GREEN   94   0
   1317 9.38 KB    148

LunarArtist_07_14 error

By Guest
Created: 2023-11-09 10:12:27
Expiry: Never
sfw

  1. 1.
    Hitch Trailblazer has a puckered hole, and that bitch loves it - Sunny Flare
  2. 2.
    Git LFS initialized.
  3. 3.
    Cloning into '/content/fix'...
  4. 4.
    remote: Enumerating objects: 74, done.
  5. 5.
    remote: Total 74 (delta 0), reused 0 (delta 0), pack-reused 74
  6. 6.
    Unpacking objects: 100% (74/74), 21.93 KiB | 1.15 MiB/s, done.
  7. 7.
    author -- TheBloke
  8. 8.
    repo -- MythoMax-L2-13B-GGUF
  9. 9.
    branch -- main
  10. 10.
    filename -- mythomax-l2-13b.Q6_K.gguf
  11. 11.
  12. 12.
  13. 13.
  14. 14.
  15. 15.
  16. 16.
    format -- gguf
  17. 17.
    backend -- koboldcpp
  18. 18.
    mode -- file
  19. 19.
    beaks -- 13
  20. 20.
    quantz -- q6_k
  21. 21.
    quantz_num -- 6
  22. 22.
    bits -- unknown
  23. 23.
    pointer -- mythomax-l2-13b.Q6_K.gguf
  24. 24.
    path_pointer -- /content/colabTemp/mythomax-l2-13b.Q6_K.gguf
  25. 25.
  26. 26.
     
  27. 27.
    ::: NOTIFICATIONS :::
  28. 28.
    model has 6 quantz and 13b - Colab will work alright but higher context might not available
  29. 29.
     
  30. 30.
    ::: Colab is magic :::
  31. 31.
     
  32. 32.
    ...[context] user didn't set context. will calculate max context automatically
  33. 33.
    ::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::
  34. 34.
    ::: notebook automatically calculated the about-right* CONTEXT for this model:
  35. 35.
    ::: 4096
  36. 36.
    ::: if model does not work properly with that context (CUDA error) then try lower it by 512
  37. 37.
    ::: it is only an approximate value - test and report back. especially with non-13b models
  38. 38.
    ::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::
  39. 39.
     
  40. 40.
    ::: DOWNLOAD BACKEND, MODEL, LORA :::
  41. 41.
    ...[backend] processing the backend: kobold.cpp
  42. 42.
    ...[cloudflare] nohup.out from the previous instance was detected, deleting
  43. 43.
    ...[model] processing the model: https://huggingface.co/TheBloke/MythoMax-L2-13B-GGUF
  44. 44.
    ...[backend] kobold.cpp is already installed
  45. 45.
    ...[cloudflare] launching Cloudflare and waiting for an answer...[model] model is already downloaded
  46. 46.
    ...[LoRA] processing LoRA
  47. 47.
     
  48. 48.
    ...[LoRA] LoRAs are specified, will process them now
  49. 49.
  50. 50.
    ...[LoRA] LoRA llama-2-13b-pny-3e is already downloaded
  51. 51.
     
  52. 52.
    ::: LAUNCHING BACKEND :::
  53. 53.
    nohup: appending output to 'nohup.out'
  54. 54.
    Cloudflare tunnel was created, here is the link:
  55. 55.
    2023-11-09T10:05:27Z INF Thank you for trying Cloudflare Tunnel. Doing so, without a Cloudflare account, is a quick way to experiment and try it out. However, be aware that these account-less Tunnels have no uptime guarantee. If you intend to use Tunnels in production you should use a pre-created named tunnel by following: https://developers.cloudflare.com/cloudflare-one/connections/connect-apps
  56. 56.
    2023-11-09T10:05:27Z INF Requesting new quick Tunnel on trycloudflare.com...
  57. 57.
    2023-11-09T10:05:28Z INF +--------------------------------------------------------------------------------------------+
  58. 58.
    2023-11-09T10:05:28Z INF | Your quick Tunnel has been created! Visit it at (it may take some time to be reachable): |
  59. 59.
  60. 60.
    2023-11-09T10:05:28Z INF +--------------------------------------------------------------------------------------------+
  61. 61.
    2023-11-09T10:05:28Z INF Cannot determine default configuration path. No file [config.yml config.yaml] in [~/.cloudflared ~/.cloudflare-warp ~/cloudflare-warp /etc/cloudflared /usr/local/etc/cloudflared]
  62. 62.
    2023-11-09T10:05:28Z INF Version 2023.10.0
  63. 63.
    2023-11-09T10:05:28Z INF GOOS: linux, GOVersion: go1.20.6, GoArch: amd64
  64. 64.
    2023-11-09T10:05:28Z INF Settings: map[ha-connections:1 protocol:quic url:http://localhost:5001]
  65. 65.
    2023-11-09T10:05:28Z INF Generated Connector ID: 039a7411-8213-4b9c-8190-81ebf24e5e6f
  66. 66.
    2023-11-09T10:05:28Z INF Autoupdate frequency is set autoupdateFreq=86400000
  67. 67.
    2023-11-09T10:05:28Z INF Initial protocol quic
  68. 68.
    2023-11-09T10:05:28Z INF ICMP proxy will use 172.28.0.12 as source for IPv4
  69. 69.
    2023-11-09T10:05:28Z INF ICMP proxy will use :: as source for IPv6
  70. 70.
    2023-11-09T10:05:28Z INF Starting metrics server on 127.0.0.1:33803/metrics
  71. 71.
    2023/11/09 10:05:28 failed to sufficiently increase receive buffer size (was: 208 kiB, wanted: 2048 kiB, got: 416 kiB). See https://github.com/quic-go/quic-go/wiki/UDP-Receive-Buffer-Size for details.
  72. 72.
    2023-11-09T10:05:28Z INF Registered tunnel connection connIndex=0 connection=718e7e64-d24e-455d-97e6-2e427e21ec1a event=0 ip=198.41.200.113 location=ord06 protocol=quic
  73. 73.
     
  74. 74.
    backend is launched with the following flags:
  75. 75.
    python /content/colabMain/koboldcpp/koboldcpp.py --highpriority --threads 2 --usecublas normal 0 mmq --gpulayers 43 --hordeconfig MythoMax-L2-13B-GGUF --lora /content/colabTemp/llama-2-13b-pny-3e/adapter_model.bin --model /content/colabTemp/mythomax-l2-13b.Q6_K.gguf --context 4096
  76. 76.
    ***
  77. 77.
    Welcome to KoboldCpp - Version 1.46.1
  78. 78.
    Setting process to Higher Priority - Use Caution
  79. 79.
    High Priority for Linux Set: 0 to 1
  80. 80.
    Attempting to use CuBLAS library for faster prompt ingestion. A compatible CuBLAS will be required.
  81. 81.
    Initializing dynamic library: koboldcpp_cublas.so
  82. 82.
    ==========
  83. 83.
    Namespace(model='/content/colabTemp/mythomax-l2-13b.Q6_K.gguf', model_param='/content/colabTemp/mythomax-l2-13b.Q6_K.gguf', port=5001, port_param=5001, host='', launch=False, lora=['/content/colabTemp/llama-2-13b-pny-3e/adapter_model.bin'], config=None, threads=2, blasthreads=2, highpriority=True, contextsize=4096, blasbatchsize=512, ropeconfig=[0.0, 10000.0], smartcontext=False, bantokens=None, forceversion=0, nommap=False, usemlock=False, noavx2=False, debugmode=-1, skiplauncher=False, hordeconfig=['MythoMax-L2-13B-GGUF'], noblas=False, useclblast=None, usecublas=['normal', '0', 'mmq'], gpulayers=43, tensor_split=None, onready='', multiuser=False, foreground=False)
  84. 84.
    ==========
  85. 85.
    Loading model: /content/colabTemp/mythomax-l2-13b.Q6_K.gguf
  86. 86.
    [Threads: 2, BlasThreads: 2, SmartContext: False]
  87. 87.
     
  88. 88.
    ---
  89. 89.
    Identified as LLAMA model: (ver 6)
  90. 90.
    Attempting to Load...
  91. 91.
    ---
  92. 92.
    Using automatic RoPE scaling (scale:1.000, base:10000.0)
  93. 93.
    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 = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 |
  94. 94.
    ggml_init_cublas: found 1 CUDA devices:
  95. 95.
    Device 0: Tesla T4, compute capability 7.5
  96. 96.
    llama_model_loader: loaded meta data with 19 key-value pairs and 363 tensors from /content/colabTemp/mythomax-l2-13b.Q6_K.gguf (version GGUF V2 (latest))
  97. 97.
    llm_load_print_meta: format = GGUF V2 (latest)
  98. 98.
    llm_load_print_meta: arch = llama
  99. 99.
    llm_load_print_meta: vocab type = SPM
  100. 100.
    llm_load_print_meta: n_vocab = 32000
  101. 101.
    llm_load_print_meta: n_merges = 0
  102. 102.
    llm_load_print_meta: n_ctx_train = 4096
  103. 103.
    llm_load_print_meta: n_embd = 5120
  104. 104.
    llm_load_print_meta: n_head = 40
  105. 105.
    llm_load_print_meta: n_head_kv = 40
  106. 106.
    llm_load_print_meta: n_layer = 40
  107. 107.
    llm_load_print_meta: n_rot = 128
  108. 108.
    llm_load_print_meta: n_gqa = 1
  109. 109.
    llm_load_print_meta: f_norm_eps = 0.0e+00
  110. 110.
    llm_load_print_meta: f_norm_rms_eps = 1.0e-05
  111. 111.
    llm_load_print_meta: n_ff = 13824
  112. 112.
    llm_load_print_meta: freq_base_train = 10000.0
  113. 113.
    llm_load_print_meta: freq_scale_train = 1
  114. 114.
    llm_load_print_meta: model type = 13B
  115. 115.
    llm_load_print_meta: model ftype = unknown, may not work (guessed)
  116. 116.
    llm_load_print_meta: model params = 13.02 B
  117. 117.
    llm_load_print_meta: model size = 9.95 GiB (6.56 BPW)
  118. 118.
    llm_load_print_meta: general.name = LLaMA v2
  119. 119.
    llm_load_print_meta: BOS token = 1 '<s>'
  120. 120.
    llm_load_print_meta: EOS token = 2 '</s>'
  121. 121.
    llm_load_print_meta: UNK token = 0 '<unk>'
  122. 122.
    llm_load_print_meta: LF token = 13 '<0x0A>'
  123. 123.
    llm_load_tensors: ggml ctx size = 10183.83 MB
  124. 124.
    llm_load_tensors: using CUDA for GPU acceleration
  125. 125.
    llm_load_tensors: mem required = 128.29 MB
  126. 126.
    llm_load_tensors: offloading 40 repeating layers to GPU
  127. 127.
    llm_load_tensors: offloading non-repeating layers to GPU
  128. 128.
    llm_load_tensors: offloaded 43/43 layers to GPU
  129. 129.
    llm_load_tensors: VRAM used: 10055.54 MB
  130. 130.
    ...................................................................................................
  131. 131.
    llama_new_context_with_model: n_ctx = 4096
  132. 132.
    llama_new_context_with_model: freq_base = 10000.0
  133. 133.
    llama_new_context_with_model: freq_scale = 1
  134. 134.
    WARNING: failed to allocate 3202.00 MB of pinned memory: out of memory
  135. 135.
    llama_kv_cache_init: offloading v cache to GPU
  136. 136.
    llama_kv_cache_init: offloading k cache to GPU
  137. 137.
    llama_kv_cache_init: VRAM kv self = 3200.00 MB
  138. 138.
    llama_new_context_with_model: kv self size = 3200.00 MB
  139. 139.
    llama_new_context_with_model: compute buffer total size = 363.88 MB
  140. 140.
    llama_new_context_with_model: VRAM scratch buffer: 358.00 MB
  141. 141.
    llama_new_context_with_model: total VRAM used: 13613.54 MB (model: 10055.54 MB, context: 3558.00 MB)
  142. 142.
     
  143. 143.
    Attempting to apply LORA adapter: /content/colabTemp/llama-2-13b-pny-3e/adapter_model.bin
  144. 144.
    llama_apply_lora_from_file_internal: applying lora adapter from '/content/colabTemp/llama-2-13b-pny-3e/adapter_model.bin' - please wait ...
  145. 145.
    llama_apply_lora_from_file_internal: unsupported file version
  146. 146.
    gpttype_load_model: error: failed to apply lora adapter
  147. 147.
    Load Model OK: False
  148. 148.
    Could not load model: /content/colabTemp/mythomax-l2-13b.Q6_K.gguf

Yandere Thread - Yandere Applejack (completed)

by Guest

Bonding with Nature

by Guest

The Long and Short of It (RGRE)

by Guest

incest relationships piece of the whole pie (lewd) by Frostybox[...]

by Guest

incest thread piece of the (non-canon) pie, limestone's pie by[...]

by Guest