API tools faq
paste
Guest User

ollama-debug-0.1.25.log

a guest
Feb 14th, 2024
132
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 8.27 KB | Software | 0 0
raw download clone embed print report
  1. time=2024-02-14T15:28:26.549-05:00 level=INFO source=images.go:706 msg="total blobs: 6"
  2. time=2024-02-14T15:28:26.549-05:00 level=INFO source=images.go:713 msg="total unused blobs removed: 0"
  3. time=2024-02-14T15:28:26.549-05:00 level=INFO source=routes.go:1014 msg="Listening on 127.0.0.1:11434 (version 0.1.25)"
  4. time=2024-02-14T15:28:26.549-05:00 level=INFO source=payload_common.go:107 msg="Extracting dynamic libraries..."
  5. time=2024-02-14T15:28:29.610-05:00 level=INFO source=payload_common.go:146 msg="Dynamic LLM libraries [cpu cpu_avx rocm cpu_avx2 cuda_v12]"
  6. time=2024-02-14T15:28:29.610-05:00 level=INFO source=gpu.go:94 msg="Detecting GPU type"
  7. time=2024-02-14T15:28:29.610-05:00 level=INFO source=gpu.go:262 msg="Searching for GPU management library libnvidia-ml.so"
  8. time=2024-02-14T15:28:29.611-05:00 level=INFO source=gpu.go:308 msg="Discovered GPU libraries: [/nix/store/z6557r7pgvmxr9x16a4ffazly8dflh65-nvidia-x11-545.29.06-6.1.77/lib/libnvidia-ml.so.545.29.06]"
  9. time=2024-02-14T15:28:29.629-05:00 level=INFO source=gpu.go:320 msg="Unable to load CUDA management library /nix/store/z6557r7pgvmxr9x16a4ffazly8dflh65-nvidia-x11-545.29.06-6.1.77/lib/libnvidia-ml.so.545.29.06: nvml vram init failure: 9"
  10. time=2024-02-14T15:28:29.629-05:00 level=INFO source=gpu.go:262 msg="Searching for GPU management library librocm_smi64.so"
  11. time=2024-02-14T15:28:29.629-05:00 level=INFO source=gpu.go:308 msg="Discovered GPU libraries: [/nix/store/146j4sd2z0miywgn0ggydfhcc8zmhxad-rocm-smi-5.7.1/lib/librocm_smi64.so.5.0]"
  12. time=2024-02-14T15:28:29.631-05:00 level=INFO source=gpu.go:109 msg="Radeon GPU detected"
  13. time=2024-02-14T15:28:29.631-05:00 level=INFO source=cpu_common.go:11 msg="CPU has AVX2"
  14. time=2024-02-14T15:28:29.631-05:00 level=INFO source=routes.go:1037 msg="no GPU detected"
  15. [GIN] 2024/02/14 - 15:28:33 | 200 | 20.929µs | 127.0.0.1 | HEAD "/"
  16. [GIN] 2024/02/14 - 15:28:33 | 200 | 518.139µs | 127.0.0.1 | POST "/api/show"
  17. [GIN] 2024/02/14 - 15:28:33 | 200 | 158.313µs | 127.0.0.1 | POST "/api/show"
  18. time=2024-02-14T15:28:34.019-05:00 level=INFO source=cpu_common.go:11 msg="CPU has AVX2"
  19. time=2024-02-14T15:28:34.019-05:00 level=INFO source=cpu_common.go:11 msg="CPU has AVX2"
  20. time=2024-02-14T15:28:34.019-05:00 level=INFO source=llm.go:77 msg="GPU not available, falling back to CPU"
  21. time=2024-02-14T15:28:34.020-05:00 level=INFO source=dyn_ext_server.go:90 msg="Loading Dynamic llm server: /tmp/ollama1719630552/cpu_avx2/libext_server.so"
  22. time=2024-02-14T15:28:34.020-05:00 level=INFO source=dyn_ext_server.go:145 msg="Initializing llama server"
  23. llama_model_loader: loaded meta data with 24 key-value pairs and 995 tensors from /home/abysssol/.ollama/models/blobs/sha256:097a1ff4445ccc1e7668f70b9de3caa60cfc2a8e2cb9da3505b13854f1cfe20f (version GGUF V3 (latest))
  24. llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
  25. llama_model_loader: - kv 0: general.architecture str = llama
  26. llama_model_loader: - kv 1: general.name str = cognitivecomputations
  27. llama_model_loader: - kv 2: llama.context_length u32 = 32768
  28. llama_model_loader: - kv 3: llama.embedding_length u32 = 4096
  29. llama_model_loader: - kv 4: llama.block_count u32 = 32
  30. llama_model_loader: - kv 5: llama.feed_forward_length u32 = 14336
  31. llama_model_loader: - kv 6: llama.rope.dimension_count u32 = 128
  32. llama_model_loader: - kv 7: llama.attention.head_count u32 = 32
  33. llama_model_loader: - kv 8: llama.attention.head_count_kv u32 = 8
  34. llama_model_loader: - kv 9: llama.expert_count u32 = 8
  35. llama_model_loader: - kv 10: llama.expert_used_count u32 = 2
  36. llama_model_loader: - kv 11: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
  37. llama_model_loader: - kv 12: llama.rope.freq_base f32 = 1000000.000000
  38. llama_model_loader: - kv 13: general.file_type u32 = 2
  39. llama_model_loader: - kv 14: tokenizer.ggml.model str = llama
  40. llama_model_loader: - kv 15: tokenizer.ggml.tokens arr[str,32002] = ["<unk>", "<s>", "</s>", "<0x00>", "<...
  41. llama_model_loader: - kv 16: tokenizer.ggml.scores arr[f32,32002] = [0.000000, 0.000000, 0.000000, 0.0000...
  42. llama_model_loader: - kv 17: tokenizer.ggml.token_type arr[i32,32002] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
  43. llama_model_loader: - kv 18: tokenizer.ggml.bos_token_id u32 = 1
  44. llama_model_loader: - kv 19: tokenizer.ggml.eos_token_id u32 = 32000
  45. llama_model_loader: - kv 20: tokenizer.ggml.add_bos_token bool = true
  46. llama_model_loader: - kv 21: tokenizer.ggml.add_eos_token bool = false
  47. llama_model_loader: - kv 22: tokenizer.chat_template str = {% if not add_generation_prompt is de...
  48. llama_model_loader: - kv 23: general.quantization_version u32 = 2
  49. llama_model_loader: - type f32: 65 tensors
  50. llama_model_loader: - type f16: 32 tensors
  51. llama_model_loader: - type q4_0: 833 tensors
  52. llama_model_loader: - type q8_0: 64 tensors
  53. llama_model_loader: - type q6_K: 1 tensors
  54. llm_load_vocab: special tokens definition check successful ( 261/32002 ).
  55. llm_load_print_meta: format = GGUF V3 (latest)
  56. llm_load_print_meta: arch = llama
  57. llm_load_print_meta: vocab type = SPM
  58. llm_load_print_meta: n_vocab = 32002
  59. llm_load_print_meta: n_merges = 0
  60. llm_load_print_meta: n_ctx_train = 32768
  61. llm_load_print_meta: n_embd = 4096
  62. llm_load_print_meta: n_head = 32
  63. llm_load_print_meta: n_head_kv = 8
  64. llm_load_print_meta: n_layer = 32
  65. llm_load_print_meta: n_rot = 128
  66. llm_load_print_meta: n_embd_head_k = 128
  67. llm_load_print_meta: n_embd_head_v = 128
  68. llm_load_print_meta: n_gqa = 4
  69. llm_load_print_meta: n_embd_k_gqa = 1024
  70. llm_load_print_meta: n_embd_v_gqa = 1024
  71. llm_load_print_meta: f_norm_eps = 0.0e+00
  72. llm_load_print_meta: f_norm_rms_eps = 1.0e-05
  73. llm_load_print_meta: f_clamp_kqv = 0.0e+00
  74. llm_load_print_meta: f_max_alibi_bias = 0.0e+00
  75. llm_load_print_meta: n_ff = 14336
  76. llm_load_print_meta: n_expert = 8
  77. llm_load_print_meta: n_expert_used = 2
  78. llm_load_print_meta: rope scaling = linear
  79. llm_load_print_meta: freq_base_train = 1000000.0
  80. llm_load_print_meta: freq_scale_train = 1
  81. llm_load_print_meta: n_yarn_orig_ctx = 32768
  82. llm_load_print_meta: rope_finetuned = unknown
  83. llm_load_print_meta: model type = 7B
  84. llm_load_print_meta: model ftype = Q4_0
  85. llm_load_print_meta: model params = 46.70 B
  86. llm_load_print_meta: model size = 24.62 GiB (4.53 BPW)
  87. llm_load_print_meta: general.name = cognitivecomputations
  88. llm_load_print_meta: BOS token = 1 '<s>'
  89. llm_load_print_meta: EOS token = 32000 '<|im_end|>'
  90. llm_load_print_meta: UNK token = 0 '<unk>'
  91. llm_load_print_meta: LF token = 13 '<0x0A>'
  92. llm_load_tensors: ggml ctx size = 0.38 MiB
  93. llm_load_tensors: CPU buffer size = 25215.88 MiB
  94. ....................................................................................................
  95. llama_new_context_with_model: n_ctx = 2048
  96. llama_new_context_with_model: freq_base = 1000000.0
  97. llama_new_context_with_model: freq_scale = 1
  98. llama_kv_cache_init: CPU KV buffer size = 256.00 MiB
  99. llama_new_context_with_model: KV self size = 256.00 MiB, K (f16): 128.00 MiB, V (f16): 128.00 MiB
  100. llama_new_context_with_model: CPU input buffer size = 13.01 MiB
  101. llama_new_context_with_model: CPU compute buffer size = 180.03 MiB
  102. llama_new_context_with_model: graph splits (measure): 1
  103. time=2024-02-14T15:28:35.290-05:00 level=INFO source=dyn_ext_server.go:156 msg="Starting llama main loop"
  104. [GIN] 2024/02/14 - 15:28:35 | 200 | 1.345573721s | 127.0.0.1 | POST "/api/chat"
Tags: log Ollama
Advertisement
Add Comment
Please, Sign In to add comment
Public Pastes
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!