Upload imatrix.log with huggingface_hub

imatrix.log

@@ -0,0 +1,146 @@
+llama_model_loader: loaded meta data with 24 key-value pairs and 291 tensors from llm-compiler-7b-ftd-IMat-GGUF/llm-compiler-7b-ftd.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              = llm-compiler-7b-ftd
+llama_model_loader: - kv   2:                          llama.block_count u32              = 32
+llama_model_loader: - kv   3:                       llama.context_length u32              = 16384
+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              = 32
+llama_model_loader: - kv   8:                       llama.rope.freq_base f32              = 1000000.000000
+llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
+llama_model_loader: - kv  10:                          general.file_type u32              = 7
+llama_model_loader: - kv  11:                           llama.vocab_size u32              = 32000
+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,32000]   = ["<unk>", "<s>", "</s>", "<0x00>", "<...
+llama_model_loader: - kv  16:                      tokenizer.ggml.scores arr[f32,32000]   = [0.000000, 0.000000, 0.000000, 0.0000...
+llama_model_loader: - kv  17:                  tokenizer.ggml.token_type arr[i32,32000]   = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
+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.add_bos_token bool             = true
+llama_model_loader: - kv  22:               tokenizer.ggml.add_eos_token bool             = false
+llama_model_loader: - kv  23:               general.quantization_version u32              = 2
+llama_model_loader: - type  f32:   65 tensors
+llama_model_loader: - type q8_0:  226 tensors
+llm_load_vocab: special tokens cache size = 259
+llm_load_vocab: token to piece cache size = 0.1684 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          = 32000
+llm_load_print_meta: n_merges         = 0
+llm_load_print_meta: n_ctx_train      = 16384
+llm_load_print_meta: n_embd           = 4096
+llm_load_print_meta: n_head           = 32
+llm_load_print_meta: n_head_kv        = 32
+llm_load_print_meta: n_layer          = 32
+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            = 1
+llm_load_print_meta: n_embd_k_gqa     = 4096
+llm_load_print_meta: n_embd_v_gqa     = 4096
+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             = 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  = 1000000.0
+llm_load_print_meta: freq_scale_train = 1
+llm_load_print_meta: n_ctx_orig_yarn  = 16384
+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       = 7B
+llm_load_print_meta: model ftype      = Q8_0
+llm_load_print_meta: model params     = 6.74 B
+llm_load_print_meta: model size       = 6.67 GiB (8.50 BPW) 
+llm_load_print_meta: general.name     = llm-compiler-7b-ftd
+llm_load_print_meta: BOS token        = 1 '<s>'
+llm_load_print_meta: EOS token        = 2 '</s>'
+llm_load_print_meta: UNK token        = 0 '<unk>'
+llm_load_print_meta: LF token         = 13 '<0x0A>'
+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 =    0.27 MiB
+llm_load_tensors: offloading 32 repeating layers to GPU
+llm_load_tensors: offloading non-repeating layers to GPU
+llm_load_tensors: offloaded 33/33 layers to GPU
+llm_load_tensors:        CPU buffer size =   132.81 MiB
+llm_load_tensors:      CUDA0 buffer size =  6695.84 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  = 1000000.0
+llama_new_context_with_model: freq_scale = 1
+llama_kv_cache_init:      CUDA0 KV buffer size =   256.00 MiB
+llama_new_context_with_model: KV self size  =  256.00 MiB, K (f16):  128.00 MiB, V (f16):  128.00 MiB
+llama_new_context_with_model:  CUDA_Host  output buffer size =     0.12 MiB
+llama_new_context_with_model:      CUDA0 compute buffer size =    70.50 MiB
+llama_new_context_with_model:  CUDA_Host compute buffer size =     9.01 MiB
+llama_new_context_with_model: graph nodes  = 1030
+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 95.108 ms
+compute_imatrix: computing over 151 chunks with batch_size 512
+compute_imatrix: 0.54 seconds per pass - ETA 1.35 minutes
+[1]8.5363,[2]6.5180,[3]6.5837,[4]8.0179,[5]9.0085,[6]9.0519,[7]8.4522,[8]9.2578,[9]9.5049,
+save_imatrix: stored collected data after 10 chunks in llm-compiler-7b-ftd-IMat-GGUF/imatrix.dat
+[10]10.1415,[11]10.0765,[12]8.7815,[13]8.5609,[14]8.9764,[15]9.5567,[16]9.6316,[17]10.0254,[18]10.2615,[19]10.4075,
+save_imatrix: stored collected data after 20 chunks in llm-compiler-7b-ftd-IMat-GGUF/imatrix.dat
+[20]10.5242,[21]10.8305,[22]10.2302,[23]9.6849,[24]9.7514,[25]9.9103,[26]9.8096,[27]9.5890,[28]9.7533,[29]9.9361,
+save_imatrix: stored collected data after 30 chunks in llm-compiler-7b-ftd-IMat-GGUF/imatrix.dat
+[30]10.1287,[31]10.1454,[32]10.3399,[33]10.4551,[34]10.7579,[35]10.8765,[36]10.7794,[37]10.2467,[38]9.8992,[39]9.7896,
+save_imatrix: stored collected data after 40 chunks in llm-compiler-7b-ftd-IMat-GGUF/imatrix.dat
+[40]9.7003,[41]9.5599,[42]9.4412,[43]9.2317,[44]9.1229,[45]8.9791,[46]9.0007,[47]9.0452,[48]9.1178,[49]9.2314,
+save_imatrix: stored collected data after 50 chunks in llm-compiler-7b-ftd-IMat-GGUF/imatrix.dat
+[50]9.2559,[51]9.5228,[52]9.7619,[53]9.9972,[54]10.2238,[55]10.3586,[56]10.2935,[57]10.1973,[58]10.2496,[59]10.3353,
+save_imatrix: stored collected data after 60 chunks in llm-compiler-7b-ftd-IMat-GGUF/imatrix.dat
+[60]10.4602,[61]10.3213,[62]10.3514,[63]10.4496,[64]10.5597,[65]10.6374,[66]10.6801,[67]10.7588,[68]10.8062,[69]10.7740,
+save_imatrix: stored collected data after 70 chunks in llm-compiler-7b-ftd-IMat-GGUF/imatrix.dat
+[70]10.7875,[71]10.7903,[72]10.7101,[73]10.6545,[74]10.5994,[75]10.5572,[76]10.5601,[77]10.5771,[78]10.5642,[79]10.5723,
+save_imatrix: stored collected data after 80 chunks in llm-compiler-7b-ftd-IMat-GGUF/imatrix.dat
+[80]10.6077,[81]10.5792,[82]10.5634,[83]10.4786,[84]10.4957,[85]10.5038,[86]10.4922,[87]10.5227,[88]10.5129,[89]10.4940,
+save_imatrix: stored collected data after 90 chunks in llm-compiler-7b-ftd-IMat-GGUF/imatrix.dat
+[90]10.4698,[91]10.4809,[92]10.4164,[93]10.4059,[94]10.3597,[95]10.3050,[96]10.3275,[97]10.3215,[98]10.3394,[99]10.3072,
+save_imatrix: stored collected data after 100 chunks in llm-compiler-7b-ftd-IMat-GGUF/imatrix.dat
+[100]10.2922,[101]10.3336,[102]10.2897,[103]10.2420,[104]10.2165,[105]10.2516,[106]10.2479,[107]10.2669,[108]10.3052,[109]10.1909,
+save_imatrix: stored collected data after 110 chunks in llm-compiler-7b-ftd-IMat-GGUF/imatrix.dat
+[110]10.1019,[111]10.0060,[112]9.9080,[113]9.8094,[114]9.7172,[115]9.6301,[116]9.5456,[117]9.4842,[118]9.5120,[119]9.5214,
+save_imatrix: stored collected data after 120 chunks in llm-compiler-7b-ftd-IMat-GGUF/imatrix.dat
+[120]9.5756,[121]9.6436,[122]9.7038,[123]9.7723,[124]9.8896,[125]10.0112,[126]10.0204,[127]10.0489,[128]9.9467,[129]9.9451,
+save_imatrix: stored collected data after 130 chunks in llm-compiler-7b-ftd-IMat-GGUF/imatrix.dat
+[130]9.9290,[131]9.9153,[132]9.8805,[133]9.8694,[134]9.8900,[135]9.9156,[136]9.9020,[137]9.8942,[138]9.9130,[139]9.9265,
+save_imatrix: stored collected data after 140 chunks in llm-compiler-7b-ftd-IMat-GGUF/imatrix.dat
+[140]9.9498,[141]9.9494,[142]9.9487,[143]9.9227,[144]9.8980,[145]9.9167,[146]9.9522,[147]9.9990,[148]10.0373,[149]10.0841,
+save_imatrix: stored collected data after 150 chunks in llm-compiler-7b-ftd-IMat-GGUF/imatrix.dat
+[150]10.1300,[151]10.1805,
+save_imatrix: stored collected data after 151 chunks in llm-compiler-7b-ftd-IMat-GGUF/imatrix.dat
+
+llama_print_timings:        load time =    1845.29 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 =   75945.00 ms / 77312 tokens (    0.98 ms per token,  1018.00 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 =   77714.38 ms / 77313 tokens
+
+Final estimate: PPL = 10.1805 +/- 0.14161