Upload imatrix.log with huggingface_hub

imatrix.log

@@ -0,0 +1,147 @@
+llama_model_loader: loaded meta data with 25 key-value pairs and 435 tensors from Yi-9B-Coder-IMat-GGUF/Yi-9B-Coder.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              = llama
+llama_model_loader: - kv   1:                               general.name str              = Yi-9B-Coder
+llama_model_loader: - kv   2:                          llama.block_count u32              = 48
+llama_model_loader: - kv   3:                       llama.context_length u32              = 4096
+llama_model_loader: - kv   4:                     llama.embedding_length u32              = 4096
+llama_model_loader: - kv   5:                  llama.feed_forward_length u32              = 11008
+llama_model_loader: - kv   6:                 llama.attention.head_count u32              = 32
+llama_model_loader: - kv   7:              llama.attention.head_count_kv u32              = 4
+llama_model_loader: - kv   8:                       llama.rope.freq_base f32              = 10000.000000
+llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32              = 0.000001
+llama_model_loader: - kv  10:                          general.file_type u32              = 7
+llama_model_loader: - kv  11:                           llama.vocab_size u32              = 64000
+llama_model_loader: - kv  12:                 llama.rope.dimension_count u32              = 128
+llama_model_loader: - kv  13:                       tokenizer.ggml.model str              = llama
+llama_model_loader: - kv  14:                         tokenizer.ggml.pre str              = default
+llama_model_loader: - kv  15:                      tokenizer.ggml.tokens arr[str,64000]   = ["<unk>", "<|startoftext|>", "<|endof...
+llama_model_loader: - kv  16:                      tokenizer.ggml.scores arr[f32,64000]   = [0.000000, 0.000000, 0.000000, 0.0000...
+llama_model_loader: - kv  17:                  tokenizer.ggml.token_type arr[i32,64000]   = [2, 3, 3, 3, 3, 3, 1, 1, 1, 3, 3, 3, ...
+llama_model_loader: - kv  18:                tokenizer.ggml.bos_token_id u32              = 1
+llama_model_loader: - kv  19:                tokenizer.ggml.eos_token_id u32              = 2
+llama_model_loader: - kv  20:            tokenizer.ggml.unknown_token_id u32              = 0
+llama_model_loader: - kv  21:            tokenizer.ggml.padding_token_id u32              = 2
+llama_model_loader: - kv  22:               tokenizer.ggml.add_bos_token bool             = false
+llama_model_loader: - kv  23:               tokenizer.ggml.add_eos_token bool             = false
+llama_model_loader: - kv  24:               general.quantization_version u32              = 2
+llama_model_loader: - type  f32:   97 tensors
+llama_model_loader: - type q8_0:  338 tensors
+llm_load_vocab: special tokens cache size = 267
+llm_load_vocab: token to piece cache size = 0.3834 MB
+llm_load_print_meta: format           = GGUF V3 (latest)
+llm_load_print_meta: arch             = llama
+llm_load_print_meta: vocab type       = SPM
+llm_load_print_meta: n_vocab          = 64000
+llm_load_print_meta: n_merges         = 0
+llm_load_print_meta: n_ctx_train      = 4096
+llm_load_print_meta: n_embd           = 4096
+llm_load_print_meta: n_head           = 32
+llm_load_print_meta: n_head_kv        = 4
+llm_load_print_meta: n_layer          = 48
+llm_load_print_meta: n_rot            = 128
+llm_load_print_meta: n_embd_head_k    = 128
+llm_load_print_meta: n_embd_head_v    = 128
+llm_load_print_meta: n_gqa            = 8
+llm_load_print_meta: n_embd_k_gqa     = 512
+llm_load_print_meta: n_embd_v_gqa     = 512
+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             = 11008
+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  = 10000.0
+llm_load_print_meta: freq_scale_train = 1
+llm_load_print_meta: n_ctx_orig_yarn  = 4096
+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       = 34B
+llm_load_print_meta: model ftype      = Q8_0
+llm_load_print_meta: model params     = 8.83 B
+llm_load_print_meta: model size       = 8.74 GiB (8.50 BPW) 
+llm_load_print_meta: general.name     = Yi-9B-Coder
+llm_load_print_meta: BOS token        = 1 '<|startoftext|>'
+llm_load_print_meta: EOS token        = 2 '<|endoftext|>'
+llm_load_print_meta: UNK token        = 0 '<unk>'
+llm_load_print_meta: PAD token        = 2 '<|endoftext|>'
+llm_load_print_meta: LF token         = 315 '<0x0A>'
+llm_load_print_meta: EOT token        = 2 '<|endoftext|>'
+llm_load_print_meta: max token length = 48
+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 =    0.41 MiB
+llm_load_tensors: offloading 48 repeating layers to GPU
+llm_load_tensors: offloading non-repeating layers to GPU
+llm_load_tensors: offloaded 49/49 layers to GPU
+llm_load_tensors:        CPU buffer size =   265.62 MiB
+llm_load_tensors:      CUDA0 buffer size =  8682.16 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:      CUDA0 KV buffer size =    48.00 MiB
+llama_new_context_with_model: KV self size  =   48.00 MiB, K (f16):   24.00 MiB, V (f16):   24.00 MiB
+llama_new_context_with_model:  CUDA_Host  output buffer size =     0.24 MiB
+llama_new_context_with_model:      CUDA0 compute buffer size =   133.00 MiB
+llama_new_context_with_model:  CUDA_Host compute buffer size =     9.01 MiB
+llama_new_context_with_model: graph nodes  = 1542
+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 99.517 ms
+compute_imatrix: computing over 146 chunks with batch_size 512
+compute_imatrix: 0.84 seconds per pass - ETA 2.05 minutes
+[1]23.1631,[2]14.0201,[3]13.8337,[4]15.6910,[5]15.9979,[6]16.4981,[7]12.7437,[8]15.7290,[9]15.6026,
+save_imatrix: stored collected data after 10 chunks in Yi-9B-Coder-IMat-GGUF/imatrix.dat
+[10]17.7123,[11]17.9431,[12]16.1416,[13]17.4802,[14]19.1233,[15]20.4605,[16]22.1210,[17]23.6353,[18]23.7434,[19]24.2365,
+save_imatrix: stored collected data after 20 chunks in Yi-9B-Coder-IMat-GGUF/imatrix.dat
+[20]25.1431,[21]23.3290,[22]23.0257,[23]23.8386,[24]24.4275,[25]24.5770,[26]23.8805,[27]24.7346,[28]25.5361,[29]26.9611,
+save_imatrix: stored collected data after 30 chunks in Yi-9B-Coder-IMat-GGUF/imatrix.dat
+[30]27.2252,[31]27.8791,[32]28.8940,[33]28.4610,[34]29.5878,[35]29.8153,[36]27.7273,[37]25.7733,[38]25.4580,[39]25.1857,
+save_imatrix: stored collected data after 40 chunks in Yi-9B-Coder-IMat-GGUF/imatrix.dat
+[40]24.8920,[41]24.4668,[42]23.8280,[43]23.6563,[44]23.0919,[45]22.8261,[46]22.7168,[47]22.9998,[48]23.3655,[49]23.7772,
+save_imatrix: stored collected data after 50 chunks in Yi-9B-Coder-IMat-GGUF/imatrix.dat
+[50]24.3145,[51]25.3137,[52]26.3264,[53]26.8731,[54]27.2882,[55]27.3431,[56]26.8452,[57]27.3450,[58]27.7474,[59]27.9772,
+save_imatrix: stored collected data after 60 chunks in Yi-9B-Coder-IMat-GGUF/imatrix.dat
+[60]27.5615,[61]27.1916,[62]27.2339,[63]27.6864,[64]28.2476,[65]28.7021,[66]28.8739,[67]29.1852,[68]29.3976,[69]29.5442,
+save_imatrix: stored collected data after 70 chunks in Yi-9B-Coder-IMat-GGUF/imatrix.dat
+[70]29.0318,[71]28.6331,[72]28.2458,[73]27.9526,[74]28.1002,[75]28.2634,[76]28.2284,[77]28.1927,[78]28.0400,[79]27.7259,
+save_imatrix: stored collected data after 80 chunks in Yi-9B-Coder-IMat-GGUF/imatrix.dat
+[80]27.4541,[81]27.0402,[82]27.0662,[83]26.8777,[84]26.6661,[85]26.6754,[86]26.4203,[87]26.1359,[88]25.9176,[89]25.9078,
+save_imatrix: stored collected data after 90 chunks in Yi-9B-Coder-IMat-GGUF/imatrix.dat
+[90]25.7199,[91]25.6668,[92]25.2476,[93]25.1993,[94]25.3737,[95]25.4112,[96]25.1537,[97]25.2050,[98]25.2597,[99]25.2710,
+save_imatrix: stored collected data after 100 chunks in Yi-9B-Coder-IMat-GGUF/imatrix.dat
+[100]24.8283,[101]24.8705,[102]24.7595,[103]24.8406,[104]24.8942,[105]25.0121,[106]24.7367,[107]24.4717,[108]24.1997,[109]23.9286,
+save_imatrix: stored collected data after 110 chunks in Yi-9B-Coder-IMat-GGUF/imatrix.dat
+[110]23.6729,[111]23.4221,[112]23.2042,[113]22.9676,[114]22.9006,[115]22.9633,[116]23.1386,[117]23.4191,[118]23.6960,[119]23.9039,
+save_imatrix: stored collected data after 120 chunks in Yi-9B-Coder-IMat-GGUF/imatrix.dat
+[120]24.3006,[121]24.6783,[122]24.8009,[123]24.8656,[124]24.6197,[125]24.6086,[126]24.4142,[127]24.3009,[128]24.1589,[129]24.2113,
+save_imatrix: stored collected data after 130 chunks in Yi-9B-Coder-IMat-GGUF/imatrix.dat
+[130]24.3836,[131]24.4772,[132]24.5623,[133]24.6763,[134]24.8778,[135]24.9183,[136]24.9277,[137]24.9997,[138]25.0110,[139]24.9703,
+save_imatrix: stored collected data after 140 chunks in Yi-9B-Coder-IMat-GGUF/imatrix.dat
+[140]25.1931,[141]25.3727,[142]25.5644,[143]25.8610,[144]26.1739,[145]26.4005,[146]26.6039,
+save_imatrix: stored collected data after 146 chunks in Yi-9B-Coder-IMat-GGUF/imatrix.dat
+
+llama_print_timings:        load time =    2143.24 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 =  113628.93 ms / 74752 tokens (    1.52 ms per token,   657.86 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 =  115527.76 ms / 74753 tokens
+
+Final estimate: PPL = 26.6039 +/- 0.59861