API tools faq
paste
Guest User

ollama Frontend

a guest
Feb 25th, 2025
58
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 11.14 KB | None | 0 0
raw download clone embed print report
  1. [GIN] 2025/02/25 - 12:44:50 | 200 | 57.179µs | 127.0.0.1 | HEAD "/"
  2. [GIN] 2025/02/25 - 12:44:50 | 200 | 22.143962ms | 127.0.0.1 | POST "/api/show"
  3. time=2025-02-25T12:44:50.346Z level=WARN source=ggml.go:132 msg="key not found" key=llama.attention.key_length default=128
  4. time=2025-02-25T12:44:50.347Z level=WARN source=ggml.go:132 msg="key not found" key=llama.attention.value_length default=128
  5. time=2025-02-25T12:44:50.347Z level=WARN source=ggml.go:132 msg="key not found" key=llama.attention.key_length default=128
  6. time=2025-02-25T12:44:50.347Z level=WARN source=ggml.go:132 msg="key not found" key=llama.attention.value_length default=128
  7. time=2025-02-25T12:44:50.347Z level=INFO source=sched.go:715 msg="new model will fit in available VRAM in single GPU, loading" model=/root/.ollama/models/blobs/sha256-667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29 gpu=0 parallel=1 available=6575390720 required="5.4 GiB"
  8. time=2025-02-25T12:44:50.347Z level=INFO source=server.go:97 msg="system memory" total="47.0 GiB" free="32.6 GiB" free_swap="1.1 GiB"
  9. time=2025-02-25T12:44:50.347Z level=WARN source=ggml.go:132 msg="key not found" key=llama.attention.key_length default=128
  10. time=2025-02-25T12:44:50.347Z level=WARN source=ggml.go:132 msg="key not found" key=llama.attention.value_length default=128
  11. time=2025-02-25T12:44:50.347Z level=INFO source=server.go:130 msg=offload library=rocm layers.requested=-1 layers.model=33 layers.offload=33 layers.split="" memory.available="[6.1 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.4 GiB" memory.required.partial="5.4 GiB" memory.required.kv="256.0 MiB" memory.required.allocations="[5.4 GiB]" memory.weights.total="4.1 GiB" memory.weights.repeating="3.7 GiB" memory.weights.nonrepeating="411.0 MiB" memory.graph.full="258.5 MiB" memory.graph.partial="677.5 MiB"
  12. time=2025-02-25T12:44:50.348Z level=INFO source=server.go:380 msg="starting llama server" cmd="/ollama/ollama runner --model /root/.ollama/models/blobs/sha256-667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29 --ctx-size 2048 --batch-size 512 --n-gpu-layers 33 --threads 8 --parallel 1 --port 44359"
  13. time=2025-02-25T12:44:50.348Z level=INFO source=sched.go:450 msg="loaded runners" count=1
  14. time=2025-02-25T12:44:50.348Z level=INFO source=server.go:557 msg="waiting for llama runner to start responding"
  15. time=2025-02-25T12:44:50.348Z level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server error"
  16. time=2025-02-25T12:44:50.358Z level=INFO source=runner.go:932 msg="starting go runner"
  17. ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
  18. ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
  19. ggml_cuda_init: found 1 ROCm devices:
  20. Device 0: Radeon RX 570 Series, compute capability 8.0, VMM: no
  21. load_backend: loaded ROCm backend from /ollama/build/lib/ollama/libggml-hip.so
  22. load_backend: loaded CPU backend from /ollama/build/lib/ollama/libggml-cpu-haswell.so
  23. time=2025-02-25T12:44:50.654Z level=INFO source=runner.go:935 msg=system info="CPU : LLAMAFILE = 1 | CPU : LLAMAFILE = 1 | ROCm : PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | LLAMAFILE = 1 | cgo(gcc)" threads=8
  24. time=2025-02-25T12:44:50.654Z level=INFO source=runner.go:993 msg="Server listening on 127.0.0.1:44359"
  25. llama_load_model_from_file: using device ROCm0 (Radeon RX 570 Series) - 7846 MiB free
  26. llama_model_loader: loaded meta data with 29 key-value pairs and 292 tensors from /root/.ollama/models/blobs/sha256-667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29 (version GGUF V3 (latest))
  27. llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
  28. llama_model_loader: - kv 0: general.architecture str = llama
  29. llama_model_loader: - kv 1: general.type str = model
  30. llama_model_loader: - kv 2: general.name str = Meta Llama 3.1 8B Instruct
  31. llama_model_loader: - kv 3: general.finetune str = Instruct
  32. llama_model_loader: - kv 4: general.basename str = Meta-Llama-3.1
  33. llama_model_loader: - kv 5: general.size_label str = 8B
  34. llama_model_loader: - kv 6: general.license str = llama3.1
  35. llama_model_loader: - kv 7: general.tags arr[str,6] = ["facebook", "meta", "pytorch", "llam...
  36. llama_model_loader: - kv 8: general.languages arr[str,8] = ["en", "de", "fr", "it", "pt", "hi", ...
  37. llama_model_loader: - kv 9: llama.block_count u32 = 32
  38. llama_model_loader: - kv 10: llama.context_length u32 = 131072
  39. llama_model_loader: - kv 11: llama.embedding_length u32 = 4096
  40. llama_model_loader: - kv 12: llama.feed_forward_length u32 = 14336
  41. llama_model_loader: - kv 13: llama.attention.head_count u32 = 32
  42. llama_model_loader: - kv 14: llama.attention.head_count_kv u32 = 8
  43. llama_model_loader: - kv 15: llama.rope.freq_base f32 = 500000.000000
  44. llama_model_loader: - kv 16: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
  45. llama_model_loader: - kv 17: general.file_type u32 = 15
  46. llama_model_loader: - kv 18: llama.vocab_size u32 = 128256
  47. llama_model_loader: - kv 19: llama.rope.dimension_count u32 = 128
  48. llama_model_loader: - kv 20: tokenizer.ggml.model str = gpt2
  49. llama_model_loader: - kv 21: tokenizer.ggml.pre str = llama-bpe
  50. llama_model_loader: - kv 22: tokenizer.ggml.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ...
  51. llama_model_loader: - kv 23: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
  52. llama_model_loader: - kv 24: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
  53. llama_model_loader: - kv 25: tokenizer.ggml.bos_token_id u32 = 128000
  54. llama_model_loader: - kv 26: tokenizer.ggml.eos_token_id u32 = 128009
  55. llama_model_loader: - kv 27: tokenizer.chat_template str = {{- bos_token }}\n{%- if custom_tools ...
  56. llama_model_loader: - kv 28: general.quantization_version u32 = 2
  57. llama_model_loader: - type f32: 66 tensors
  58. llama_model_loader: - type q4_K: 193 tensors
  59. llama_model_loader: - type q6_K: 33 tensors
  60. time=2025-02-25T12:44:50.850Z level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server loading model"
  61. llm_load_vocab: special tokens cache size = 256
  62. llm_load_vocab: token to piece cache size = 0.7999 MB
  63. llm_load_print_meta: format = GGUF V3 (latest)
  64. llm_load_print_meta: arch = llama
  65. llm_load_print_meta: vocab type = BPE
  66. llm_load_print_meta: n_vocab = 128256
  67. llm_load_print_meta: n_merges = 280147
  68. llm_load_print_meta: vocab_only = 0
  69. llm_load_print_meta: n_ctx_train = 131072
  70. llm_load_print_meta: n_embd = 4096
  71. llm_load_print_meta: n_layer = 32
  72. llm_load_print_meta: n_head = 32
  73. llm_load_print_meta: n_head_kv = 8
  74. llm_load_print_meta: n_rot = 128
  75. llm_load_print_meta: n_swa = 0
  76. llm_load_print_meta: n_embd_head_k = 128
  77. llm_load_print_meta: n_embd_head_v = 128
  78. llm_load_print_meta: n_gqa = 4
  79. llm_load_print_meta: n_embd_k_gqa = 1024
  80. llm_load_print_meta: n_embd_v_gqa = 1024
  81. llm_load_print_meta: f_norm_eps = 0.0e+00
  82. llm_load_print_meta: f_norm_rms_eps = 1.0e-05
  83. llm_load_print_meta: f_clamp_kqv = 0.0e+00
  84. llm_load_print_meta: f_max_alibi_bias = 0.0e+00
  85. llm_load_print_meta: f_logit_scale = 0.0e+00
  86. llm_load_print_meta: n_ff = 14336
  87. llm_load_print_meta: n_expert = 0
  88. llm_load_print_meta: n_expert_used = 0
  89. llm_load_print_meta: causal attn = 1
  90. llm_load_print_meta: pooling type = 0
  91. llm_load_print_meta: rope type = 0
  92. llm_load_print_meta: rope scaling = linear
  93. llm_load_print_meta: freq_base_train = 500000.0
  94. llm_load_print_meta: freq_scale_train = 1
  95. llm_load_print_meta: n_ctx_orig_yarn = 131072
  96. llm_load_print_meta: rope_finetuned = unknown
  97. llm_load_print_meta: ssm_d_conv = 0
  98. llm_load_print_meta: ssm_d_inner = 0
  99. llm_load_print_meta: ssm_d_state = 0
  100. llm_load_print_meta: ssm_dt_rank = 0
  101. llm_load_print_meta: ssm_dt_b_c_rms = 0
  102. llm_load_print_meta: model type = 8B
  103. llm_load_print_meta: model ftype = Q4_K - Medium
  104. llm_load_print_meta: model params = 8.03 B
  105. llm_load_print_meta: model size = 4.58 GiB (4.89 BPW)
  106. llm_load_print_meta: general.name = Meta Llama 3.1 8B Instruct
  107. llm_load_print_meta: BOS token = 128000 '<|begin_of_text|>'
  108. llm_load_print_meta: EOS token = 128009 '<|eot_id|>'
  109. llm_load_print_meta: EOT token = 128009 '<|eot_id|>'
  110. llm_load_print_meta: EOM token = 128008 '<|eom_id|>'
  111. llm_load_print_meta: LF token = 128 'Ä'
  112. llm_load_print_meta: EOG token = 128008 '<|eom_id|>'
  113. llm_load_print_meta: EOG token = 128009 '<|eot_id|>'
  114. llm_load_print_meta: max token length = 256
  115. llm_load_tensors: offloading 32 repeating layers to GPU
  116. llm_load_tensors: offloading output layer to GPU
  117. llm_load_tensors: offloaded 33/33 layers to GPU
  118. llm_load_tensors: ROCm0 model buffer size = 4403.49 MiB
  119. llm_load_tensors: CPU_Mapped model buffer size = 281.81 MiB
  120. llama_new_context_with_model: n_seq_max = 1
  121. llama_new_context_with_model: n_ctx = 2048
  122. llama_new_context_with_model: n_ctx_per_seq = 2048
  123. llama_new_context_with_model: n_batch = 512
  124. llama_new_context_with_model: n_ubatch = 512
  125. llama_new_context_with_model: flash_attn = 0
  126. llama_new_context_with_model: freq_base = 500000.0
  127. llama_new_context_with_model: freq_scale = 1
  128. llama_new_context_with_model: n_ctx_per_seq (2048) < n_ctx_train (131072) -- the full capacity of the model will not be utilized
  129. llama_kv_cache_init: kv_size = 2048, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 32, can_shift = 1
  130. llama_kv_cache_init: ROCm0 KV buffer size = 256.00 MiB
  131. llama_new_context_with_model: KV self size = 256.00 MiB, K (f16): 128.00 MiB, V (f16): 128.00 MiB
  132. llama_new_context_with_model: ROCm_Host output buffer size = 0.50 MiB
  133. llama_new_context_with_model: ROCm0 compute buffer size = 258.50 MiB
  134. llama_new_context_with_model: ROCm_Host compute buffer size = 12.01 MiB
  135. llama_new_context_with_model: graph nodes = 1030
  136. llama_new_context_with_model: graph splits = 2
  137. time=2025-02-25T12:44:52.355Z level=INFO source=server.go:596 msg="llama runner started in 2.01 seconds"
  138. [GIN] 2025/02/25 - 12:44:52 | 200 | 2.065835539s | 127.0.0.1 | POST "/api/generate"
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!