compiled llama.cpp from main on 2024-09-26 and error when loading model
Traceback (most recent call last):
File "/home/user/text-generation-webui/modules/ui_model_menu.py", line 231, in load_model_wrapper
shared.model, shared.tokenizer = load_model(selected_model, loader)
File "/home/user/text-generation-webui/modules/models.py", line 93, in load_model
output = load_func_maploader
File "/home/user/text-generation-webui/modules/models.py", line 278, in llamacpp_loader
model, tokenizer = LlamaCppModel.from_pretrained(model_file)
File "/home/user/text-generation-webui/modules/llamacpp_model.py", line 85, in from_pretrained
result.model = Llama(**params)
File "/home/user/miniconda3/envs/textgen/lib/python3.10/site-packages/llama_cpp_cuda_tensorcores/llama.py", line 392, in init
_LlamaContext(
File "/home/user/miniconda3/envs/textgen/lib/python3.10/site-packages/llama_cpp_cuda_tensorcores/_internals.py", line 298, in init
raise ValueError("Failed to create llama_context")
ValueError: Failed to create llama_context
it looks like you're in text-gen-webui which i think uses llama-cpp-python, not llama.cpp
I get this and I am running on llamafile with llama.cpp
warning: couldn't find nvcc (nvidia c compiler) try setting $CUDA_PATH if it's installed
prebuilt binary /zip/ggml-cuda.so not found
{"timestamp":1727533861,"level":"INFO","function":"main","line":2669,"message":"build info","build":1500,"commit":"a30b324"}
{"timestamp":1727533861,"level":"INFO","function":"main","line":2672,"message":"system info","n_threads":4,"n_threads_batch":-1,"total_threads":8,"system_info":"AVX = 1 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | "}
Multi Modal Mode Enabledclip_model_load: model name: openai/clip-vit-large-patch14-336
clip_model_load: description: image encoder for LLaVA
clip_model_load: GGUF version: 3
clip_model_load: alignment: 32
clip_model_load: n_tensors: 377
clip_model_load: n_kv: 19
clip_model_load: ftype: q4_0
clip_model_load: text_encoder: 0
clip_model_load: vision_encoder: 1
clip_model_load: llava_projector: 1
clip_model_load: model size: 169.33 MB
clip_model_load: metadata size: 0.15 MB
clip_model_load: total allocated memory: 196.02 MB
llama_model_loader: loaded meta data with 35 key-value pairs and 255 tensors from /home/jim/text-generation-webui/models/Llama-3.2-3B-Instruct-Q8_0.gguf (version GGUF V3 (latest))
llama_model_loader: - tensor 0: rope_freqs.weight f32 [ 64, 1, 1, 1 ]
llama_model_loader: - tensor 1: token_embd.weight q8_0 [ 3072, 128256, 1, 1 ]
llama_model_loader: - tensor 2: blk.0.attn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 3: blk.0.ffn_down.weight q8_0 [ 8192, 3072, 1, 1 ]
llama_model_loader: - tensor 4: blk.0.ffn_gate.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 5: blk.0.ffn_up.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 6: blk.0.ffn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 7: blk.0.attn_k.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 8: blk.0.attn_output.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 9: blk.0.attn_q.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 10: blk.0.attn_v.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 11: blk.1.attn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 12: blk.1.ffn_down.weight q8_0 [ 8192, 3072, 1, 1 ]
llama_model_loader: - tensor 13: blk.1.ffn_gate.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 14: blk.1.ffn_up.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 15: blk.1.ffn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 16: blk.1.attn_k.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 17: blk.1.attn_output.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 18: blk.1.attn_q.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 19: blk.1.attn_v.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 20: blk.10.attn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 21: blk.10.ffn_down.weight q8_0 [ 8192, 3072, 1, 1 ]
llama_model_loader: - tensor 22: blk.10.ffn_gate.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 23: blk.10.ffn_up.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 24: blk.10.ffn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 25: blk.10.attn_k.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 26: blk.10.attn_output.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 27: blk.10.attn_q.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 28: blk.10.attn_v.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 29: blk.11.attn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 30: blk.11.ffn_down.weight q8_0 [ 8192, 3072, 1, 1 ]
llama_model_loader: - tensor 31: blk.11.ffn_gate.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 32: blk.11.ffn_up.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 33: blk.11.ffn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 34: blk.11.attn_k.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 35: blk.11.attn_output.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 36: blk.11.attn_q.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 37: blk.11.attn_v.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 38: blk.12.attn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 39: blk.12.ffn_down.weight q8_0 [ 8192, 3072, 1, 1 ]
llama_model_loader: - tensor 40: blk.12.ffn_gate.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 41: blk.12.ffn_up.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 42: blk.12.ffn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 43: blk.12.attn_k.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 44: blk.12.attn_output.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 45: blk.12.attn_q.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 46: blk.12.attn_v.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 47: blk.13.attn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 48: blk.13.ffn_down.weight q8_0 [ 8192, 3072, 1, 1 ]
llama_model_loader: - tensor 49: blk.13.ffn_gate.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 50: blk.13.ffn_up.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 51: blk.13.ffn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 52: blk.13.attn_k.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 53: blk.13.attn_output.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 54: blk.13.attn_q.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 55: blk.13.attn_v.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 56: blk.14.attn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 57: blk.14.ffn_down.weight q8_0 [ 8192, 3072, 1, 1 ]
llama_model_loader: - tensor 58: blk.14.ffn_gate.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 59: blk.14.ffn_up.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 60: blk.14.ffn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 61: blk.14.attn_k.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 62: blk.14.attn_output.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 63: blk.14.attn_q.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 64: blk.14.attn_v.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 65: blk.15.attn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 66: blk.15.ffn_down.weight q8_0 [ 8192, 3072, 1, 1 ]
llama_model_loader: - tensor 67: blk.15.ffn_gate.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 68: blk.15.ffn_up.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 69: blk.15.ffn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 70: blk.15.attn_k.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 71: blk.15.attn_output.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 72: blk.15.attn_q.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 73: blk.15.attn_v.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 74: blk.16.attn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 75: blk.16.ffn_down.weight q8_0 [ 8192, 3072, 1, 1 ]
llama_model_loader: - tensor 76: blk.16.ffn_gate.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 77: blk.16.ffn_up.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 78: blk.16.ffn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 79: blk.16.attn_k.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 80: blk.16.attn_output.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 81: blk.16.attn_q.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 82: blk.16.attn_v.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 83: blk.17.attn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 84: blk.17.ffn_down.weight q8_0 [ 8192, 3072, 1, 1 ]
llama_model_loader: - tensor 85: blk.17.ffn_gate.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 86: blk.17.ffn_up.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 87: blk.17.ffn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 88: blk.17.attn_k.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 89: blk.17.attn_output.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 90: blk.17.attn_q.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 91: blk.17.attn_v.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 92: blk.18.attn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 93: blk.18.ffn_down.weight q8_0 [ 8192, 3072, 1, 1 ]
llama_model_loader: - tensor 94: blk.18.ffn_gate.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 95: blk.18.ffn_up.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 96: blk.18.ffn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 97: blk.18.attn_k.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 98: blk.18.attn_output.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 99: blk.18.attn_q.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 100: blk.18.attn_v.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 101: blk.19.attn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 102: blk.19.ffn_down.weight q8_0 [ 8192, 3072, 1, 1 ]
llama_model_loader: - tensor 103: blk.19.ffn_gate.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 104: blk.19.ffn_up.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 105: blk.19.ffn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 106: blk.19.attn_k.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 107: blk.19.attn_output.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 108: blk.19.attn_q.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 109: blk.19.attn_v.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 110: blk.2.attn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 111: blk.2.ffn_down.weight q8_0 [ 8192, 3072, 1, 1 ]
llama_model_loader: - tensor 112: blk.2.ffn_gate.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 113: blk.2.ffn_up.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 114: blk.2.ffn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 115: blk.2.attn_k.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 116: blk.2.attn_output.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 117: blk.2.attn_q.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 118: blk.2.attn_v.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 119: blk.20.ffn_gate.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 120: blk.20.ffn_up.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 121: blk.20.attn_k.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 122: blk.20.attn_output.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 123: blk.20.attn_q.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 124: blk.20.attn_v.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 125: blk.3.attn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 126: blk.3.ffn_down.weight q8_0 [ 8192, 3072, 1, 1 ]
llama_model_loader: - tensor 127: blk.3.ffn_gate.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 128: blk.3.ffn_up.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 129: blk.3.ffn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 130: blk.3.attn_k.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 131: blk.3.attn_output.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 132: blk.3.attn_q.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 133: blk.3.attn_v.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 134: blk.4.attn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 135: blk.4.ffn_down.weight q8_0 [ 8192, 3072, 1, 1 ]
llama_model_loader: - tensor 136: blk.4.ffn_gate.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 137: blk.4.ffn_up.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 138: blk.4.ffn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 139: blk.4.attn_k.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 140: blk.4.attn_output.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 141: blk.4.attn_q.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 142: blk.4.attn_v.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 143: blk.5.attn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 144: blk.5.ffn_down.weight q8_0 [ 8192, 3072, 1, 1 ]
llama_model_loader: - tensor 145: blk.5.ffn_gate.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 146: blk.5.ffn_up.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 147: blk.5.ffn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 148: blk.5.attn_k.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 149: blk.5.attn_output.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 150: blk.5.attn_q.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 151: blk.5.attn_v.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 152: blk.6.attn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 153: blk.6.ffn_down.weight q8_0 [ 8192, 3072, 1, 1 ]
llama_model_loader: - tensor 154: blk.6.ffn_gate.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 155: blk.6.ffn_up.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 156: blk.6.ffn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 157: blk.6.attn_k.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 158: blk.6.attn_output.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 159: blk.6.attn_q.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 160: blk.6.attn_v.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 161: blk.7.attn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 162: blk.7.ffn_down.weight q8_0 [ 8192, 3072, 1, 1 ]
llama_model_loader: - tensor 163: blk.7.ffn_gate.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 164: blk.7.ffn_up.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 165: blk.7.ffn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 166: blk.7.attn_k.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 167: blk.7.attn_output.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 168: blk.7.attn_q.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 169: blk.7.attn_v.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 170: blk.8.attn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 171: blk.8.ffn_down.weight q8_0 [ 8192, 3072, 1, 1 ]
llama_model_loader: - tensor 172: blk.8.ffn_gate.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 173: blk.8.ffn_up.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 174: blk.8.ffn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 175: blk.8.attn_k.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 176: blk.8.attn_output.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 177: blk.8.attn_q.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 178: blk.8.attn_v.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 179: blk.9.attn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 180: blk.9.ffn_down.weight q8_0 [ 8192, 3072, 1, 1 ]
llama_model_loader: - tensor 181: blk.9.ffn_gate.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 182: blk.9.ffn_up.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 183: blk.9.ffn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 184: blk.9.attn_k.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 185: blk.9.attn_output.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 186: blk.9.attn_q.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 187: blk.9.attn_v.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 188: blk.20.attn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 189: blk.20.ffn_down.weight q8_0 [ 8192, 3072, 1, 1 ]
llama_model_loader: - tensor 190: blk.20.ffn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 191: blk.21.attn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 192: blk.21.ffn_down.weight q8_0 [ 8192, 3072, 1, 1 ]
llama_model_loader: - tensor 193: blk.21.ffn_gate.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 194: blk.21.ffn_up.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 195: blk.21.ffn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 196: blk.21.attn_k.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 197: blk.21.attn_output.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 198: blk.21.attn_q.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 199: blk.21.attn_v.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 200: blk.22.attn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 201: blk.22.ffn_down.weight q8_0 [ 8192, 3072, 1, 1 ]
llama_model_loader: - tensor 202: blk.22.ffn_gate.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 203: blk.22.ffn_up.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 204: blk.22.ffn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 205: blk.22.attn_k.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 206: blk.22.attn_output.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 207: blk.22.attn_q.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 208: blk.22.attn_v.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 209: blk.23.attn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 210: blk.23.ffn_down.weight q8_0 [ 8192, 3072, 1, 1 ]
llama_model_loader: - tensor 211: blk.23.ffn_gate.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 212: blk.23.ffn_up.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 213: blk.23.ffn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 214: blk.23.attn_k.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 215: blk.23.attn_output.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 216: blk.23.attn_q.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 217: blk.23.attn_v.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 218: blk.24.attn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 219: blk.24.ffn_down.weight q8_0 [ 8192, 3072, 1, 1 ]
llama_model_loader: - tensor 220: blk.24.ffn_gate.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 221: blk.24.ffn_up.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 222: blk.24.ffn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 223: blk.24.attn_k.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 224: blk.24.attn_output.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 225: blk.24.attn_q.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 226: blk.24.attn_v.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 227: blk.25.attn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 228: blk.25.ffn_down.weight q8_0 [ 8192, 3072, 1, 1 ]
llama_model_loader: - tensor 229: blk.25.ffn_gate.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 230: blk.25.ffn_up.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 231: blk.25.ffn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 232: blk.25.attn_k.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 233: blk.25.attn_output.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 234: blk.25.attn_q.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 235: blk.25.attn_v.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 236: blk.26.attn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 237: blk.26.ffn_down.weight q8_0 [ 8192, 3072, 1, 1 ]
llama_model_loader: - tensor 238: blk.26.ffn_gate.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 239: blk.26.ffn_up.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 240: blk.26.ffn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 241: blk.26.attn_k.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 242: blk.26.attn_output.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 243: blk.26.attn_q.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 244: blk.26.attn_v.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 245: blk.27.attn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 246: blk.27.ffn_down.weight q8_0 [ 8192, 3072, 1, 1 ]
llama_model_loader: - tensor 247: blk.27.ffn_gate.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 248: blk.27.ffn_up.weight q8_0 [ 3072, 8192, 1, 1 ]
llama_model_loader: - tensor 249: blk.27.ffn_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: - tensor 250: blk.27.attn_k.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 251: blk.27.attn_output.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 252: blk.27.attn_q.weight q8_0 [ 3072, 3072, 1, 1 ]
llama_model_loader: - tensor 253: blk.27.attn_v.weight q8_0 [ 3072, 1024, 1, 1 ]
llama_model_loader: - tensor 254: output_norm.weight f32 [ 3072, 1, 1, 1 ]
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv 0: general.architecture str = llama
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = Llama 3.2 3B Instruct
llama_model_loader: - kv 3: general.finetune str = Instruct
llama_model_loader: - kv 4: general.basename str = Llama-3.2
llama_model_loader: - kv 5: general.size_label str = 3B
llama_model_loader: - kv 6: general.license str = llama3.2
llama_model_loader: - kv 7: general.tags arr[str,6] = ["facebook", "meta", "pytorch", "llam...
llama_model_loader: - kv 8: general.languages arr[str,8] = ["en", "de", "fr", "it", "pt", "hi", ...
llama_model_loader: - kv 9: llama.block_count u32 = 28
llama_model_loader: - kv 10: llama.context_length u32 = 131072
llama_model_loader: - kv 11: llama.embedding_length u32 = 3072
llama_model_loader: - kv 12: llama.feed_forward_length u32 = 8192
llama_model_loader: - kv 13: llama.attention.head_count u32 = 24
llama_model_loader: - kv 14: llama.attention.head_count_kv u32 = 8
llama_model_loader: - kv 15: llama.rope.freq_base f32 = 500000.000000
llama_model_loader: - kv 16: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 17: llama.attention.key_length u32 = 128
llama_model_loader: - kv 18: llama.attention.value_length u32 = 128
llama_model_loader: - kv 19: general.file_type u32 = 7
llama_model_loader: - kv 20: llama.vocab_size u32 = 128256
llama_model_loader: - kv 21: llama.rope.dimension_count u32 = 128
llama_model_loader: - kv 22: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 23: tokenizer.ggml.pre str = llama-bpe
llama_model_loader: - kv 24: tokenizer.ggml.tokens arr[str,128256] = ["!", """, "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 25: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 26: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
llama_model_loader: - kv 27: tokenizer.ggml.bos_token_id u32 = 128000
llama_model_loader: - kv 28: tokenizer.ggml.eos_token_id u32 = 128009
llama_model_loader: - kv 29: tokenizer.chat_template str = {{- bos_token }}\n{%- if custom_tools ...
llama_model_loader: - kv 30: general.quantization_version u32 = 2
llama_model_loader: - kv 31: quantize.imatrix.file str = /models_out/Llama-3.2-3B-Instruct-GGU...
llama_model_loader: - kv 32: quantize.imatrix.dataset str = /training_dir/calibration_datav3.txt
llama_model_loader: - kv 33: quantize.imatrix.entries_count i32 = 196
llama_model_loader: - kv 34: quantize.imatrix.chunks_count i32 = 125
llama_model_loader: - type f32: 58 tensors
llama_model_loader: - type q8_0: 197 tensors
llm_load_vocab: special tokens definition check successful ( 256/128256 ).
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = llama
llm_load_print_meta: vocab type = BPE
llm_load_print_meta: n_vocab = 128256
llm_load_print_meta: n_merges = 280147
llm_load_print_meta: n_ctx_train = 131072
llm_load_print_meta: n_embd = 3072
llm_load_print_meta: n_head = 24
llm_load_print_meta: n_head_kv = 8
llm_load_print_meta: n_layer = 28
llm_load_print_meta: n_rot = 128
llm_load_print_meta: n_gqa = 3
llm_load_print_meta: f_norm_eps = 0.0e+00
llm_load_print_meta: f_norm_rms_eps = 1.0e-05
llm_load_print_meta: f_clamp_kqv = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: n_ff = 8192
llm_load_print_meta: n_expert = 0
llm_load_print_meta: n_expert_used = 0
llm_load_print_meta: rope scaling = linear
llm_load_print_meta: freq_base_train = 500000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_yarn_orig_ctx = 131072
llm_load_print_meta: rope_finetuned = unknown
llm_load_print_meta: model type = ?B
llm_load_print_meta: model ftype = mostly Q8_0
llm_load_print_meta: model params = 3.21 B
llm_load_print_meta: model size = 3.18 GiB (8.50 BPW)
llm_load_print_meta: general.name = Llama 3.2 3B Instruct
llm_load_print_meta: BOS token = 128000 '<|begin_of_text|>'
llm_load_print_meta: EOS token = 128009 '<|eot_id|>'
llm_load_print_meta: LF token = 128 'Ä'
llm_load_tensors: ggml ctx size = 0.10 MiB
error: create_tensor: tensor 'output.weight' not found
... while loading Llama-3.2-3B-Instruct-Q8_0.gguf
I did manage to get the Llama 3.2 version to work with an updated ollama (using ollama's command- ollama run llama3.2) but that is their model version.
why does it look like you're trying to load a vision model..? it looks like it's mentioning openai clip
also concerned by
warning: couldn't find nvcc (nvidia c compiler) try setting $CUDA_PATH if it's installed
prebuilt binary /zip/ggml-cuda.so not found
can you run any other models?
I did manage to get the Llama 3.2 version to work with an updated ollama (using ollama's command- ollama run llama3.2) but that is their model version.
The llama.cpp base used by llamafile is outdated, from a month ago. It doesn't support tied embedding-output weights (in the llama architecture), which is why you're getting this error (GGUFs generated by newer versions of llama.cpp omit the output tensor to match this change).