Upload imatrix.log with huggingface_hub

imatrix.log

@@ -0,0 +1,141 @@
+llama_model_loader: loaded meta data with 23 key-value pairs and 283 tensors from codegeex4-all-9b-IMat-GGUF/codegeex4-all-9b.Q8_0.gguf.hardlink.gguf (version GGUF V3 (latest))
+llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
+llama_model_loader: - kv   0:                       general.architecture str              = chatglm
+llama_model_loader: - kv   1:                               general.name str              = codegeex4-all-9b
+llama_model_loader: - kv   2:                     chatglm.context_length u32              = 131072
+llama_model_loader: - kv   3:                   chatglm.embedding_length u32              = 4096
+llama_model_loader: - kv   4:                chatglm.feed_forward_length u32              = 13696
+llama_model_loader: - kv   5:                        chatglm.block_count u32              = 40
+llama_model_loader: - kv   6:               chatglm.attention.head_count u32              = 32
+llama_model_loader: - kv   7:            chatglm.attention.head_count_kv u32              = 2
+llama_model_loader: - kv   8:   chatglm.attention.layer_norm_rms_epsilon f32              = 0.000010
+llama_model_loader: - kv   9:                          general.file_type u32              = 7
+llama_model_loader: - kv  10:               chatglm.rope.dimension_count u32              = 64
+llama_model_loader: - kv  11:               tokenizer.ggml.add_bos_token bool             = false
+llama_model_loader: - kv  12:                     chatglm.rope.freq_base f32              = 500.000000
+llama_model_loader: - kv  13:                       tokenizer.ggml.model str              = gpt2
+llama_model_loader: - kv  14:                         tokenizer.ggml.pre str              = chatglm-bpe
+llama_model_loader: - kv  15:                      tokenizer.ggml.tokens arr[str,151552]  = ["!", "\"", "#", "$", "%", "&", "'", ...
+llama_model_loader: - kv  16:                  tokenizer.ggml.token_type arr[i32,151552]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
+llama_model_loader: - kv  17:                      tokenizer.ggml.merges arr[str,151073]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
+llama_model_loader: - kv  18:            tokenizer.ggml.padding_token_id u32              = 151329
+llama_model_loader: - kv  19:                tokenizer.ggml.eos_token_id u32              = 151329
+llama_model_loader: - kv  20:                tokenizer.ggml.eot_token_id u32              = 151336
+llama_model_loader: - kv  21:            tokenizer.ggml.unknown_token_id u32              = 151329
+llama_model_loader: - kv  22:               general.quantization_version u32              = 2
+llama_model_loader: - type  f32:  121 tensors
+llama_model_loader: - type q8_0:  162 tensors
+llm_load_vocab: special tokens cache size = 223
+llm_load_vocab: token to piece cache size = 0.9732 MB
+llm_load_print_meta: format           = GGUF V3 (latest)
+llm_load_print_meta: arch             = chatglm
+llm_load_print_meta: vocab type       = BPE
+llm_load_print_meta: n_vocab          = 151552
+llm_load_print_meta: n_merges         = 151073
+llm_load_print_meta: n_ctx_train      = 131072
+llm_load_print_meta: n_embd           = 4096
+llm_load_print_meta: n_head           = 32
+llm_load_print_meta: n_head_kv        = 2
+llm_load_print_meta: n_layer          = 40
+llm_load_print_meta: n_rot            = 64
+llm_load_print_meta: n_swa            = 0
+llm_load_print_meta: n_embd_head_k    = 128
+llm_load_print_meta: n_embd_head_v    = 128
+llm_load_print_meta: n_gqa            = 16
+llm_load_print_meta: n_embd_k_gqa     = 256
+llm_load_print_meta: n_embd_v_gqa     = 256
+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: f_logit_scale    = 0.0e+00
+llm_load_print_meta: n_ff             = 13696
+llm_load_print_meta: n_expert         = 0
+llm_load_print_meta: n_expert_used    = 0
+llm_load_print_meta: causal attn      = 1
+llm_load_print_meta: pooling type     = 0
+llm_load_print_meta: rope type        = 0
+llm_load_print_meta: rope scaling     = linear
+llm_load_print_meta: freq_base_train  = 500.0
+llm_load_print_meta: freq_scale_train = 1
+llm_load_print_meta: n_ctx_orig_yarn  = 131072
+llm_load_print_meta: rope_finetuned   = unknown
+llm_load_print_meta: ssm_d_conv       = 0
+llm_load_print_meta: ssm_d_inner      = 0
+llm_load_print_meta: ssm_d_state      = 0
+llm_load_print_meta: ssm_dt_rank      = 0
+llm_load_print_meta: model type       = 9B
+llm_load_print_meta: model ftype      = Q8_0
+llm_load_print_meta: model params     = 9.40 B
+llm_load_print_meta: model size       = 9.30 GiB (8.50 BPW) 
+llm_load_print_meta: general.name     = codegeex4-all-9b
+llm_load_print_meta: EOS token        = 151329 '<|endoftext|>'
+llm_load_print_meta: UNK token        = 151329 '<|endoftext|>'
+llm_load_print_meta: PAD token        = 151329 '<|endoftext|>'
+llm_load_print_meta: LF token         = 128 'Ä'
+llm_load_print_meta: EOT token        = 151336 '<|user|>'
+llm_load_print_meta: max token length = 1024
+ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
+ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
+ggml_cuda_init: found 1 CUDA devices:
+  Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9, VMM: yes
+llm_load_tensors: ggml ctx size =    0.28 MiB
+llm_load_tensors: offloading 40 repeating layers to GPU
+llm_load_tensors: offloading non-repeating layers to GPU
+llm_load_tensors: offloaded 41/41 layers to GPU
+llm_load_tensors:        CPU buffer size =   629.00 MiB
+llm_load_tensors:      CUDA0 buffer size =  8897.23 MiB
+.................................................................................
+llama_new_context_with_model: n_ctx      = 512
+llama_new_context_with_model: n_batch    = 512
+llama_new_context_with_model: n_ubatch   = 512
+llama_new_context_with_model: flash_attn = 0
+llama_new_context_with_model: freq_base  = 500.0
+llama_new_context_with_model: freq_scale = 1
+llama_kv_cache_init:      CUDA0 KV buffer size =    20.00 MiB
+llama_new_context_with_model: KV self size  =   20.00 MiB, K (f16):   10.00 MiB, V (f16):   10.00 MiB
+llama_new_context_with_model:  CUDA_Host  output buffer size =     0.58 MiB
+llama_new_context_with_model:      CUDA0 compute buffer size =   304.00 MiB
+llama_new_context_with_model:  CUDA_Host compute buffer size =     9.01 MiB
+llama_new_context_with_model: graph nodes  = 1606
+llama_new_context_with_model: graph splits = 2
+
+system_info: n_threads = 25 / 32 | AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 1 | AVX512_VBMI = 1 | AVX512_VNNI = 1 | AVX512_BF16 = 1 | FMA = 1 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | 
+compute_imatrix: tokenizing the input ..
+compute_imatrix: tokenization took 122.92 ms
+compute_imatrix: computing over 125 chunks with batch_size 512
+compute_imatrix: 0.63 seconds per pass - ETA 1.30 minutes
+[1]10.3562,[2]8.4325,[3]7.7173,[4]9.6163,[5]9.6539,[6]7.8712,[7]8.6433,[8]9.1616,[9]9.5800,
+save_imatrix: stored collected data after 10 chunks in codegeex4-all-9b-IMat-GGUF/imatrix.dat
+[10]8.1854,[11]9.0245,[12]10.1385,[13]10.8339,[14]11.3143,[15]12.0013,[16]12.5792,[17]12.9746,[18]12.4173,[19]11.6037,
+save_imatrix: stored collected data after 20 chunks in codegeex4-all-9b-IMat-GGUF/imatrix.dat
+[20]11.7752,[21]12.4757,[22]12.1252,[23]12.7541,[24]12.6786,[25]13.2785,[26]13.4211,[27]13.7764,[28]14.4623,[29]14.7203,
+save_imatrix: stored collected data after 30 chunks in codegeex4-all-9b-IMat-GGUF/imatrix.dat
+[30]14.6740,[31]13.7066,[32]13.2003,[33]12.9453,[34]12.7611,[35]12.8194,[36]13.1588,[37]13.1278,[38]13.2979,[39]13.6020,
+save_imatrix: stored collected data after 40 chunks in codegeex4-all-9b-IMat-GGUF/imatrix.dat
+[40]13.6874,[41]14.4190,[42]15.0294,[43]15.5386,[44]15.8908,[45]16.1925,[46]15.9531,[47]16.1393,[48]16.2833,[49]16.2760,
+save_imatrix: stored collected data after 50 chunks in codegeex4-all-9b-IMat-GGUF/imatrix.dat
+[50]16.2608,[51]16.2804,[52]16.5852,[53]16.7566,[54]17.0592,[55]17.1281,[56]17.0877,[57]17.1132,[58]17.0390,[59]16.8126,
+save_imatrix: stored collected data after 60 chunks in codegeex4-all-9b-IMat-GGUF/imatrix.dat
+[60]16.6386,[61]16.4616,[62]16.4449,[63]16.5449,[64]16.3393,[65]16.2853,[66]16.2069,[67]16.0896,[68]16.0264,[69]15.9704,
+save_imatrix: stored collected data after 70 chunks in codegeex4-all-9b-IMat-GGUF/imatrix.dat
+[70]15.9065,[71]15.8381,[72]15.8003,[73]15.7025,[74]15.5344,[75]15.4538,[76]15.4497,[77]15.4111,[78]15.3426,[79]15.3654,
+save_imatrix: stored collected data after 80 chunks in codegeex4-all-9b-IMat-GGUF/imatrix.dat
+[80]15.3707,[81]15.2761,[82]15.3316,[83]15.3867,[84]15.0731,[85]15.0980,[86]15.0961,[87]15.1150,[88]15.1433,[89]15.1545,
+save_imatrix: stored collected data after 90 chunks in codegeex4-all-9b-IMat-GGUF/imatrix.dat
+[90]14.9914,[91]14.8445,[92]14.6858,[93]14.5355,[94]14.3787,[95]14.2427,[96]14.1677,[97]14.1794,[98]14.2049,[99]14.4170,
+save_imatrix: stored collected data after 100 chunks in codegeex4-all-9b-IMat-GGUF/imatrix.dat
+[100]14.6055,[101]14.7210,[102]14.9603,[103]15.0024,[104]15.0448,[105]14.8945,[106]14.8769,[107]14.8630,[108]14.7411,[109]14.6102,
+save_imatrix: stored collected data after 110 chunks in codegeex4-all-9b-IMat-GGUF/imatrix.dat
+[110]14.6423,[111]14.7466,[112]14.7437,[113]14.7807,[114]14.8204,[115]14.9192,[116]14.9062,[117]14.8987,[118]14.8812,[119]14.7589,
+save_imatrix: stored collected data after 120 chunks in codegeex4-all-9b-IMat-GGUF/imatrix.dat
+[120]14.9470,[121]15.1001,[122]15.2480,[123]15.3920,[124]15.5287,[125]15.6589,
+save_imatrix: stored collected data after 125 chunks in codegeex4-all-9b-IMat-GGUF/imatrix.dat
+
+llama_print_timings:        load time =   16954.85 ms
+llama_print_timings:      sample time =       0.00 ms /     1 runs   (    0.00 ms per token,      inf tokens per second)
+llama_print_timings: prompt eval time =   66214.21 ms / 64000 tokens (    1.03 ms per token,   966.56 tokens per second)
+llama_print_timings:        eval time =       0.00 ms /     1 runs   (    0.00 ms per token,      inf tokens per second)
+llama_print_timings:       total time =   83433.10 ms / 64001 tokens
+
+Final estimate: PPL = 15.6589 +/- 0.26003