|
2023/11/07 19:20:47 images.go:824: total blobs: 11 |
|
2023/11/07 19:20:47 images.go:831: total unused blobs removed: 0 |
|
2023/11/07 19:20:47 routes.go:680: Listening on 127.0.0.1:11434 (version 0.1.8) |
|
[GIN] 2023/11/07 - 19:21:48 | 200 | 1.035598ms | 127.0.0.1 | HEAD "/" |
|
[GIN] 2023/11/07 - 19:21:48 | 200 | 5.39239ms | 127.0.0.1 | POST "/api/show" |
|
2023/11/07 19:21:48 llama.go:384: starting llama runner |
|
2023/11/07 19:21:48 llama.go:386: error starting the external llama runner: fork/exec /var/folders/8c/lmckjks95fj4h_jqzw4v3k_w0000gn/T/ollama3772859082/llama.cpp/gguf/build/metal/bin/ollama-runner: bad CPU type in executable |
|
2023/11/07 19:21:48 llama.go:384: starting llama runner |
|
2023/11/07 19:21:48 llama.go:442: waiting for llama runner to start responding |
|
{"timestamp":1699352509,"level":"WARNING","function":"server_params_parse","line":873,"message":"Not compiled with GPU offload support, --n-gpu-layers option will be ignored. See main README.md for information on enabling GPU BLAS support","n_gpu_layers":-1} |
|
{"timestamp":1699352509,"level":"INFO","function":"main","line":1324,"message":"build info","build":219,"commit":"9e70cc0"} |
|
{"timestamp":1699352509,"level":"INFO","function":"main","line":1330,"message":"system info","n_threads":2,"n_threads_batch":-1,"total_threads":4,"system_info":"AVX = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 0 | NEON = 0 | ARM_FMA = 0 | F16C = 0 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | "} |
|
llama_model_loader: loaded meta data with 19 key-value pairs and 237 tensors from /Users/admin/.ollama/models/blobs/sha256:66002b78c70a22ab25e16cc9a1736c6cc6335398c7312e3eb33db202350afe66 (version GGUF V2 (latest)) |
|
llama_model_loader: - tensor 0: token_embd.weight q4_0 [ 3200, 32000, 1, 1 ] |
|
llama_model_loader: - tensor 1: blk.0.attn_q.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 2: blk.0.attn_k.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 3: blk.0.attn_v.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 4: blk.0.attn_output.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 5: blk.0.ffn_gate.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 6: blk.0.ffn_down.weight q4_0 [ 8640, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 7: blk.0.ffn_up.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 8: blk.0.attn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 9: blk.0.ffn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 10: blk.1.attn_q.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 11: blk.1.attn_k.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 12: blk.1.attn_v.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 13: blk.1.attn_output.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 14: blk.1.ffn_gate.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 15: blk.1.ffn_down.weight q4_0 [ 8640, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 16: blk.1.ffn_up.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 17: blk.1.attn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 18: blk.1.ffn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 19: blk.2.attn_q.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 20: blk.2.attn_k.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 21: blk.2.attn_v.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 22: blk.2.attn_output.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 23: blk.2.ffn_gate.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 24: blk.2.ffn_down.weight q4_0 [ 8640, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 25: blk.2.ffn_up.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 26: blk.2.attn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 27: blk.2.ffn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 28: blk.3.attn_q.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 29: blk.3.attn_k.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 30: blk.3.attn_v.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 31: blk.3.attn_output.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 32: blk.3.ffn_gate.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 33: blk.3.ffn_down.weight q4_0 [ 8640, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 34: blk.3.ffn_up.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 35: blk.3.attn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 36: blk.3.ffn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 37: blk.4.attn_q.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 38: blk.4.attn_k.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 39: blk.4.attn_v.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 40: blk.4.attn_output.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 41: blk.4.ffn_gate.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 42: blk.4.ffn_down.weight q4_0 [ 8640, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 43: blk.4.ffn_up.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 44: blk.4.attn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 45: blk.4.ffn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 46: blk.5.attn_q.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 47: blk.5.attn_k.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 48: blk.5.attn_v.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 49: blk.5.attn_output.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 50: blk.5.ffn_gate.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 51: blk.5.ffn_down.weight q4_0 [ 8640, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 52: blk.5.ffn_up.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 53: blk.5.attn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 54: blk.5.ffn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 55: blk.6.attn_q.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 56: blk.6.attn_k.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 57: blk.6.attn_v.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 58: blk.6.attn_output.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 59: blk.6.ffn_gate.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 60: blk.6.ffn_down.weight q4_0 [ 8640, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 61: blk.6.ffn_up.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 62: blk.6.attn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 63: blk.6.ffn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 64: blk.7.attn_q.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 65: blk.7.attn_k.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 66: blk.7.attn_v.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 67: blk.7.attn_output.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 68: blk.7.ffn_gate.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 69: blk.7.ffn_down.weight q4_0 [ 8640, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 70: blk.7.ffn_up.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 71: blk.7.attn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 72: blk.7.ffn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 73: blk.8.attn_q.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 74: blk.8.attn_k.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 75: blk.8.attn_v.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 76: blk.8.attn_output.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 77: blk.8.ffn_gate.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 78: blk.8.ffn_down.weight q4_0 [ 8640, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 79: blk.8.ffn_up.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 80: blk.8.attn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 81: blk.8.ffn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 82: blk.9.attn_q.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 83: blk.9.attn_k.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 84: blk.9.attn_v.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 85: blk.9.attn_output.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 86: blk.9.ffn_gate.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 87: blk.9.ffn_down.weight q4_0 [ 8640, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 88: blk.9.ffn_up.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 89: blk.9.attn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 90: blk.9.ffn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 91: blk.10.attn_q.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 92: blk.10.attn_k.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 93: blk.10.attn_v.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 94: blk.10.attn_output.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 95: blk.10.ffn_gate.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 96: blk.10.ffn_down.weight q4_0 [ 8640, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 97: blk.10.ffn_up.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 98: blk.10.attn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 99: blk.10.ffn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 100: blk.11.attn_q.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 101: blk.11.attn_k.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 102: blk.11.attn_v.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 103: blk.11.attn_output.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 104: blk.11.ffn_gate.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 105: blk.11.ffn_down.weight q4_0 [ 8640, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 106: blk.11.ffn_up.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 107: blk.11.attn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 108: blk.11.ffn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 109: blk.12.attn_q.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 110: blk.12.attn_k.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 111: blk.12.attn_v.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 112: blk.12.attn_output.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 113: blk.12.ffn_gate.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 114: blk.12.ffn_down.weight q4_0 [ 8640, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 115: blk.12.ffn_up.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 116: blk.12.attn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 117: blk.12.ffn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 118: blk.13.attn_q.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 119: blk.13.attn_k.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 120: blk.13.attn_v.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 121: blk.13.attn_output.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 122: blk.13.ffn_gate.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 123: blk.13.ffn_down.weight q4_0 [ 8640, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 124: blk.13.ffn_up.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 125: blk.13.attn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 126: blk.13.ffn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 127: blk.14.attn_q.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 128: blk.14.attn_k.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 129: blk.14.attn_v.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 130: blk.14.attn_output.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 131: blk.14.ffn_gate.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 132: blk.14.ffn_down.weight q4_0 [ 8640, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 133: blk.14.ffn_up.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 134: blk.14.attn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 135: blk.14.ffn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 136: blk.15.attn_q.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 137: blk.15.attn_k.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 138: blk.15.attn_v.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 139: blk.15.attn_output.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 140: blk.15.ffn_gate.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 141: blk.15.ffn_down.weight q4_0 [ 8640, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 142: blk.15.ffn_up.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 143: blk.15.attn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 144: blk.15.ffn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 145: blk.16.attn_q.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 146: blk.16.attn_k.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 147: blk.16.attn_v.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 148: blk.16.attn_output.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 149: blk.16.ffn_gate.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 150: blk.16.ffn_down.weight q4_0 [ 8640, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 151: blk.16.ffn_up.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 152: blk.16.attn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 153: blk.16.ffn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 154: blk.17.attn_q.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 155: blk.17.attn_k.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 156: blk.17.attn_v.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 157: blk.17.attn_output.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 158: blk.17.ffn_gate.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 159: blk.17.ffn_down.weight q4_0 [ 8640, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 160: blk.17.ffn_up.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 161: blk.17.attn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 162: blk.17.ffn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 163: blk.18.attn_q.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 164: blk.18.attn_k.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 165: blk.18.attn_v.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 166: blk.18.attn_output.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 167: blk.18.ffn_gate.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 168: blk.18.ffn_down.weight q4_0 [ 8640, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 169: blk.18.ffn_up.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 170: blk.18.attn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 171: blk.18.ffn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 172: blk.19.attn_q.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 173: blk.19.attn_k.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 174: blk.19.attn_v.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 175: blk.19.attn_output.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 176: blk.19.ffn_gate.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 177: blk.19.ffn_down.weight q4_0 [ 8640, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 178: blk.19.ffn_up.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 179: blk.19.attn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 180: blk.19.ffn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 181: blk.20.attn_q.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 182: blk.20.attn_k.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 183: blk.20.attn_v.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 184: blk.20.attn_output.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 185: blk.20.ffn_gate.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 186: blk.20.ffn_down.weight q4_0 [ 8640, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 187: blk.20.ffn_up.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 188: blk.20.attn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 189: blk.20.ffn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 190: blk.21.attn_q.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 191: blk.21.attn_k.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 192: blk.21.attn_v.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 193: blk.21.attn_output.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 194: blk.21.ffn_gate.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 195: blk.21.ffn_down.weight q4_0 [ 8640, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 196: blk.21.ffn_up.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 197: blk.21.attn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 198: blk.21.ffn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 199: blk.22.attn_q.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 200: blk.22.attn_k.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 201: blk.22.attn_v.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 202: blk.22.attn_output.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 203: blk.22.ffn_gate.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 204: blk.22.ffn_down.weight q4_0 [ 8640, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 205: blk.22.ffn_up.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 206: blk.22.attn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 207: blk.22.ffn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 208: blk.23.attn_q.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 209: blk.23.attn_k.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 210: blk.23.attn_v.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 211: blk.23.attn_output.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 212: blk.23.ffn_gate.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 213: blk.23.ffn_down.weight q4_0 [ 8640, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 214: blk.23.ffn_up.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 215: blk.23.attn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 216: blk.23.ffn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 217: blk.24.attn_q.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 218: blk.24.attn_k.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 219: blk.24.attn_v.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 220: blk.24.attn_output.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 221: blk.24.ffn_gate.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 222: blk.24.ffn_down.weight q4_0 [ 8640, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 223: blk.24.ffn_up.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 224: blk.24.attn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 225: blk.24.ffn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 226: blk.25.attn_q.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 227: blk.25.attn_k.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 228: blk.25.attn_v.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 229: blk.25.attn_output.weight q4_0 [ 3200, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 230: blk.25.ffn_gate.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 231: blk.25.ffn_down.weight q4_0 [ 8640, 3200, 1, 1 ] |
|
llama_model_loader: - tensor 232: blk.25.ffn_up.weight q4_0 [ 3200, 8640, 1, 1 ] |
|
llama_model_loader: - tensor 233: blk.25.attn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 234: blk.25.ffn_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 235: output_norm.weight f32 [ 3200, 1, 1, 1 ] |
|
llama_model_loader: - tensor 236: output.weight q8_0 [ 3200, 32000, 1, 1 ] |
|
llama_model_loader: - kv 0: general.architecture str |
|
llama_model_loader: - kv 1: general.name str |
|
llama_model_loader: - kv 2: llama.context_length u32 |
|
llama_model_loader: - kv 3: llama.embedding_length u32 |
|
llama_model_loader: - kv 4: llama.block_count u32 |
|
llama_model_loader: - kv 5: llama.feed_forward_length u32 |
|
llama_model_loader: - kv 6: llama.rope.dimension_count u32 |
|
llama_model_loader: - kv 7: llama.attention.head_count u32 |
|
llama_model_loader: - kv 8: llama.attention.head_count_kv u32 |
|
llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 |
|
llama_model_loader: - kv 10: general.file_type u32 |
|
llama_model_loader: - kv 11: tokenizer.ggml.model str |
|
llama_model_loader: - kv 12: tokenizer.ggml.tokens arr |
|
llama_model_loader: - kv 13: tokenizer.ggml.scores arr |
|
llama_model_loader: - kv 14: tokenizer.ggml.token_type arr |
|
llama_model_loader: - kv 15: tokenizer.ggml.bos_token_id u32 |
|
llama_model_loader: - kv 16: tokenizer.ggml.eos_token_id u32 |
|
llama_model_loader: - kv 17: tokenizer.ggml.padding_token_id u32 |
|
llama_model_loader: - kv 18: general.quantization_version u32 |
|
llama_model_loader: - type f32: 53 tensors |
|
llama_model_loader: - type q4_0: 183 tensors |
|
llama_model_loader: - type q8_0: 1 tensors |
|
llm_load_vocab: special tokens definition check successful ( 259/32000 ). |
|
llm_load_print_meta: format = GGUF V2 (latest) |
|
llm_load_print_meta: arch = llama |
|
llm_load_print_meta: vocab type = SPM |
|
llm_load_print_meta: n_vocab = 32000 |
|
llm_load_print_meta: n_merges = 0 |
|
llm_load_print_meta: n_ctx_train = 2048 |
|
llm_load_print_meta: n_embd = 3200 |
|
llm_load_print_meta: n_head = 32 |
|
llm_load_print_meta: n_head_kv = 32 |
|
llm_load_print_meta: n_layer = 26 |
|
llm_load_print_meta: n_rot = 100 |
|
llm_load_print_meta: n_gqa = 1 |
|
llm_load_print_meta: f_norm_eps = 0.0e+00 |
|
llm_load_print_meta: f_norm_rms_eps = 1.0e-06 |
|
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 = 8640 |
|
llm_load_print_meta: freq_base_train = 10000.0 |
|
llm_load_print_meta: freq_scale_train = 1 |
|
llm_load_print_meta: model type = 3B |
|
llm_load_print_meta: model ftype = mostly Q4_0 |
|
llm_load_print_meta: model params = 3.43 B |
|
llm_load_print_meta: model size = 1.84 GiB (4.62 BPW) |
|
llm_load_print_meta: general.name = pankajmathur |
|
llm_load_print_meta: BOS token = 1 '<s>' |
|
llm_load_print_meta: EOS token = 2 '</s>' |
|
llm_load_print_meta: UNK token = 0 '<unk>' |
|
llm_load_print_meta: PAD token = 0 '<unk>' |
|
llm_load_print_meta: LF token = 13 '<0x0A>' |
|
llm_load_tensors: ggml ctx size = 0.08 MB |
|
llm_load_tensors: mem required = 1887.57 MB |
|
................ |
|
............................................. |
|
............... |
|
....... |
|
... |
|
........ |
|
llama_new_context_with_model: n_ctx = 2048 |
|
llama_new_context_with_model: freq_base = 10000.0 |
|
llama_new_context_with_model: freq_scale = 1 |
|
llama_new_context_with_model: kv self size = 650.00 MB |
|
llama_new_context_with_model: compute buffer total size = 156.88 MB |
|
llama server listening at http://127.0.0.1:55568 |
|
|
|
{"timestamp":1699352522,"level":"INFO","function":"main","line":1749,"message":"HTTP server listening","hostname":"127.0.0.1","port":55568} |
|
{"timestamp":1699352522,"level":"INFO","function":"log_server_request","line":1240,"message":"request","remote_addr":"127.0.0.1","remote_port":49743,"status":200,"method":"HEAD","path":"/","params":{}} |
|
2023/11/07 19:22:02 llama.go:456: llama runner started in 13.401789 seconds |
|
[GIN] 2023/11/07 - 19:22:02 | 200 | 13.791850245s | 127.0.0.1 | POST "/api/generate" |
|
{"timestamp":1699352526,"level":"INFO","function":"log_server_request","line":1240,"message":"request","remote_addr":"127.0.0.1","remote_port":49743,"status":200,"method":"HEAD","path":"/","params":{}} |
|
2023/11/07 19:22:06 llama.go:399: signal: segmentation fault |
|
2023/11/07 19:22:06 llama.go:473: llama runner stopped successfully |
|
[GIN] 2023/11/07 - 19:22:06 | 200 | 265.904241ms | 127.0.0.1 | POST "/api/generate" |
|
[GIN] 2023/11/07 - 19:22:37 | 200 | 17.588µs | 127.0.0.1 | HEAD "/" |
|
[GIN] 2023/11/07 - 19:22:37 | 200 | 1.539704ms | 127.0.0.1 | GET "/api/tags" |
|
2023/11/07 19:23:12 llama.go:473: llama runner stopped successfully |
|
2023/11/09 19:03:00 images.go:824: total blobs: 11 |
|
2023/11/09 19:03:00 images.go:831: total unused blobs removed: 0 |
|
2023/11/09 19:03:00 routes.go:680: Listening on 127.0.0.1:11434 (version 0.1.8) |