Upload imatrix.log with huggingface_hub

imatrix.log

@@ -0,0 +1,143 @@
+llama_model_loader: loaded meta data with 25 key-value pairs and 508 tensors from gemma-2-27b-it-IMat-GGUF/gemma-2-27b-it.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              = gemma2
+llama_model_loader: - kv   1:                               general.name str              = gemma-2-27b-it
+llama_model_loader: - kv   2:                      gemma2.context_length u32              = 8192
+llama_model_loader: - kv   3:                    gemma2.embedding_length u32              = 4608
+llama_model_loader: - kv   4:                         gemma2.block_count u32              = 46
+llama_model_loader: - kv   5:                 gemma2.feed_forward_length u32              = 36864
+llama_model_loader: - kv   6:                gemma2.attention.head_count u32              = 32
+llama_model_loader: - kv   7:             gemma2.attention.head_count_kv u32              = 16
+llama_model_loader: - kv   8:    gemma2.attention.layer_norm_rms_epsilon f32              = 0.000001
+llama_model_loader: - kv   9:                gemma2.attention.key_length u32              = 128
+llama_model_loader: - kv  10:              gemma2.attention.value_length u32              = 128
+llama_model_loader: - kv  11:                          general.file_type u32              = 7
+llama_model_loader: - kv  12:                       tokenizer.ggml.model str              = llama
+llama_model_loader: - kv  13:                         tokenizer.ggml.pre str              = default
+llama_model_loader: - kv  14:                      tokenizer.ggml.tokens arr[str,256000]  = ["<pad>", "<eos>", "<bos>", "<unk>", ...
+llama_model_loader: - kv  15:                      tokenizer.ggml.scores arr[f32,256000]  = [0.000000, 0.000000, 0.000000, 0.0000...
+llama_model_loader: - kv  16:                  tokenizer.ggml.token_type arr[i32,256000]  = [3, 3, 3, 2, 1, 1, 1, 1, 1, 1, 1, 1, ...
+llama_model_loader: - kv  17:                tokenizer.ggml.bos_token_id u32              = 2
+llama_model_loader: - kv  18:                tokenizer.ggml.eos_token_id u32              = 1
+llama_model_loader: - kv  19:            tokenizer.ggml.unknown_token_id u32              = 3
+llama_model_loader: - kv  20:            tokenizer.ggml.padding_token_id u32              = 0
+llama_model_loader: - kv  21:               tokenizer.ggml.add_bos_token bool             = true
+llama_model_loader: - kv  22:               tokenizer.ggml.add_eos_token bool             = false
+llama_model_loader: - kv  23:                    tokenizer.chat_template str              = {{ bos_token }}{% if messages[0]['rol...
+llama_model_loader: - kv  24:               general.quantization_version u32              = 2
+llama_model_loader: - type  f32:  185 tensors
+llama_model_loader: - type q8_0:  323 tensors
+llm_load_vocab: special tokens cache size = 260
+llm_load_vocab: token to piece cache size = 1.6014 MB
+llm_load_print_meta: format           = GGUF V3 (latest)
+llm_load_print_meta: arch             = gemma2
+llm_load_print_meta: vocab type       = SPM
+llm_load_print_meta: n_vocab          = 256000
+llm_load_print_meta: n_merges         = 0
+llm_load_print_meta: n_ctx_train      = 8192
+llm_load_print_meta: n_embd           = 4608
+llm_load_print_meta: n_head           = 32
+llm_load_print_meta: n_head_kv        = 16
+llm_load_print_meta: n_layer          = 46
+llm_load_print_meta: n_rot            = 144
+llm_load_print_meta: n_embd_head_k    = 128
+llm_load_print_meta: n_embd_head_v    = 128
+llm_load_print_meta: n_gqa            = 2
+llm_load_print_meta: n_embd_k_gqa     = 2048
+llm_load_print_meta: n_embd_v_gqa     = 2048
+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: f_logit_scale    = 0.0e+00
+llm_load_print_meta: n_ff             = 36864
+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        = 2
+llm_load_print_meta: rope scaling     = linear
+llm_load_print_meta: freq_base_train  = 10000.0
+llm_load_print_meta: freq_scale_train = 1
+llm_load_print_meta: n_ctx_orig_yarn  = 8192
+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       = ?B
+llm_load_print_meta: model ftype      = Q8_0
+llm_load_print_meta: model params     = 27.23 B
+llm_load_print_meta: model size       = 26.94 GiB (8.50 BPW) 
+llm_load_print_meta: general.name     = gemma-2-27b-it
+llm_load_print_meta: BOS token        = 2 '<bos>'
+llm_load_print_meta: EOS token        = 1 '<eos>'
+llm_load_print_meta: UNK token        = 3 '<unk>'
+llm_load_print_meta: PAD token        = 0 '<pad>'
+llm_load_print_meta: LF token         = 227 '<0x0A>'
+llm_load_print_meta: EOT token        = 107 '<end_of_turn>'
+llm_load_print_meta: max token length = 93
+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 =    0.45 MiB
+llm_load_tensors: offloading 37 repeating layers to GPU
+llm_load_tensors: offloaded 37/47 layers to GPU
+llm_load_tensors:        CPU buffer size = 27591.06 MiB
+llm_load_tensors:      CUDA0 buffer size = 21231.35 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  = 10000.0
+llama_new_context_with_model: freq_scale = 1
+llama_kv_cache_init:  CUDA_Host KV buffer size =    36.00 MiB
+llama_kv_cache_init:      CUDA0 KV buffer size =   148.00 MiB
+llama_new_context_with_model: KV self size  =  184.00 MiB, K (f16):   92.00 MiB, V (f16):   92.00 MiB
+llama_new_context_with_model:  CUDA_Host  output buffer size =     0.98 MiB
+llama_new_context_with_model:      CUDA0 compute buffer size =  1704.31 MiB
+llama_new_context_with_model:  CUDA_Host compute buffer size =    10.01 MiB
+llama_new_context_with_model: graph nodes  = 1709
+llama_new_context_with_model: graph splits = 121
+
+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 126.52 ms
+compute_imatrix: computing over 128 chunks with batch_size 512
+compute_imatrix: 1.97 seconds per pass - ETA 4.20 minutes
+[1]16.8060,[2]10.0388,[3]8.6860,[4]10.8551,[5]10.6816,[6]8.5806,[7]9.5274,[8]10.0565,[9]10.8304,
+save_imatrix: stored collected data after 10 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat
+[10]9.2142,[11]9.3787,[12]10.2510,[13]11.1856,[14]11.6859,[15]12.6435,[16]13.3837,[17]13.5288,[18]14.3690,[19]13.6140,
+save_imatrix: stored collected data after 20 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat
+[20]13.8628,[21]14.2014,[22]13.9559,[23]14.2008,[24]14.3894,[25]14.7491,[26]14.2443,[27]14.6796,[28]15.1159,[29]14.8935,
+save_imatrix: stored collected data after 30 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat
+[30]14.7781,[31]13.7545,[32]13.2662,[33]13.0484,[34]12.8644,[35]12.7189,[36]12.9116,[37]12.9272,[38]12.9377,[39]13.1664,
+save_imatrix: stored collected data after 40 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat
+[40]13.3908,[41]13.7261,[42]14.3809,[43]15.0405,[44]15.6225,[45]16.0831,[46]15.7899,[47]15.8613,[48]16.2568,[49]16.5927,
+save_imatrix: stored collected data after 50 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat
+[50]16.2484,[51]16.2360,[52]16.3678,[53]16.6269,[54]16.9455,[55]17.2366,[56]17.3912,[57]17.4234,[58]17.5112,[59]17.2045,
+save_imatrix: stored collected data after 60 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat
+[60]16.9565,[61]16.6263,[62]16.5667,[63]16.5981,[64]16.5561,[65]16.4957,[66]16.4538,[67]16.3132,[68]16.1684,[69]16.2471,
+save_imatrix: stored collected data after 70 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat
+[70]16.2391,[71]16.2548,[72]16.2723,[73]16.2170,[74]16.1591,[75]16.1024,[76]16.1478,[77]16.2332,[78]16.2062,[79]16.1531,
+save_imatrix: stored collected data after 80 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat
+[80]16.2953,[81]16.3488,[82]16.3215,[83]16.3536,[84]16.4559,[85]16.2309,[86]16.1677,[87]16.0908,[88]16.1282,[89]16.2161,
+save_imatrix: stored collected data after 90 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat
+[90]16.2864,[91]16.1855,[92]16.0805,[93]15.9261,[94]15.7792,[95]15.6751,[96]15.5429,[97]15.3907,[98]15.2958,[99]15.3161,
+save_imatrix: stored collected data after 100 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat
+[100]15.3213,[101]15.4828,[102]15.6273,[103]15.7855,[104]16.1017,[105]16.3573,[106]16.4126,[107]16.4446,[108]16.5071,[109]16.4200,
+save_imatrix: stored collected data after 110 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat
+[110]16.3406,[111]16.1420,[112]15.9301,[113]16.0263,[114]16.0351,[115]16.0151,[116]16.0227,[117]16.0788,[118]16.0826,[119]16.0903,
+save_imatrix: stored collected data after 120 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat
+[120]16.0969,[121]16.1101,[122]16.0417,[123]16.1350,[124]16.2564,[125]16.3835,[126]16.5740,[127]16.7243,[128]16.8485,
+save_imatrix: stored collected data after 128 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat
+
+llama_print_timings:        load time =    4135.04 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 =  235882.68 ms / 65536 tokens (    3.60 ms per token,   277.83 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 =  239612.08 ms / 65537 tokens
+
+Final estimate: PPL = 16.8485 +/- 0.33601