset=370894080, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[244]: n_dims = 1, name = v.blk.3.attn_out.bias, tensor_size=4608, offset=370898688, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[245]: n_dims = 2, name = v.blk.3.attn_out.weight, tensor_size=912384, offset=370903296, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[246]: n_dims = 1, name = v.blk.3.attn_qkv.bias, tensor_size=13824, offset=371815680, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[247]: n_dims = 2, name = v.blk.3.attn_qkv.weight, tensor_size=2985984, offset=371829504, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[248]: n_dims = 1, name = v.blk.3.ffn_down.bias, tensor_size=4608, offset=374815488, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[249]: n_dims = 2, name = v.blk.3.ffn_down.weight, tensor_size=9916416, offset=374820096, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[250]: n_dims = 1, name = v.blk.3.ffn_up.bias, tensor_size=17216, offset=384736512, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[251]: n_dims = 2, name = v.blk.3.ffn_up.weight, tensor_size=3408768, offset=384753728, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[252]: n_dims = 1, name = v.blk.3.ln1.bias, tensor_size=4608, offset=388162496, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[253]: n_dims = 1, name = v.blk.3.ln1.weight, tensor_size=4608, offset=388167104, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[254]: n_dims = 1, name = v.blk.3.ln2.bias, tensor_size=4608, offset=388171712, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[255]: n_dims = 1, name = v.blk.3.ln2.weight, tensor_size=4608, offset=388176320, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[256]: n_dims = 1, name = v.blk.4.attn_out.bias, tensor_size=4608, offset=388180928, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[257]: n_dims = 2, name = v.blk.4.attn_out.weight, tensor_size=912384, offset=388185536, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[258]: n_dims = 1, name = v.blk.4.attn_qkv.bias, tensor_size=13824, offset=389097920, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[259]: n_dims = 2, name = v.blk.4.attn_qkv.weight, tensor_size=2985984, offset=389111744, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[260]: n_dims = 1, name = v.blk.4.ffn_down.bias, tensor_size=4608, offset=392097728, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[261]: n_dims = 2, name = v.blk.4.ffn_down.weight, tensor_size=9916416, offset=392102336, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[262]: n_dims = 1, name = v.blk.4.ffn_up.bias, tensor_size=17216, offset=402018752, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[263]: n_dims = 2, name = v.blk.4.ffn_up.weight, tensor_size=3408768, offset=402035968, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[264]: n_dims = 1, name = v.blk.4.ln1.bias, tensor_size=4608, offset=405444736, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[265]: n_dims = 1, name = v.blk.4.ln1.weight, tensor_size=4608, offset=405449344, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[266]: n_dims = 1, name = v.blk.4.ln2.bias, tensor_size=4608, offset=405453952, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[267]: n_dims = 1, name = v.blk.4.ln2.weight, tensor_size=4608, offset=405458560, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[268]: n_dims = 1, name = v.blk.5.attn_out.bias, tensor_size=4608, offset=405463168, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[269]: n_dims = 2, name = v.blk.5.attn_out.weight, tensor_size=912384, offset=405467776, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[270]: n_dims = 1, name = v.blk.5.attn_qkv.bias, tensor_size=13824, offset=406380160, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[271]: n_dims = 2, name = v.blk.5.attn_qkv.weight, tensor_size=2985984, offset=406393984, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[272]: n_dims = 1, name = v.blk.5.ffn_down.bias, tensor_size=4608, offset=409379968, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[273]: n_dims = 2, name = v.blk.5.ffn_down.weight, tensor_size=9916416, offset=409384576, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[274]: n_dims = 1, name = v.blk.5.ffn_up.bias, tensor_size=17216, offset=419300992, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[275]: n_dims = 2, name = v.blk.5.ffn_up.weight, tensor_size=3408768, offset=419318208, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[276]: n_dims = 1, name = v.blk.5.ln1.bias, tensor_size=4608, offset=422726976, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[277]: n_dims = 1, name = v.blk.5.ln1.weight, tensor_size=4608, offset=422731584, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[278]: n_dims = 1, name = v.blk.5.ln2.bias, tensor_size=4608, offset=422736192, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[279]: n_dims = 1, name = v.blk.5.ln2.weight, tensor_size=4608, offset=422740800, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[280]: n_dims = 1, name = v.blk.6.attn_out.bias, tensor_size=4608, offset=422745408, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[281]: n_dims = 2, name = v.blk.6.attn_out.weight, tensor_size=912384, offset=422750016, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[282]: n_dims = 1, name = v.blk.6.attn_qkv.bias, tensor_size=13824, offset=423662400, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[283]: n_dims = 2, name = v.blk.6.attn_qkv.weight, tensor_size=2985984, offset=423676224, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[284]: n_dims = 1, name = v.blk.6.ffn_down.bias, tensor_size=4608, offset=426662208, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[285]: n_dims = 2, name = v.blk.6.ffn_down.weight, tensor_size=9916416, offset=426666816, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[286]: n_dims = 1, name = v.blk.6.ffn_up.bias, tensor_size=17216, offset=436583232, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[287]: n_dims = 2, name = v.blk.6.ffn_up.weight, tensor_size=3408768, offset=436600448, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[288]: n_dims = 1, name = v.blk.6.ln1.bias, tensor_size=4608, offset=440009216, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[289]: n_dims = 1, name = v.blk.6.ln1.weight, tensor_size=4608, offset=440013824, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[290]: n_dims = 1, name = v.blk.6.ln2.bias, tensor_size=4608, offset=440018432, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[291]: n_dims = 1, name = v.blk.6.ln2.weight, tensor_size=4608, offset=440023040, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[292]: n_dims = 1, name = v.blk.7.attn_out.bias, tensor_size=4608, offset=440027648, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[293]: n_dims = 2, name = v.blk.7.attn_out.weight, tensor_size=912384, offset=440032256, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[294]: n_dims = 1, name = v.blk.7.attn_qkv.bias, tensor_size=13824, offset=440944640, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[295]: n_dims = 2, name = v.blk.7.attn_qkv.weight, tensor_size=2985984, offset=440958464, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[296]: n_dims = 1, name = v.blk.7.ffn_down.bias, tensor_size=4608, offset=443944448, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[297]: n_dims = 2, name = v.blk.7.ffn_down.weight, tensor_size=9916416, offset=443949056, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[298]: n_dims = 1, name = v.blk.7.ffn_up.bias, tensor_size=17216, offset=453865472, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[299]: n_dims = 2, name = v.blk.7.ffn_up.weight, tensor_size=3408768, offset=453882688, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[300]: n_dims = 1, name = v.blk.7.ln1.bias, tensor_size=4608, offset=457291456, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[301]: n_dims = 1, name = v.blk.7.ln1.weight, tensor_size=4608, offset=457296064, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[302]: n_dims = 1, name = v.blk.7.ln2.bias, tensor_size=4608, offset=457300672, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[303]: n_dims = 1, name = v.blk.7.ln2.weight, tensor_size=4608, offset=457305280, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[304]: n_dims = 1, name = v.blk.8.attn_out.bias, tensor_size=4608, offset=457309888, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[305]: n_dims = 2, name = v.blk.8.attn_out.weight, tensor_size=912384, offset=457314496, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[306]: n_dims = 1, name = v.blk.8.attn_qkv.bias, tensor_size=13824, offset=458226880, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[307]: n_dims = 2, name = v.blk.8.attn_qkv.weight, tensor_size=2985984, offset=458240704, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[308]: n_dims = 1, name = v.blk.8.ffn_down.bias, tensor_size=4608, offset=461226688, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[309]: n_dims = 2, name = v.blk.8.ffn_down.weight, tensor_size=9916416, offset=461231296, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[310]: n_dims = 1, name = v.blk.8.ffn_up.bias, tensor_size=17216, offset=471147712, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[311]: n_dims = 2, name = v.blk.8.ffn_up.weight, tensor_size=3408768, offset=471164928, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[312]: n_dims = 1, name = v.blk.8.ln1.bias, tensor_size=4608, offset=474573696, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[313]: n_dims = 1, name = v.blk.8.ln1.weight, tensor_size=4608, offset=474578304, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[314]: n_dims = 1, name = v.blk.8.ln2.bias, tensor_size=4608, offset=474582912, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[315]: n_dims = 1, name = v.blk.8.ln2.weight, tensor_size=4608, offset=474587520, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[316]: n_dims = 1, name = v.blk.9.attn_out.bias, tensor_size=4608, offset=474592128, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[317]: n_dims = 2, name = v.blk.9.attn_out.weight, tensor_size=912384, offset=474596736, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[318]: n_dims = 1, name = v.blk.9.attn_qkv.bias, tensor_size=13824, offset=475509120, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[319]: n_dims = 2, name = v.blk.9.attn_qkv.weight, tensor_size=2985984, offset=475522944, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[320]: n_dims = 1, name = v.blk.9.ffn_down.bias, tensor_size=4608, offset=478508928, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[321]: n_dims = 2, name = v.blk.9.ffn_down.weight, tensor_size=9916416, offset=478513536, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[322]: n_dims = 1, name = v.blk.9.ffn_up.bias, tensor_size=17216, offset=488429952, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[323]: n_dims = 2, name = v.blk.9.ffn_up.weight, tensor_size=3408768, offset=488447168, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[324]: n_dims = 1, name = v.blk.9.ln1.bias, tensor_size=4608, offset=491855936, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[325]: n_dims = 1, name = v.blk.9.ln1.weight, tensor_size=4608, offset=491860544, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[326]: n_dims = 1, name = v.blk.9.ln2.bias, tensor_size=4608, offset=491865152, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[327]: n_dims = 1, name = v.blk.9.ln2.weight, tensor_size=4608, offset=491869760, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[328]: n_dims = 1, name = v.deepstack.16.fc1.bias, tensor_size=18432, offset=491874368, shape:[4608, 1, 1, 1], type = f32 clip_model_loader: tensor[329]: n_dims = 2, name = v.deepstack.16.fc1.weight, tensor_size=11943936, offset=491892800, shape:[4608, 4608, 1, 1], type = q4_K clip_model_loader: tensor[330]: n_dims = 1, name = v.deepstack.16.fc2.bias, tensor_size=20480, offset=503836736, shape:[5120, 1, 1, 1], type = f32 clip_model_loader: tensor[331]: n_dims = 2, name = v.deepstack.16.fc2.weight, tensor_size=13271040, offset=503857216, shape:[4608, 5120, 1, 1], type = q4_K clip_model_loader: tensor[332]: n_dims = 1, name = v.deepstack.16.norm.bias, tensor_size=18432, offset=517128256, shape:[4608, 1, 1, 1], type = f32 clip_model_loader: tensor[333]: n_dims = 1, name = v.deepstack.16.norm.weight, tensor_size=18432, offset=517146688, shape:[4608, 1, 1, 1], type = f32 clip_model_loader: tensor[334]: n_dims = 1, name = v.deepstack.24.fc1.bias, tensor_size=18432, offset=517165120, shape:[4608, 1, 1, 1], type = f32 clip_model_loader: tensor[335]: n_dims = 2, name = v.deepstack.24.fc1.weight, tensor_size=11943936, offset=517183552, shape:[4608, 4608, 1, 1], type = q4_K clip_model_loader: tensor[336]: n_dims = 1, name = v.deepstack.24.fc2.bias, tensor_size=20480, offset=529127488, shape:[5120, 1, 1, 1], type = f32 clip_model_loader: tensor[337]: n_dims = 2, name = v.deepstack.24.fc2.weight, tensor_size=13271040, offset=529147968, shape:[4608, 5120, 1, 1], type = q4_K clip_model_loader: tensor[338]: n_dims = 1, name = v.deepstack.24.norm.bias, tensor_size=18432, offset=542419008, shape:[4608, 1, 1, 1], type = f32 clip_model_loader: tensor[339]: n_dims = 1, name = v.deepstack.24.norm.weight, tensor_size=18432, offset=542437440, shape:[4608, 1, 1, 1], type = f32 clip_model_loader: tensor[340]: n_dims = 1, name = v.deepstack.8.fc1.bias, tensor_size=18432, offset=542455872, shape:[4608, 1, 1, 1], type = f32 clip_model_loader: tensor[341]: n_dims = 2, name = v.deepstack.8.fc1.weight, tensor_size=11943936, offset=542474304, shape:[4608, 4608, 1, 1], type = q4_K clip_model_loader: tensor[342]: n_dims = 1, name = v.deepstack.8.fc2.bias, tensor_size=20480, offset=554418240, shape:[5120, 1, 1, 1], type = f32 clip_model_loader: tensor[343]: n_dims = 2, name = v.deepstack.8.fc2.weight, tensor_size=13271040, offset=554438720, shape:[4608, 5120, 1, 1], type = q4_K clip_model_loader: tensor[344]: n_dims = 1, name = v.deepstack.8.norm.bias, tensor_size=18432, offset=567709760, shape:[4608, 1, 1, 1], type = f32 clip_model_loader: tensor[345]: n_dims = 1, name = v.deepstack.8.norm.weight, tensor_size=18432, offset=567728192, shape:[4608, 1, 1, 1], type = f32 clip_model_loader: tensor[346]: n_dims = 1, name = v.patch_embd.bias, tensor_size=4608, offset=567746624, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[347]: n_dims = 4, name = v.patch_embd.weight, tensor_size=1769472, offset=567751232, shape:[16, 16, 3, 1152], type = f16 clip_model_loader: tensor[348]: n_dims = 4, name = v.patch_embd.weight.1, tensor_size=1769472, offset=569520704, shape:[16, 16, 3, 1152], type = f16 clip_model_loader: tensor[349]: n_dims = 2, name = v.position_embd.weight, tensor_size=10616832, offset=571290176, shape:[1152, 2304, 1, 1], type = f32 clip_model_loader: tensor[350]: n_dims = 1, name = v.post_ln.bias, tensor_size=4608, offset=581907008, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[351]: n_dims = 1, name = v.post_ln.weight, tensor_size=4608, offset=581911616, shape:[1152, 1, 1, 1], type = f32 clip_ctx: CLIP using CUDA0 backend load_hparams: Qwen-VL models require at minimum 1024 image tokens to function correctly on grounding tasks load_hparams: if you encounter problems with accuracy, try adding --image-min-tokens 1024 load_hparams: more info: https://github.com/ggml-org/llama.cpp/issues/16842 load_hparams: projector: qwen3vl_merger load_hparams: n_embd: 1152 load_hparams: n_head: 16 load_hparams: n_ff: 4304 load_hparams: n_layer: 27 load_hparams: ffn_op: gelu load_hparams: projection_dim: 5120 --- vision hparams --- load_hparams: image_size: 768 load_hparams: patch_size: 16 load_hparams: has_llava_proj: 0 load_hparams: minicpmv_version: 0 load_hparams: n_merge: 2 load_hparams: n_wa_pattern: 0 load_hparams: image_min_pixels: 8192 load_hparams: image_max_pixels: 4194304 load_hparams: model size: 554.96 MiB load_hparams: metadata size: 0.12 MiB load_tensors: loaded 352 tensors from C:\Users\Gurka.ollama\models\blobs\sha256-ef210e40ef6ed7f0d13e709846d3da88ddc4d509d044998f3cf08976d8d04ecc warmup: warmup with image size = 1472 x 1472 alloc_compute_meta: CUDA0 compute buffer size = 417.54 MiB alloc_compute_meta: CPU compute buffer size = 24.93 MiB alloc_compute_meta: graph splits = 1, nodes = 853 warmup: flash attention is enabled time=2025-12-19T05:28:13.359+01:00 level=INFO source=server.go:1376 msg="llama runner started in 4.38 seconds" time=2025-12-19T05:28:13.359+01:00 level=INFO source=sched.go:517 msg="loaded runners" count=1 time=2025-12-19T05:28:13.359+01:00 level=INFO source=server.go:1338 msg="waiting for llama runner to start responding" time=2025-12-19T05:28:13.359+01:00 level=INFO source=server.go:1376 msg="llama runner started in 4.38 seconds" [GIN] 2025/12/19 - 05:28:13 | 200 | 10.0988776s | 127.0.0.1 | POST "/api/generate" llama-context.cpp:1238: GGML_ASSERT((n_outputs_prev + n_outputs)*n_embd <= (int64_t) embd_size) failed time=2025-12-19T05:28:14.864+01:00 level=ERROR source=server.go:1583 msg="post predict" error="Post "http://127.0.0.1:52531/completion": read tcp 127.0.0.1:52544->127.0.0.1:52531: wsarecv: An existing connection was forcibly closed by the remote host." [GIN] 2025/12/19 - 05:28:14 | 500 | 291.4232ms | 127.0.0.1 | POST "/api/chat" time=2025-12-19T05:28:14.898+01:00 level=ERROR source=server.go:302 msg="llama runner terminated" error="exit status 1"

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.12.6 ,0.12.7, 0.12.10, 0.13.4 , 5

Originally created by @Gurka-065 on GitHub (Dec 19, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/13527 ### What is the issue? the GGUF model loads correctly in Ollama: the qwen3vl architecture, all weights, and the vision projector are detected and initialized. When you send the first chat/generate request, the llama.cpp runtime hits an internal assertion: GGML_ASSERT((n_outputs_prev + n_outputs)*n_embd <= (int64_t) embd_size) failed This means: the runtime is trying to write more embedding/output data than the buffer size it allocated, which indicates: A bug or incompatibility in the current llama.cpp/Ollama build with the qwen3vl architecture (especially with your converted GGUF), or A mismatch between how the GGUF was produced and what this llama.cpp version expects. and i test all the llama.cpp and also the build one that for qwen3 vl and it still fail and i test the old and the new one and it still same thing i even test the one for qwen3 only and qwen2 but still dos not working but the qwen3 vl when pulling it from ollama site it dos work fine but not that one from llama.cpp even specific version and i also test ollama 0.12.6 ,0.12.7, 0.12.10, 0.13.4 , 5 ### Relevant log output ... clip_model_loader: n_tensors: 352 clip_model_loader: n_kv: 28 clip_model_loader: has vision encoder clip_model_loader: tensor[0]: n_dims = 1, name = mm.0.bias, tensor_size=18432, offset=0, shape:[4608, 1, 1, 1], type = f32 clip_model_loader: tensor[1]: n_dims = 2, name = mm.0.weight, tensor_size=11943936, offset=18432, shape:[4608, 4608, 1, 1], type = q4_K clip_model_loader: tensor[2]: n_dims = 1, name = mm.2.bias, tensor_size=20480, offset=11962368, shape:[5120, 1, 1, 1], type = f32 clip_model_loader: tensor[3]: n_dims = 2, name = mm.2.weight, tensor_size=13271040, offset=11982848, shape:[4608, 5120, 1, 1], type = q4_K clip_model_loader: tensor[4]: n_dims = 1, name = v.blk.0.attn_out.bias, tensor_size=4608, offset=25253888, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[5]: n_dims = 2, name = v.blk.0.attn_out.weight, tensor_size=912384, offset=25258496, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[6]: n_dims = 1, name = v.blk.0.attn_qkv.bias, tensor_size=13824, offset=26170880, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[7]: n_dims = 2, name = v.blk.0.attn_qkv.weight, tensor_size=2985984, offset=26184704, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[8]: n_dims = 1, name = v.blk.0.ffn_down.bias, tensor_size=4608, offset=29170688, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[9]: n_dims = 2, name = v.blk.0.ffn_down.weight, tensor_size=9916416, offset=29175296, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[10]: n_dims = 1, name = v.blk.0.ffn_up.bias, tensor_size=17216, offset=39091712, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[11]: n_dims = 2, name = v.blk.0.ffn_up.weight, tensor_size=3408768, offset=39108928, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[12]: n_dims = 1, name = v.blk.0.ln1.bias, tensor_size=4608, offset=42517696, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[13]: n_dims = 1, name = v.blk.0.ln1.weight, tensor_size=4608, offset=42522304, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[14]: n_dims = 1, name = v.blk.0.ln2.bias, tensor_size=4608, offset=42526912, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[15]: n_dims = 1, name = v.blk.0.ln2.weight, tensor_size=4608, offset=42531520, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[16]: n_dims = 1, name = v.blk.1.attn_out.bias, tensor_size=4608, offset=42536128, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[17]: n_dims = 2, name = v.blk.1.attn_out.weight, tensor_size=912384, offset=42540736, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[18]: n_dims = 1, name = v.blk.1.attn_qkv.bias, tensor_size=13824, offset=43453120, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[19]: n_dims = 2, name = v.blk.1.attn_qkv.weight, tensor_size=2985984, offset=43466944, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[20]: n_dims = 1, name = v.blk.1.ffn_down.bias, tensor_size=4608, offset=46452928, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[21]: n_dims = 2, name = v.blk.1.ffn_down.weight, tensor_size=9916416, offset=46457536, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[22]: n_dims = 1, name = v.blk.1.ffn_up.bias, tensor_size=17216, offset=56373952, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[23]: n_dims = 2, name = v.blk.1.ffn_up.weight, tensor_size=3408768, offset=56391168, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[24]: n_dims = 1, name = v.blk.1.ln1.bias, tensor_size=4608, offset=59799936, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[25]: n_dims = 1, name = v.blk.1.ln1.weight, tensor_size=4608, offset=59804544, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[26]: n_dims = 1, name = v.blk.1.ln2.bias, tensor_size=4608, offset=59809152, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[27]: n_dims = 1, name = v.blk.1.ln2.weight, tensor_size=4608, offset=59813760, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[28]: n_dims = 1, name = v.blk.10.attn_out.bias, tensor_size=4608, offset=59818368, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[29]: n_dims = 2, name = v.blk.10.attn_out.weight, tensor_size=912384, offset=59822976, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[30]: n_dims = 1, name = v.blk.10.attn_qkv.bias, tensor_size=13824, offset=60735360, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[31]: n_dims = 2, name = v.blk.10.attn_qkv.weight, tensor_size=2985984, offset=60749184, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[32]: n_dims = 1, name = v.blk.10.ffn_down.bias, tensor_size=4608, offset=63735168, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[33]: n_dims = 2, name = v.blk.10.ffn_down.weight, tensor_size=9916416, offset=63739776, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[34]: n_dims = 1, name = v.blk.10.ffn_up.bias, tensor_size=17216, offset=73656192, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[35]: n_dims = 2, name = v.blk.10.ffn_up.weight, tensor_size=3408768, offset=73673408, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[36]: n_dims = 1, name = v.blk.10.ln1.bias, tensor_size=4608, offset=77082176, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[37]: n_dims = 1, name = v.blk.10.ln1.weight, tensor_size=4608, offset=77086784, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[38]: n_dims = 1, name = v.blk.10.ln2.bias, tensor_size=4608, offset=77091392, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[39]: n_dims = 1, name = v.blk.10.ln2.weight, tensor_size=4608, offset=77096000, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[40]: n_dims = 1, name = v.blk.11.attn_out.bias, tensor_size=4608, offset=77100608, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[41]: n_dims = 2, name = v.blk.11.attn_out.weight, tensor_size=912384, offset=77105216, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[42]: n_dims = 1, name = v.blk.11.attn_qkv.bias, tensor_size=13824, offset=78017600, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[43]: n_dims = 2, name = v.blk.11.attn_qkv.weight, tensor_size=2985984, offset=78031424, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[44]: n_dims = 1, name = v.blk.11.ffn_down.bias, tensor_size=4608, offset=81017408, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[45]: n_dims = 2, name = v.blk.11.ffn_down.weight, tensor_size=9916416, offset=81022016, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[46]: n_dims = 1, name = v.blk.11.ffn_up.bias, tensor_size=17216, offset=90938432, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[47]: n_dims = 2, name = v.blk.11.ffn_up.weight, tensor_size=3408768, offset=90955648, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[48]: n_dims = 1, name = v.blk.11.ln1.bias, tensor_size=4608, offset=94364416, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[49]: n_dims = 1, name = v.blk.11.ln1.weight, tensor_size=4608, offset=94369024, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[50]: n_dims = 1, name = v.blk.11.ln2.bias, tensor_size=4608, offset=94373632, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[51]: n_dims = 1, name = v.blk.11.ln2.weight, tensor_size=4608, offset=94378240, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[52]: n_dims = 1, name = v.blk.12.attn_out.bias, tensor_size=4608, offset=94382848, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[53]: n_dims = 2, name = v.blk.12.attn_out.weight, tensor_size=912384, offset=94387456, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[54]: n_dims = 1, name = v.blk.12.attn_qkv.bias, tensor_size=13824, offset=95299840, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[55]: n_dims = 2, name = v.blk.12.attn_qkv.weight, tensor_size=2985984, offset=95313664, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[56]: n_dims = 1, name = v.blk.12.ffn_down.bias, tensor_size=4608, offset=98299648, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[57]: n_dims = 2, name = v.blk.12.ffn_down.weight, tensor_size=9916416, offset=98304256, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[58]: n_dims = 1, name = v.blk.12.ffn_up.bias, tensor_size=17216, offset=108220672, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[59]: n_dims = 2, name = v.blk.12.ffn_up.weight, tensor_size=3408768, offset=108237888, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[60]: n_dims = 1, name = v.blk.12.ln1.bias, tensor_size=4608, offset=111646656, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[61]: n_dims = 1, name = v.blk.12.ln1.weight, tensor_size=4608, offset=111651264, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[62]: n_dims = 1, name = v.blk.12.ln2.bias, tensor_size=4608, offset=111655872, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[63]: n_dims = 1, name = v.blk.12.ln2.weight, tensor_size=4608, offset=111660480, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[64]: n_dims = 1, name = v.blk.13.attn_out.bias, tensor_size=4608, offset=111665088, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[65]: n_dims = 2, name = v.blk.13.attn_out.weight, tensor_size=912384, offset=111669696, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[66]: n_dims = 1, name = v.blk.13.attn_qkv.bias, tensor_size=13824, offset=112582080, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[67]: n_dims = 2, name = v.blk.13.attn_qkv.weight, tensor_size=2985984, offset=112595904, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[68]: n_dims = 1, name = v.blk.13.ffn_down.bias, tensor_size=4608, offset=115581888, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[69]: n_dims = 2, name = v.blk.13.ffn_down.weight, tensor_size=9916416, offset=115586496, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[70]: n_dims = 1, name = v.blk.13.ffn_up.bias, tensor_size=17216, offset=125502912, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[71]: n_dims = 2, name = v.blk.13.ffn_up.weight, tensor_size=3408768, offset=125520128, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[72]: n_dims = 1, name = v.blk.13.ln1.bias, tensor_size=4608, offset=128928896, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[73]: n_dims = 1, name = v.blk.13.ln1.weight, tensor_size=4608, offset=128933504, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[74]: n_dims = 1, name = v.blk.13.ln2.bias, tensor_size=4608, offset=128938112, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[75]: n_dims = 1, name = v.blk.13.ln2.weight, tensor_size=4608, offset=128942720, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[76]: n_dims = 1, name = v.blk.14.attn_out.bias, tensor_size=4608, offset=128947328, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[77]: n_dims = 2, name = v.blk.14.attn_out.weight, tensor_size=912384, offset=128951936, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[78]: n_dims = 1, name = v.blk.14.attn_qkv.bias, tensor_size=13824, offset=129864320, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[79]: n_dims = 2, name = v.blk.14.attn_qkv.weight, tensor_size=2985984, offset=129878144, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[80]: n_dims = 1, name = v.blk.14.ffn_down.bias, tensor_size=4608, offset=132864128, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[81]: n_dims = 2, name = v.blk.14.ffn_down.weight, tensor_size=9916416, offset=132868736, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[82]: n_dims = 1, name = v.blk.14.ffn_up.bias, tensor_size=17216, offset=142785152, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[83]: n_dims = 2, name = v.blk.14.ffn_up.weight, tensor_size=3408768, offset=142802368, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[84]: n_dims = 1, name = v.blk.14.ln1.bias, tensor_size=4608, offset=146211136, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[85]: n_dims = 1, name = v.blk.14.ln1.weight, tensor_size=4608, offset=146215744, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[86]: n_dims = 1, name = v.blk.14.ln2.bias, tensor_size=4608, offset=146220352, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[87]: n_dims = 1, name = v.blk.14.ln2.weight, tensor_size=4608, offset=146224960, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[88]: n_dims = 1, name = v.blk.15.attn_out.bias, tensor_size=4608, offset=146229568, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[89]: n_dims = 2, name = v.blk.15.attn_out.weight, tensor_size=912384, offset=146234176, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[90]: n_dims = 1, name = v.blk.15.attn_qkv.bias, tensor_size=13824, offset=147146560, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[91]: n_dims = 2, name = v.blk.15.attn_qkv.weight, tensor_size=2985984, offset=147160384, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[92]: n_dims = 1, name = v.blk.15.ffn_down.bias, tensor_size=4608, offset=150146368, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[93]: n_dims = 2, name = v.blk.15.ffn_down.weight, tensor_size=9916416, offset=150150976, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[94]: n_dims = 1, name = v.blk.15.ffn_up.bias, tensor_size=17216, offset=160067392, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[95]: n_dims = 2, name = v.blk.15.ffn_up.weight, tensor_size=3408768, offset=160084608, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[96]: n_dims = 1, name = v.blk.15.ln1.bias, tensor_size=4608, offset=163493376, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[97]: n_dims = 1, name = v.blk.15.ln1.weight, tensor_size=4608, offset=163497984, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[98]: n_dims = 1, name = v.blk.15.ln2.bias, tensor_size=4608, offset=163502592, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[99]: n_dims = 1, name = v.blk.15.ln2.weight, tensor_size=4608, offset=163507200, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[100]: n_dims = 1, name = v.blk.16.attn_out.bias, tensor_size=4608, offset=163511808, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[101]: n_dims = 2, name = v.blk.16.attn_out.weight, tensor_size=912384, offset=163516416, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[102]: n_dims = 1, name = v.blk.16.attn_qkv.bias, tensor_size=13824, offset=164428800, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[103]: n_dims = 2, name = v.blk.16.attn_qkv.weight, tensor_size=2985984, offset=164442624, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[104]: n_dims = 1, name = v.blk.16.ffn_down.bias, tensor_size=4608, offset=167428608, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[105]: n_dims = 2, name = v.blk.16.ffn_down.weight, tensor_size=9916416, offset=167433216, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[106]: n_dims = 1, name = v.blk.16.ffn_up.bias, tensor_size=17216, offset=177349632, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[107]: n_dims = 2, name = v.blk.16.ffn_up.weight, tensor_size=3408768, offset=177366848, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[108]: n_dims = 1, name = v.blk.16.ln1.bias, tensor_size=4608, offset=180775616, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[109]: n_dims = 1, name = v.blk.16.ln1.weight, tensor_size=4608, offset=180780224, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[110]: n_dims = 1, name = v.blk.16.ln2.bias, tensor_size=4608, offset=180784832, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[111]: n_dims = 1, name = v.blk.16.ln2.weight, tensor_size=4608, offset=180789440, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[112]: n_dims = 1, name = v.blk.17.attn_out.bias, tensor_size=4608, offset=180794048, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[113]: n_dims = 2, name = v.blk.17.attn_out.weight, tensor_size=912384, offset=180798656, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[114]: n_dims = 1, name = v.blk.17.attn_qkv.bias, tensor_size=13824, offset=181711040, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[115]: n_dims = 2, name = v.blk.17.attn_qkv.weight, tensor_size=2985984, offset=181724864, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[116]: n_dims = 1, name = v.blk.17.ffn_down.bias, tensor_size=4608, offset=184710848, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[117]: n_dims = 2, name = v.blk.17.ffn_down.weight, tensor_size=9916416, offset=184715456, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[118]: n_dims = 1, name = v.blk.17.ffn_up.bias, tensor_size=17216, offset=194631872, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[119]: n_dims = 2, name = v.blk.17.ffn_up.weight, tensor_size=3408768, offset=194649088, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[120]: n_dims = 1, name = v.blk.17.ln1.bias, tensor_size=4608, offset=198057856, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[121]: n_dims = 1, name = v.blk.17.ln1.weight, tensor_size=4608, offset=198062464, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[122]: n_dims = 1, name = v.blk.17.ln2.bias, tensor_size=4608, offset=198067072, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[123]: n_dims = 1, name = v.blk.17.ln2.weight, tensor_size=4608, offset=198071680, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[124]: n_dims = 1, name = v.blk.18.attn_out.bias, tensor_size=4608, offset=198076288, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[125]: n_dims = 2, name = v.blk.18.attn_out.weight, tensor_size=912384, offset=198080896, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[126]: n_dims = 1, name = v.blk.18.attn_qkv.bias, tensor_size=13824, offset=198993280, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[127]: n_dims = 2, name = v.blk.18.attn_qkv.weight, tensor_size=2985984, offset=199007104, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[128]: n_dims = 1, name = v.blk.18.ffn_down.bias, tensor_size=4608, offset=201993088, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[129]: n_dims = 2, name = v.blk.18.ffn_down.weight, tensor_size=9916416, offset=201997696, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[130]: n_dims = 1, name = v.blk.18.ffn_up.bias, tensor_size=17216, offset=211914112, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[131]: n_dims = 2, name = v.blk.18.ffn_up.weight, tensor_size=3408768, offset=211931328, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[132]: n_dims = 1, name = v.blk.18.ln1.bias, tensor_size=4608, offset=215340096, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[133]: n_dims = 1, name = v.blk.18.ln1.weight, tensor_size=4608, offset=215344704, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[134]: n_dims = 1, name = v.blk.18.ln2.bias, tensor_size=4608, offset=215349312, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[135]: n_dims = 1, name = v.blk.18.ln2.weight, tensor_size=4608, offset=215353920, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[136]: n_dims = 1, name = v.blk.19.attn_out.bias, tensor_size=4608, offset=215358528, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[137]: n_dims = 2, name = v.blk.19.attn_out.weight, tensor_size=912384, offset=215363136, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[138]: n_dims = 1, name = v.blk.19.attn_qkv.bias, tensor_size=13824, offset=216275520, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[139]: n_dims = 2, name = v.blk.19.attn_qkv.weight, tensor_size=2985984, offset=216289344, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[140]: n_dims = 1, name = v.blk.19.ffn_down.bias, tensor_size=4608, offset=219275328, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[141]: n_dims = 2, name = v.blk.19.ffn_down.weight, tensor_size=9916416, offset=219279936, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[142]: n_dims = 1, name = v.blk.19.ffn_up.bias, tensor_size=17216, offset=229196352, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[143]: n_dims = 2, name = v.blk.19.ffn_up.weight, tensor_size=3408768, offset=229213568, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[144]: n_dims = 1, name = v.blk.19.ln1.bias, tensor_size=4608, offset=232622336, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[145]: n_dims = 1, name = v.blk.19.ln1.weight, tensor_size=4608, offset=232626944, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[146]: n_dims = 1, name = v.blk.19.ln2.bias, tensor_size=4608, offset=232631552, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[147]: n_dims = 1, name = v.blk.19.ln2.weight, tensor_size=4608, offset=232636160, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[148]: n_dims = 1, name = v.blk.2.attn_out.bias, tensor_size=4608, offset=232640768, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[149]: n_dims = 2, name = v.blk.2.attn_out.weight, tensor_size=912384, offset=232645376, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[150]: n_dims = 1, name = v.blk.2.attn_qkv.bias, tensor_size=13824, offset=233557760, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[151]: n_dims = 2, name = v.blk.2.attn_qkv.weight, tensor_size=2985984, offset=233571584, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[152]: n_dims = 1, name = v.blk.2.ffn_down.bias, tensor_size=4608, offset=236557568, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[153]: n_dims = 2, name = v.blk.2.ffn_down.weight, tensor_size=9916416, offset=236562176, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[154]: n_dims = 1, name = v.blk.2.ffn_up.bias, tensor_size=17216, offset=246478592, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[155]: n_dims = 2, name = v.blk.2.ffn_up.weight, tensor_size=3408768, offset=246495808, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[156]: n_dims = 1, name = v.blk.2.ln1.bias, tensor_size=4608, offset=249904576, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[157]: n_dims = 1, name = v.blk.2.ln1.weight, tensor_size=4608, offset=249909184, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[158]: n_dims = 1, name = v.blk.2.ln2.bias, tensor_size=4608, offset=249913792, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[159]: n_dims = 1, name = v.blk.2.ln2.weight, tensor_size=4608, offset=249918400, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[160]: n_dims = 1, name = v.blk.20.attn_out.bias, tensor_size=4608, offset=249923008, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[161]: n_dims = 2, name = v.blk.20.attn_out.weight, tensor_size=912384, offset=249927616, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[162]: n_dims = 1, name = v.blk.20.attn_qkv.bias, tensor_size=13824, offset=250840000, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[163]: n_dims = 2, name = v.blk.20.attn_qkv.weight, tensor_size=2985984, offset=250853824, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[164]: n_dims = 1, name = v.blk.20.ffn_down.bias, tensor_size=4608, offset=253839808, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[165]: n_dims = 2, name = v.blk.20.ffn_down.weight, tensor_size=9916416, offset=253844416, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[166]: n_dims = 1, name = v.blk.20.ffn_up.bias, tensor_size=17216, offset=263760832, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[167]: n_dims = 2, name = v.blk.20.ffn_up.weight, tensor_size=3408768, offset=263778048, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[168]: n_dims = 1, name = v.blk.20.ln1.bias, tensor_size=4608, offset=267186816, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[169]: n_dims = 1, name = v.blk.20.ln1.weight, tensor_size=4608, offset=267191424, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[170]: n_dims = 1, name = v.blk.20.ln2.bias, tensor_size=4608, offset=267196032, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[171]: n_dims = 1, name = v.blk.20.ln2.weight, tensor_size=4608, offset=267200640, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[172]: n_dims = 1, name = v.blk.21.attn_out.bias, tensor_size=4608, offset=267205248, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[173]: n_dims = 2, name = v.blk.21.attn_out.weight, tensor_size=912384, offset=267209856, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[174]: n_dims = 1, name = v.blk.21.attn_qkv.bias, tensor_size=13824, offset=268122240, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[175]: n_dims = 2, name = v.blk.21.attn_qkv.weight, tensor_size=2985984, offset=268136064, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[176]: n_dims = 1, name = v.blk.21.ffn_down.bias, tensor_size=4608, offset=271122048, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[177]: n_dims = 2, name = v.blk.21.ffn_down.weight, tensor_size=9916416, offset=271126656, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[178]: n_dims = 1, name = v.blk.21.ffn_up.bias, tensor_size=17216, offset=281043072, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[179]: n_dims = 2, name = v.blk.21.ffn_up.weight, tensor_size=3408768, offset=281060288, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[180]: n_dims = 1, name = v.blk.21.ln1.bias, tensor_size=4608, offset=284469056, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[181]: n_dims = 1, name = v.blk.21.ln1.weight, tensor_size=4608, offset=284473664, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[182]: n_dims = 1, name = v.blk.21.ln2.bias, tensor_size=4608, offset=284478272, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[183]: n_dims = 1, name = v.blk.21.ln2.weight, tensor_size=4608, offset=284482880, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[184]: n_dims = 1, name = v.blk.22.attn_out.bias, tensor_size=4608, offset=284487488, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[185]: n_dims = 2, name = v.blk.22.attn_out.weight, tensor_size=912384, offset=284492096, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[186]: n_dims = 1, name = v.blk.22.attn_qkv.bias, tensor_size=13824, offset=285404480, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[187]: n_dims = 2, name = v.blk.22.attn_qkv.weight, tensor_size=2985984, offset=285418304, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[188]: n_dims = 1, name = v.blk.22.ffn_down.bias, tensor_size=4608, offset=288404288, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[189]: n_dims = 2, name = v.blk.22.ffn_down.weight, tensor_size=9916416, offset=288408896, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[190]: n_dims = 1, name = v.blk.22.ffn_up.bias, tensor_size=17216, offset=298325312, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[191]: n_dims = 2, name = v.blk.22.ffn_up.weight, tensor_size=3408768, offset=298342528, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[192]: n_dims = 1, name = v.blk.22.ln1.bias, tensor_size=4608, offset=301751296, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[193]: n_dims = 1, name = v.blk.22.ln1.weight, tensor_size=4608, offset=301755904, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[194]: n_dims = 1, name = v.blk.22.ln2.bias, tensor_size=4608, offset=301760512, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[195]: n_dims = 1, name = v.blk.22.ln2.weight, tensor_size=4608, offset=301765120, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[196]: n_dims = 1, name = v.blk.23.attn_out.bias, tensor_size=4608, offset=301769728, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[197]: n_dims = 2, name = v.blk.23.attn_out.weight, tensor_size=912384, offset=301774336, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[198]: n_dims = 1, name = v.blk.23.attn_qkv.bias, tensor_size=13824, offset=302686720, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[199]: n_dims = 2, name = v.blk.23.attn_qkv.weight, tensor_size=2985984, offset=302700544, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[200]: n_dims = 1, name = v.blk.23.ffn_down.bias, tensor_size=4608, offset=305686528, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[201]: n_dims = 2, name = v.blk.23.ffn_down.weight, tensor_size=9916416, offset=305691136, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[202]: n_dims = 1, name = v.blk.23.ffn_up.bias, tensor_size=17216, offset=315607552, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[203]: n_dims = 2, name = v.blk.23.ffn_up.weight, tensor_size=3408768, offset=315624768, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[204]: n_dims = 1, name = v.blk.23.ln1.bias, tensor_size=4608, offset=319033536, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[205]: n_dims = 1, name = v.blk.23.ln1.weight, tensor_size=4608, offset=319038144, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[206]: n_dims = 1, name = v.blk.23.ln2.bias, tensor_size=4608, offset=319042752, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[207]: n_dims = 1, name = v.blk.23.ln2.weight, tensor_size=4608, offset=319047360, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[208]: n_dims = 1, name = v.blk.24.attn_out.bias, tensor_size=4608, offset=319051968, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[209]: n_dims = 2, name = v.blk.24.attn_out.weight, tensor_size=912384, offset=319056576, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[210]: n_dims = 1, name = v.blk.24.attn_qkv.bias, tensor_size=13824, offset=319968960, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[211]: n_dims = 2, name = v.blk.24.attn_qkv.weight, tensor_size=2985984, offset=319982784, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[212]: n_dims = 1, name = v.blk.24.ffn_down.bias, tensor_size=4608, offset=322968768, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[213]: n_dims = 2, name = v.blk.24.ffn_down.weight, tensor_size=9916416, offset=322973376, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[214]: n_dims = 1, name = v.blk.24.ffn_up.bias, tensor_size=17216, offset=332889792, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[215]: n_dims = 2, name = v.blk.24.ffn_up.weight, tensor_size=3408768, offset=332907008, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[216]: n_dims = 1, name = v.blk.24.ln1.bias, tensor_size=4608, offset=336315776, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[217]: n_dims = 1, name = v.blk.24.ln1.weight, tensor_size=4608, offset=336320384, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[218]: n_dims = 1, name = v.blk.24.ln2.bias, tensor_size=4608, offset=336324992, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[219]: n_dims = 1, name = v.blk.24.ln2.weight, tensor_size=4608, offset=336329600, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[220]: n_dims = 1, name = v.blk.25.attn_out.bias, tensor_size=4608, offset=336334208, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[221]: n_dims = 2, name = v.blk.25.attn_out.weight, tensor_size=912384, offset=336338816, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[222]: n_dims = 1, name = v.blk.25.attn_qkv.bias, tensor_size=13824, offset=337251200, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[223]: n_dims = 2, name = v.blk.25.attn_qkv.weight, tensor_size=2985984, offset=337265024, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[224]: n_dims = 1, name = v.blk.25.ffn_down.bias, tensor_size=4608, offset=340251008, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[225]: n_dims = 2, name = v.blk.25.ffn_down.weight, tensor_size=9916416, offset=340255616, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[226]: n_dims = 1, name = v.blk.25.ffn_up.bias, tensor_size=17216, offset=350172032, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[227]: n_dims = 2, name = v.blk.25.ffn_up.weight, tensor_size=3408768, offset=350189248, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[228]: n_dims = 1, name = v.blk.25.ln1.bias, tensor_size=4608, offset=353598016, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[229]: n_dims = 1, name = v.blk.25.ln1.weight, tensor_size=4608, offset=353602624, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[230]: n_dims = 1, name = v.blk.25.ln2.bias, tensor_size=4608, offset=353607232, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[231]: n_dims = 1, name = v.blk.25.ln2.weight, tensor_size=4608, offset=353611840, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[232]: n_dims = 1, name = v.blk.26.attn_out.bias, tensor_size=4608, offset=353616448, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[233]: n_dims = 2, name = v.blk.26.attn_out.weight, tensor_size=912384, offset=353621056, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[234]: n_dims = 1, name = v.blk.26.attn_qkv.bias, tensor_size=13824, offset=354533440, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[235]: n_dims = 2, name = v.blk.26.attn_qkv.weight, tensor_size=2985984, offset=354547264, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[236]: n_dims = 1, name = v.blk.26.ffn_down.bias, tensor_size=4608, offset=357533248, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[237]: n_dims = 2, name = v.blk.26.ffn_down.weight, tensor_size=9916416, offset=357537856, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[238]: n_dims = 1, name = v.blk.26.ffn_up.bias, tensor_size=17216, offset=367454272, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[239]: n_dims = 2, name = v.blk.26.ffn_up.weight, tensor_size=3408768, offset=367471488, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[240]: n_dims = 1, name = v.blk.26.ln1.bias, tensor_size=4608, offset=370880256, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[241]: n_dims = 1, name = v.blk.26.ln1.weight, tensor_size=4608, offset=370884864, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[242]: n_dims = 1, name = v.blk.26.ln2.bias, tensor_size=4608, offset=370889472, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[243]: n_dims = 1, name = v.blk.26.ln2.weight, tensor_size=4608, offset=370894080, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[244]: n_dims = 1, name = v.blk.3.attn_out.bias, tensor_size=4608, offset=370898688, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[245]: n_dims = 2, name = v.blk.3.attn_out.weight, tensor_size=912384, offset=370903296, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[246]: n_dims = 1, name = v.blk.3.attn_qkv.bias, tensor_size=13824, offset=371815680, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[247]: n_dims = 2, name = v.blk.3.attn_qkv.weight, tensor_size=2985984, offset=371829504, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[248]: n_dims = 1, name = v.blk.3.ffn_down.bias, tensor_size=4608, offset=374815488, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[249]: n_dims = 2, name = v.blk.3.ffn_down.weight, tensor_size=9916416, offset=374820096, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[250]: n_dims = 1, name = v.blk.3.ffn_up.bias, tensor_size=17216, offset=384736512, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[251]: n_dims = 2, name = v.blk.3.ffn_up.weight, tensor_size=3408768, offset=384753728, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[252]: n_dims = 1, name = v.blk.3.ln1.bias, tensor_size=4608, offset=388162496, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[253]: n_dims = 1, name = v.blk.3.ln1.weight, tensor_size=4608, offset=388167104, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[254]: n_dims = 1, name = v.blk.3.ln2.bias, tensor_size=4608, offset=388171712, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[255]: n_dims = 1, name = v.blk.3.ln2.weight, tensor_size=4608, offset=388176320, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[256]: n_dims = 1, name = v.blk.4.attn_out.bias, tensor_size=4608, offset=388180928, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[257]: n_dims = 2, name = v.blk.4.attn_out.weight, tensor_size=912384, offset=388185536, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[258]: n_dims = 1, name = v.blk.4.attn_qkv.bias, tensor_size=13824, offset=389097920, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[259]: n_dims = 2, name = v.blk.4.attn_qkv.weight, tensor_size=2985984, offset=389111744, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[260]: n_dims = 1, name = v.blk.4.ffn_down.bias, tensor_size=4608, offset=392097728, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[261]: n_dims = 2, name = v.blk.4.ffn_down.weight, tensor_size=9916416, offset=392102336, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[262]: n_dims = 1, name = v.blk.4.ffn_up.bias, tensor_size=17216, offset=402018752, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[263]: n_dims = 2, name = v.blk.4.ffn_up.weight, tensor_size=3408768, offset=402035968, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[264]: n_dims = 1, name = v.blk.4.ln1.bias, tensor_size=4608, offset=405444736, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[265]: n_dims = 1, name = v.blk.4.ln1.weight, tensor_size=4608, offset=405449344, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[266]: n_dims = 1, name = v.blk.4.ln2.bias, tensor_size=4608, offset=405453952, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[267]: n_dims = 1, name = v.blk.4.ln2.weight, tensor_size=4608, offset=405458560, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[268]: n_dims = 1, name = v.blk.5.attn_out.bias, tensor_size=4608, offset=405463168, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[269]: n_dims = 2, name = v.blk.5.attn_out.weight, tensor_size=912384, offset=405467776, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[270]: n_dims = 1, name = v.blk.5.attn_qkv.bias, tensor_size=13824, offset=406380160, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[271]: n_dims = 2, name = v.blk.5.attn_qkv.weight, tensor_size=2985984, offset=406393984, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[272]: n_dims = 1, name = v.blk.5.ffn_down.bias, tensor_size=4608, offset=409379968, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[273]: n_dims = 2, name = v.blk.5.ffn_down.weight, tensor_size=9916416, offset=409384576, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[274]: n_dims = 1, name = v.blk.5.ffn_up.bias, tensor_size=17216, offset=419300992, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[275]: n_dims = 2, name = v.blk.5.ffn_up.weight, tensor_size=3408768, offset=419318208, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[276]: n_dims = 1, name = v.blk.5.ln1.bias, tensor_size=4608, offset=422726976, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[277]: n_dims = 1, name = v.blk.5.ln1.weight, tensor_size=4608, offset=422731584, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[278]: n_dims = 1, name = v.blk.5.ln2.bias, tensor_size=4608, offset=422736192, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[279]: n_dims = 1, name = v.blk.5.ln2.weight, tensor_size=4608, offset=422740800, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[280]: n_dims = 1, name = v.blk.6.attn_out.bias, tensor_size=4608, offset=422745408, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[281]: n_dims = 2, name = v.blk.6.attn_out.weight, tensor_size=912384, offset=422750016, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[282]: n_dims = 1, name = v.blk.6.attn_qkv.bias, tensor_size=13824, offset=423662400, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[283]: n_dims = 2, name = v.blk.6.attn_qkv.weight, tensor_size=2985984, offset=423676224, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[284]: n_dims = 1, name = v.blk.6.ffn_down.bias, tensor_size=4608, offset=426662208, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[285]: n_dims = 2, name = v.blk.6.ffn_down.weight, tensor_size=9916416, offset=426666816, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[286]: n_dims = 1, name = v.blk.6.ffn_up.bias, tensor_size=17216, offset=436583232, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[287]: n_dims = 2, name = v.blk.6.ffn_up.weight, tensor_size=3408768, offset=436600448, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[288]: n_dims = 1, name = v.blk.6.ln1.bias, tensor_size=4608, offset=440009216, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[289]: n_dims = 1, name = v.blk.6.ln1.weight, tensor_size=4608, offset=440013824, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[290]: n_dims = 1, name = v.blk.6.ln2.bias, tensor_size=4608, offset=440018432, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[291]: n_dims = 1, name = v.blk.6.ln2.weight, tensor_size=4608, offset=440023040, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[292]: n_dims = 1, name = v.blk.7.attn_out.bias, tensor_size=4608, offset=440027648, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[293]: n_dims = 2, name = v.blk.7.attn_out.weight, tensor_size=912384, offset=440032256, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[294]: n_dims = 1, name = v.blk.7.attn_qkv.bias, tensor_size=13824, offset=440944640, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[295]: n_dims = 2, name = v.blk.7.attn_qkv.weight, tensor_size=2985984, offset=440958464, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[296]: n_dims = 1, name = v.blk.7.ffn_down.bias, tensor_size=4608, offset=443944448, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[297]: n_dims = 2, name = v.blk.7.ffn_down.weight, tensor_size=9916416, offset=443949056, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[298]: n_dims = 1, name = v.blk.7.ffn_up.bias, tensor_size=17216, offset=453865472, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[299]: n_dims = 2, name = v.blk.7.ffn_up.weight, tensor_size=3408768, offset=453882688, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[300]: n_dims = 1, name = v.blk.7.ln1.bias, tensor_size=4608, offset=457291456, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[301]: n_dims = 1, name = v.blk.7.ln1.weight, tensor_size=4608, offset=457296064, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[302]: n_dims = 1, name = v.blk.7.ln2.bias, tensor_size=4608, offset=457300672, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[303]: n_dims = 1, name = v.blk.7.ln2.weight, tensor_size=4608, offset=457305280, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[304]: n_dims = 1, name = v.blk.8.attn_out.bias, tensor_size=4608, offset=457309888, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[305]: n_dims = 2, name = v.blk.8.attn_out.weight, tensor_size=912384, offset=457314496, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[306]: n_dims = 1, name = v.blk.8.attn_qkv.bias, tensor_size=13824, offset=458226880, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[307]: n_dims = 2, name = v.blk.8.attn_qkv.weight, tensor_size=2985984, offset=458240704, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[308]: n_dims = 1, name = v.blk.8.ffn_down.bias, tensor_size=4608, offset=461226688, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[309]: n_dims = 2, name = v.blk.8.ffn_down.weight, tensor_size=9916416, offset=461231296, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[310]: n_dims = 1, name = v.blk.8.ffn_up.bias, tensor_size=17216, offset=471147712, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[311]: n_dims = 2, name = v.blk.8.ffn_up.weight, tensor_size=3408768, offset=471164928, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[312]: n_dims = 1, name = v.blk.8.ln1.bias, tensor_size=4608, offset=474573696, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[313]: n_dims = 1, name = v.blk.8.ln1.weight, tensor_size=4608, offset=474578304, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[314]: n_dims = 1, name = v.blk.8.ln2.bias, tensor_size=4608, offset=474582912, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[315]: n_dims = 1, name = v.blk.8.ln2.weight, tensor_size=4608, offset=474587520, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[316]: n_dims = 1, name = v.blk.9.attn_out.bias, tensor_size=4608, offset=474592128, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[317]: n_dims = 2, name = v.blk.9.attn_out.weight, tensor_size=912384, offset=474596736, shape:[1152, 1152, 1, 1], type = q5_0 clip_model_loader: tensor[318]: n_dims = 1, name = v.blk.9.attn_qkv.bias, tensor_size=13824, offset=475509120, shape:[3456, 1, 1, 1], type = f32 clip_model_loader: tensor[319]: n_dims = 2, name = v.blk.9.attn_qkv.weight, tensor_size=2985984, offset=475522944, shape:[1152, 3456, 1, 1], type = q5_1 clip_model_loader: tensor[320]: n_dims = 1, name = v.blk.9.ffn_down.bias, tensor_size=4608, offset=478508928, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[321]: n_dims = 2, name = v.blk.9.ffn_down.weight, tensor_size=9916416, offset=478513536, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[322]: n_dims = 1, name = v.blk.9.ffn_up.bias, tensor_size=17216, offset=488429952, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[323]: n_dims = 2, name = v.blk.9.ffn_up.weight, tensor_size=3408768, offset=488447168, shape:[1152, 4304, 1, 1], type = q5_0 clip_model_loader: tensor[324]: n_dims = 1, name = v.blk.9.ln1.bias, tensor_size=4608, offset=491855936, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[325]: n_dims = 1, name = v.blk.9.ln1.weight, tensor_size=4608, offset=491860544, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[326]: n_dims = 1, name = v.blk.9.ln2.bias, tensor_size=4608, offset=491865152, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[327]: n_dims = 1, name = v.blk.9.ln2.weight, tensor_size=4608, offset=491869760, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[328]: n_dims = 1, name = v.deepstack.16.fc1.bias, tensor_size=18432, offset=491874368, shape:[4608, 1, 1, 1], type = f32 clip_model_loader: tensor[329]: n_dims = 2, name = v.deepstack.16.fc1.weight, tensor_size=11943936, offset=491892800, shape:[4608, 4608, 1, 1], type = q4_K clip_model_loader: tensor[330]: n_dims = 1, name = v.deepstack.16.fc2.bias, tensor_size=20480, offset=503836736, shape:[5120, 1, 1, 1], type = f32 clip_model_loader: tensor[331]: n_dims = 2, name = v.deepstack.16.fc2.weight, tensor_size=13271040, offset=503857216, shape:[4608, 5120, 1, 1], type = q4_K clip_model_loader: tensor[332]: n_dims = 1, name = v.deepstack.16.norm.bias, tensor_size=18432, offset=517128256, shape:[4608, 1, 1, 1], type = f32 clip_model_loader: tensor[333]: n_dims = 1, name = v.deepstack.16.norm.weight, tensor_size=18432, offset=517146688, shape:[4608, 1, 1, 1], type = f32 clip_model_loader: tensor[334]: n_dims = 1, name = v.deepstack.24.fc1.bias, tensor_size=18432, offset=517165120, shape:[4608, 1, 1, 1], type = f32 clip_model_loader: tensor[335]: n_dims = 2, name = v.deepstack.24.fc1.weight, tensor_size=11943936, offset=517183552, shape:[4608, 4608, 1, 1], type = q4_K clip_model_loader: tensor[336]: n_dims = 1, name = v.deepstack.24.fc2.bias, tensor_size=20480, offset=529127488, shape:[5120, 1, 1, 1], type = f32 clip_model_loader: tensor[337]: n_dims = 2, name = v.deepstack.24.fc2.weight, tensor_size=13271040, offset=529147968, shape:[4608, 5120, 1, 1], type = q4_K clip_model_loader: tensor[338]: n_dims = 1, name = v.deepstack.24.norm.bias, tensor_size=18432, offset=542419008, shape:[4608, 1, 1, 1], type = f32 clip_model_loader: tensor[339]: n_dims = 1, name = v.deepstack.24.norm.weight, tensor_size=18432, offset=542437440, shape:[4608, 1, 1, 1], type = f32 clip_model_loader: tensor[340]: n_dims = 1, name = v.deepstack.8.fc1.bias, tensor_size=18432, offset=542455872, shape:[4608, 1, 1, 1], type = f32 clip_model_loader: tensor[341]: n_dims = 2, name = v.deepstack.8.fc1.weight, tensor_size=11943936, offset=542474304, shape:[4608, 4608, 1, 1], type = q4_K clip_model_loader: tensor[342]: n_dims = 1, name = v.deepstack.8.fc2.bias, tensor_size=20480, offset=554418240, shape:[5120, 1, 1, 1], type = f32 clip_model_loader: tensor[343]: n_dims = 2, name = v.deepstack.8.fc2.weight, tensor_size=13271040, offset=554438720, shape:[4608, 5120, 1, 1], type = q4_K clip_model_loader: tensor[344]: n_dims = 1, name = v.deepstack.8.norm.bias, tensor_size=18432, offset=567709760, shape:[4608, 1, 1, 1], type = f32 clip_model_loader: tensor[345]: n_dims = 1, name = v.deepstack.8.norm.weight, tensor_size=18432, offset=567728192, shape:[4608, 1, 1, 1], type = f32 clip_model_loader: tensor[346]: n_dims = 1, name = v.patch_embd.bias, tensor_size=4608, offset=567746624, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[347]: n_dims = 4, name = v.patch_embd.weight, tensor_size=1769472, offset=567751232, shape:[16, 16, 3, 1152], type = f16 clip_model_loader: tensor[348]: n_dims = 4, name = v.patch_embd.weight.1, tensor_size=1769472, offset=569520704, shape:[16, 16, 3, 1152], type = f16 clip_model_loader: tensor[349]: n_dims = 2, name = v.position_embd.weight, tensor_size=10616832, offset=571290176, shape:[1152, 2304, 1, 1], type = f32 clip_model_loader: tensor[350]: n_dims = 1, name = v.post_ln.bias, tensor_size=4608, offset=581907008, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[351]: n_dims = 1, name = v.post_ln.weight, tensor_size=4608, offset=581911616, shape:[1152, 1, 1, 1], type = f32 clip_ctx: CLIP using CUDA0 backend load_hparams: Qwen-VL models require at minimum 1024 image tokens to function correctly on grounding tasks load_hparams: if you encounter problems with accuracy, try adding --image-min-tokens 1024 load_hparams: more info: https://github.com/ggml-org/llama.cpp/issues/16842 load_hparams: projector: qwen3vl_merger load_hparams: n_embd: 1152 load_hparams: n_head: 16 load_hparams: n_ff: 4304 load_hparams: n_layer: 27 load_hparams: ffn_op: gelu load_hparams: projection_dim: 5120 --- vision hparams --- load_hparams: image_size: 768 load_hparams: patch_size: 16 load_hparams: has_llava_proj: 0 load_hparams: minicpmv_version: 0 load_hparams: n_merge: 2 load_hparams: n_wa_pattern: 0 load_hparams: image_min_pixels: 8192 load_hparams: image_max_pixels: 4194304 load_hparams: model size: 554.96 MiB load_hparams: metadata size: 0.12 MiB load_tensors: loaded 352 tensors from C:\Users\Gurka\.ollama\models\blobs\sha256-ef210e40ef6ed7f0d13e709846d3da88ddc4d509d044998f3cf08976d8d04ecc warmup: warmup with image size = 1472 x 1472 alloc_compute_meta: CUDA0 compute buffer size = 417.54 MiB alloc_compute_meta: CPU compute buffer size = 24.93 MiB alloc_compute_meta: graph splits = 1, nodes = 853 warmup: flash attention is enabled time=2025-12-19T05:28:13.359+01:00 level=INFO source=server.go:1376 msg="llama runner started in 4.38 seconds" time=2025-12-19T05:28:13.359+01:00 level=INFO source=sched.go:517 msg="loaded runners" count=1 time=2025-12-19T05:28:13.359+01:00 level=INFO source=server.go:1338 msg="waiting for llama runner to start responding" time=2025-12-19T05:28:13.359+01:00 level=INFO source=server.go:1376 msg="llama runner started in 4.38 seconds" [GIN] 2025/12/19 - 05:28:13 | 200 | 10.0988776s | 127.0.0.1 | POST "/api/generate" llama-context.cpp:1238: GGML_ASSERT((n_outputs_prev + n_outputs)*n_embd <= (int64_t) embd_size) failed time=2025-12-19T05:28:14.864+01:00 level=ERROR source=server.go:1583 msg="post predict" error="Post \"http://127.0.0.1:52531/completion\": read tcp 127.0.0.1:52544->127.0.0.1:52531: wsarecv: An existing connection was forcibly closed by the remote host." [GIN] 2025/12/19 - 05:28:14 | 500 | 291.4232ms | 127.0.0.1 | POST "/api/chat" time=2025-12-19T05:28:14.898+01:00 level=ERROR source=server.go:302 msg="llama runner terminated" error="exit status 1" ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.12.6 ,0.12.7, 0.12.10, 0.13.4 , 5

GiteaMirror added the bug label 2026-05-04 23:36:19 -05:00

GiteaMirror closed this issue

2026-05-04 23:36:21 -05:00

GiteaMirror commented

2026-05-04 23:36:23 -05:00

@aslak3 commented on GitHub (Dec 23, 2025):

I'm not in anyway attached to this project, just a user. However it's clear you need to do two things to get this issue noticed:

Fix the title "I face an issue" tells the reader nothing.
Fix the formatting of the dump you have included.

HTH.

@aslak3 commented on GitHub (Dec 23, 2025): I'm not in anyway attached to this project, just a user. However it's clear you need to do two things to get this issue noticed: 1. Fix the title "I face an issue" tells the reader nothing. 2. Fix the formatting of the dump you have included. HTH.

GiteaMirror commented

2026-05-04 23:36:23 -05:00

@jamestmartin commented on GitHub (Jan 23, 2026):

Awful formatting aside of the OP, I'm having the same issue on Fedora 43/RX 9070 XT/9800X3D, Ollama 0.15.0. Using hf.co/unsloth/Qwen3-VL-8B-Thinking-GGUF:Q6_K. The Q4 version from ollama.com works fine, but I specifically want the Q6 quant. The issue also applies to hf.co/unsloth/Qwen3-VL-32B-Thinking-GGUF:UD-Q4_K_XL. Decreasing num_batch, num_gpu, num_ctx,, flash attention, KV cache, and hipblaslt don't work.

Don't have time to file a real bug report right now. Already spent too much time debugging other peoples' crap.

@jamestmartin commented on GitHub (Jan 23, 2026): Awful formatting aside of the OP, I'm having the same issue on Fedora 43/RX 9070 XT/9800X3D, Ollama 0.15.0. Using hf.co/unsloth/Qwen3-VL-8B-Thinking-GGUF:Q6_K. The Q4 version from ollama.com works fine, but I specifically want the Q6 quant. The issue also applies to hf.co/unsloth/Qwen3-VL-32B-Thinking-GGUF:UD-Q4_K_XL. Decreasing num_batch, num_gpu, num_ctx,, flash attention, KV cache, and hipblaslt don't work. Don't have time to file a real bug report right now. Already spent too much time debugging other peoples' crap.

Sign in to join this conversation.

Branches Tags

main

hoyyeva/anthropic-local-image-path

dhiltgen/ci

dhiltgen/llama-runner

parth-remove-claude-desktop-launch

hoyyeva/anthropic-reference-images-path

parth-anthropic-reference-images-path

brucemacd/download-before-remove

hoyyeva/editor-config-repair

parth-mlx-decode-checkpoints

parth-launch-codex-app

hoyyeva/fix-codex-model-metadata-warning

hoyyeva/qwen

parth/hide-claude-desktop-till-release

hoyyeva/opencode-image-modality

parth-add-claude-code-autoinstall

release_v0.22.0

pdevine/manifest-list

codex/fix-codex-model-metadata-warning

pdevine/addressable-manifest

brucemacd/launch-fetch-reccomended

jmorganca/llama-compat

launch-copilot-cli

hoyyeva/opencode-thinking

release_v0.20.7

parth-auto-save-backup

parth-test

jmorganca/gemma4-audio-replacements

fix-manifest-digest-on-pull

hoyyeva/vscode-improve

brucemacd/install-server-wait

parth/update-claude-docs

brucemac/start-ap-install

pdevine/mlx-update

pdevine/qwen35_vision

drifkin/api-show-fallback

mintlify/image-generation-1773352582

hoyyeva/server-context-length-local-config

jmorganca/faster-reptition-penalties

jmorganca/convert-nemotron

parth-pi-thinking

pdevine/sampling-penalties

jmorganca/fix-create-quantization-memory

dongchen/resumable_transfer_fix

pdevine/sampling-cache-error

jessegross/mlx-usage

hoyyeva/openclaw-config

hoyyeva/app-html

pdevine/qwen3next

brucemacd/sign-sh-install

brucemacd/tui-update

brucemacd/usage-api

jmorganca/launch-empty

fix-app-dist-embed

mxyng/mlx-compile

mxyng/mlx-quant

mxyng/mlx-glm4.7

mxyng/mlx

brucemacd/simplify-model-picker

jmorganca/qwen3-concurrent

fix-glm-4.7-flash-mla-config

drifkin/qwen3-coder-opening-tag

brucemacd/usage-cli

fix-cuda12-fattn-shmem

ollama-imagegen-docs

parth/fix-multiline-inputs

brucemacd/config-docs

mxyng/model-files

mxyng/simple-execute

fix-imagegen-ollama-models

mxyng/async-upload

jmorganca/lazy-no-dtype-changes

imagegen-auto-detect-create

parth/decrease-concurrent-download-hf

fix-mlx-quantize-init

jmorganca/x-cleanup

usage

imagegen-readme

jmorganca/glm-image

mlx-gpu-cd

jmorganca/imagegen-modelfile

parth/agent-skills

parth/agent-allowlist

parth/signed-in-offline

parth/agents

parth/fix-context-chopping

improve-cloud-flow

parth/add-models-websearch

parth/prompt-renderer-mcp

jmorganca/native-settings

jmorganca/download-stream-hash

jmorganca/client2-rebased

brucemacd/oai-chat-req-multipart

jessegross/multi_chunk_reserve

grace/additional-omit-empty

grace/mistral-3-large

mxyng/tokenizer2

mxyng/tokenizer

jessegross/flash

hoyyeva/windows-nacked-app

mxyng/cleanup-attention

grace/deepseek-parser

hoyyeva/remember-unsent-prompt

parth/add-lfs-pointer-error-conversion

parth/olmo2-test2

hoyyeva/ollama-launchagent-plist

nicole/olmo-model

parth/olmo-test

mxyng/remove-embedded

parth/render-template

jmorganca/intellect-3

parth/remove-prealloc-linter

jmorganca/cmd-eval

nicole/nomic-embed-text-fix

mxyng/lint-2

hoyyeva/add-gemini-3-pro-preview

hoyyeva/load-model-list

mxyng/expand-path

mxyng/environ-2

hoyyeva/deeplink-json-encoding

parth/improve-tool-calling-tests

hoyyeva/conversation

hoyyeva/assistant-edit-response

hoyyeva/thinking

origin/brucemacd/invalid-char-i-err

parth/improve-tool-calling

jmorganca/required-omitempty

grace/qwen3-vl-tests

mxyng/iter-client

parth/docs-readme

nicole/embed-test

pdevine/integration-benchstat

parth/remove-generate-cmd

parth/add-toolcall-id

mxyng/server-tests

jmorganca/glm-4.6

jmorganca/gin-h-compat

drifkin/stable-tool-args

pdevine/qwen3-more-thinking

parth/add-websearch-client

nicole/websearch_local

jmorganca/qwen3-coder-updates

grace/deepseek-v3-migration-tests

mxyng/fix-create

jmorganca/cloud-errors

pdevine/parser-tidy

revert-12233-parth/simplify-entrypoints-runner

parth/enable-so-gpt-oss

brucemacd/qwen3vl

jmorganca/readme-simplify

parth/gpt-oss-structured-outputs

revert-12039-jmorganca/tools-braces

mxyng/embeddings

mxyng/gguf

mxyng/benchmark

mxyng/types-null

parth/move-parsing

mxyng/gemma2

jmorganca/docs

mxyng/16-bit

mxyng/create-stdin

pdevine/authorizedkeys

mxyng/quant

parth/opt-in-error-context-window

brucemacd/cache-models

brucemacd/runner-completion

jmorganca/llama-update-6

brucemacd/benchmark-list

brucemacd/partial-read-caps

parth/deepseek-r1-tools

mxyng/omit-array

parth/tool-prefix-temp

brucemacd/runner-test

jmorganca/qwen25vl

brucemacd/model-forward-test-ext

parth/python-function-parsing

jmorganca/cuda-compression-none

drifkin/num-parallel

drifkin/chat-truncation-fix

jmorganca/sync

parth/python-tools-calling

drifkin/array-head-count

brucemacd/create-no-loop

parth/server-enable-content-stream-with-tools

qwen25omni

mxyng/v3

brucemacd/ropeconfig

jmorganca/silence-tokenizer

parth/sample-so-test

parth/sampling-structured-outputs

brucemacd/doc-go-engine

parth/constrained-sampling-json

jmorganca/mistral-wip

brucemacd/mistral-small-convert

parth/sample-unmarshal-json-for-params

brucemacd/jomorganca/mistral

pdevine/bfloat16

jmorganca/mistral

brucemacd/mistral

pdevine/logging

parth/sample-correctness-fix

parth/sample-fix-sorting

jmorgan/sample-fix-sorting-extras

jmorganca/temp-0-images

brucemacd/parallel-embed-models

brucemacd/shim-grammar

jmorganca/fix-gguf-error

bmizerany/nameswork

jmorganca/faster-releases

bmizerany/validatenames

brucemacd/err-no-vocab

brucemacd/rope-config

brucemacd/err-hint

brucemacd/qwen2_5

brucemacd/logprobs

brucemacd/new_runner_graph_bench

progress-flicker

brucemacd/forward-test

brucemacd/go_qwen2

pdevine/gemma2

jmorganca/add-missing-symlink-eval

mxyng/next-debug

parth/set-context-size-openai

brucemacd/next-bpe-bench

brucemacd/next-bpe-test

brucemacd/new_runner_e2e

brucemacd/new_runner_qwen2

pdevine/convert-cohere2

brucemacd/convert-cli

parth/log-probs

mxyng/next-mlx

mxyng/cmd-history

parth/templating

parth/tokenize-detokenize

brucemacd/check-key-register

bmizerany/grammar

jmorganca/vendor-081b29bd

mxyng/func-checks

jmorganca/fix-null-format

parth/fix-default-to-warn-json

jmorganca/qwen2vl

jmorganca/no-concat

parth/cmd-cleanup-SO

brucemacd/check-key-register-structured-err

parth/openai-stream-usage

parth/fix-referencing-so

stream-tools-stop

jmorganca/degin-1

brucemacd/install-path-clean

brucemacd/push-name-validation

brucemacd/browser-key-register

jmorganca/openai-fix-first-message

jmorganca/fix-proxy

jessegross/sample

parth/disallow-streaming-tools

dhiltgen/remove_submodule

jmorganca/ga

jmorganca/mllama

pdevine/newlines

pdevine/geems-2b

jmorganca/llama-bump

mxyng/modelname-7

mxyng/gin-slog

mxyng/modelname-6

jyan/convert-prog

jyan/quant5

paligemma-support

pdevine/import-docs

jmorganca/openai-context

jyan/paligemma

jyan/p2

jyan/palitest

bmizerany/embedspeedup

jmorganca/llama-vit

brucemacd/allow-ollama

royh/ep-methods

royh/whisper

mxyng/api-models

mxyng/fix-memory

jyan/q4_4/8

jyan/ollama-v

royh/stream-tools

roy-embed-parallel

bmizerany/hrm

revert-5963-revert-5924-mxyng/llama3.1-rope

royh/embed-viz

jyan/local2

jyan/auth

jyan/local

jyan/parse-temp

jmorganca/template-mistral

jyan/reord-g

royh-openai-suffixdocs

royh-imgembed

royh-embed-parallel

jyan/quant4

royh-precision

jyan/progress

pdevine/fix-template

jyan/quant3

pdevine/ggla

mxyng/update-registry-domain

jmorganca/ggml-static

mxyng/create-context

jyan/v0.146

mxyng/layers-from-files

build_dist

bmizerany/noseek

royh-ls

royh-name

timeout

mxyng/server-timestamp

bmizerany/nosillyggufslurps

royh-params

jmorganca/llama-cpp-7c26775

royh-openai-delete

royh-show-rigid

jmorganca/enable-fa

jmorganca/no-error-template

jyan/format

royh-testdelete

bmizerany/fastverify

language_support

pdevine/ps-glitches

brucemacd/tokenize

bruce/iq-quants

bmizerany/filepathwithcoloninhost

mxyng/split-bin

bmizerany/client-registry

jmorganca/if-none-match

native

jmorganca/native

jmorganca/batch-embeddings

jmorganca/initcmake

jmorganca/mm

pdevine/showggmlinfo

modenameenforcealphanum

bmizerany/modenameenforcealphanum

jmorganca/done-reason

jmorganca/llama-cpp-8960fe8

ollama.com

bmizerany/filepathnobuild

bmizerany/types/model/defaultfix

rmdisplaylong

nogogen

bmizerany/x

modelfile-readme

bmizerany/replacecolon

jmorganca/limit

jmorganca/execstack

jmorganca/replace-assets

mxyng/tune-concurrency

jmorganca/testing

whitespace-detection

jmorganca/options

upgrade-all

scratch

cuda-search

mattw/airenamer

mattw/allmodelsonhuggingface

mattw/quantcontext

mattw/whatneedstorun

brucemacd/llama-mem-calc

mattw/faq-context

mattw/communitylinks

mattw/noprune

mattw/python-functioncalling

rename

mxyng/install

pulse

remove-first

editor

mattw/selfqueryingretrieval

cgo

mattw/howtoquant

api

matt/streamingapi

format-config

mxyng/extra-args

shell

update-nous-hermes

cp-model

upload-progress

fix-unknown-model

fix-model-names

delete-fix

insecure-registry

ls

deletemodels

progressbar

readme-updates

license-layers

skip-list

list-models

modelpath

matt/examplemodelfiles

distribution

go-opts

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/ollama#70969