Upload imatrix.log with huggingface_hub

imatrix.log

@@ -0,0 +1,127 @@
+build: 3825 (1e436302) with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
+llama_model_loader: loaded meta data with 31 key-value pairs and 147 tensors from Llama-3.2-1B-Instruct-IMat-GGUF/Llama-3.2-1B-Instruct.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.type str              = model
+llama_model_loader: - kv   2:                               general.name str              = Llama 3.2 1B Instruct
+llama_model_loader: - kv   3:                           general.finetune str              = Instruct
+llama_model_loader: - kv   4:                           general.basename str              = Llama-3.2
+llama_model_loader: - kv   5:                         general.size_label str              = 1B
+llama_model_loader: - kv   6:                            general.license str              = llama3.2
+llama_model_loader: - kv   7:                               general.tags arr[str,6]       = ["facebook", "meta", "pytorch", "llam...
+llama_model_loader: - kv   8:                          general.languages arr[str,8]       = ["en", "de", "fr", "it", "pt", "hi", ...
+llama_model_loader: - kv   9:                          llama.block_count u32              = 16
+llama_model_loader: - kv  10:                       llama.context_length u32              = 131072
+llama_model_loader: - kv  11:                     llama.embedding_length u32              = 2048
+llama_model_loader: - kv  12:                  llama.feed_forward_length u32              = 8192
+llama_model_loader: - kv  13:                 llama.attention.head_count u32              = 32
+llama_model_loader: - kv  14:              llama.attention.head_count_kv u32              = 8
+llama_model_loader: - kv  15:                       llama.rope.freq_base f32              = 500000.000000
+llama_model_loader: - kv  16:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
+llama_model_loader: - kv  17:                 llama.attention.key_length u32              = 64
+llama_model_loader: - kv  18:               llama.attention.value_length u32              = 64
+llama_model_loader: - kv  19:                          general.file_type u32              = 7
+llama_model_loader: - kv  20:                           llama.vocab_size u32              = 128256
+llama_model_loader: - kv  21:                 llama.rope.dimension_count u32              = 64
+llama_model_loader: - kv  22:                       tokenizer.ggml.model str              = gpt2
+llama_model_loader: - kv  23:                         tokenizer.ggml.pre str              = llama-bpe
+llama_model_loader: - kv  24:                      tokenizer.ggml.tokens arr[str,128256]  = ["!", "\"", "#", "$", "%", "&", "'", ...
+llama_model_loader: - kv  25:                  tokenizer.ggml.token_type arr[i32,128256]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
+llama_model_loader: - kv  26:                      tokenizer.ggml.merges arr[str,280147]  = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
+llama_model_loader: - kv  27:                tokenizer.ggml.bos_token_id u32              = 128000
+llama_model_loader: - kv  28:                tokenizer.ggml.eos_token_id u32              = 128009
+llama_model_loader: - kv  29:                    tokenizer.chat_template str              = {{- bos_token }}\n{%- if custom_tools ...
+llama_model_loader: - kv  30:               general.quantization_version u32              = 2
+llama_model_loader: - type  f32:   34 tensors
+llama_model_loader: - type q8_0:  113 tensors
+llm_load_vocab: special tokens cache size = 256
+llm_load_vocab: token to piece cache size = 0.7999 MB
+llm_load_print_meta: format           = GGUF V3 (latest)
+llm_load_print_meta: arch             = llama
+llm_load_print_meta: vocab type       = BPE
+llm_load_print_meta: n_vocab          = 128256
+llm_load_print_meta: n_merges         = 280147
+llm_load_print_meta: vocab_only       = 0
+llm_load_print_meta: n_ctx_train      = 131072
+llm_load_print_meta: n_embd           = 2048
+llm_load_print_meta: n_layer          = 16
+llm_load_print_meta: n_head           = 32
+llm_load_print_meta: n_head_kv        = 8
+llm_load_print_meta: n_rot            = 64
+llm_load_print_meta: n_swa            = 0
+llm_load_print_meta: n_embd_head_k    = 64
+llm_load_print_meta: n_embd_head_v    = 64
+llm_load_print_meta: n_gqa            = 4
+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-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             = 8192
+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  = 500000.0
+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: ssm_dt_b_c_rms   = 0
+llm_load_print_meta: model type       = ?B
+llm_load_print_meta: model ftype      = Q8_0
+llm_load_print_meta: model params     = 1.24 B
+llm_load_print_meta: model size       = 1.22 GiB (8.50 BPW) 
+llm_load_print_meta: general.name     = Llama 3.2 1B Instruct
+llm_load_print_meta: BOS token        = 128000 '<|begin_of_text|>'
+llm_load_print_meta: EOS token        = 128009 '<|eot_id|>'
+llm_load_print_meta: LF token         = 128 'Ä'
+llm_load_print_meta: EOT token        = 128009 '<|eot_id|>'
+llm_load_print_meta: EOM token        = 128008 '<|eom_id|>'
+llm_load_print_meta: EOG token        = 128008 '<|eom_id|>'
+llm_load_print_meta: EOG token        = 128009 '<|eot_id|>'
+llm_load_print_meta: max token length = 256
+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 =    0.14 MiB
+llm_load_tensors: offloading 16 repeating layers to GPU
+llm_load_tensors: offloading non-repeating layers to GPU
+llm_load_tensors: offloaded 17/17 layers to GPU
+llm_load_tensors:        CPU buffer size =   266.16 MiB
+llm_load_tensors:      CUDA0 buffer size =  1252.42 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  = 500000.0
+llama_new_context_with_model: freq_scale = 1
+llama_kv_cache_init:      CUDA0 KV buffer size =    16.00 MiB
+llama_new_context_with_model: KV self size  =   16.00 MiB, K (f16):    8.00 MiB, V (f16):    8.00 MiB
+llama_new_context_with_model:  CUDA_Host  output buffer size =     0.49 MiB
+llama_new_context_with_model:      CUDA0 compute buffer size =   254.50 MiB
+llama_new_context_with_model:  CUDA_Host compute buffer size =     5.01 MiB
+llama_new_context_with_model: graph nodes  = 518
+llama_new_context_with_model: graph splits = 2
+
+system_info: n_threads = 25 (n_threads_batch = 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 | RISCV_VECT = 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 41.228 ms
+compute_imatrix: computing over 125 chunks with batch_size 512
+compute_imatrix: 0.27 seconds per pass - ETA 0.55 minutes
+[1]10.1003,[2]8.7720,[3]7.6214,[4]9.5709,[5]9.9748,[6]8.1803,[7]8.9931,[8]9.8189,[9]9.8290,[10]8.8016,[11]9.5176,[12]10.4471,[13]11.0957,[14]11.5884,[15]11.9080,[16]12.2895,[17]12.5080,[18]12.0233,[19]11.3547,[20]11.3911,[21]11.7520,[22]11.6329,[23]12.1215,[24]12.1673,[25]12.5908,[26]12.6425,[27]12.8542,[28]13.3951,[29]13.4406,[30]13.4958,[31]12.6603,[32]11.9421,[33]11.5444,[34]11.1900,[35]11.4356,[36]11.7923,[37]11.7055,[38]11.7950,[39]12.0074,[40]12.1217,[41]12.5260,[42]12.9512,[43]13.4504,[44]13.7702,[45]14.1608,[46]13.8227,[47]14.0141,[48]14.1086,[49]14.2237,[50]13.9614,[51]14.0995,[52]14.3164,[53]14.4866,[54]14.6511,[55]14.7375,[56]14.7230,[57]14.7250,[58]14.6895,[59]14.7109,[60]14.5806,[61]14.4905,[62]14.5499,[63]14.5756,[64]14.4582,[65]14.4160,[66]14.4073,[67]14.3236,[68]14.2669,[69]14.2115,[70]14.1506,[71]14.0868,[72]14.0321,[73]13.9478,[74]13.8268,[75]13.8096,[76]13.8170,[77]13.7423,[78]13.7053,[79]13.7641,[80]13.7904,[81]13.7380,[82]13.7433,[83]13.7881,[84]13.5757,[85]13.6192,[86]13.6431,[87]13.6291,[88]13.6536,[89]13.6300,[90]13.4896,[91]13.3255,[92]13.1715,[93]13.0364,[94]12.9000,[95]12.7725,[96]12.6925,[97]12.6859,[98]12.7142,[99]12.8512,[100]12.9701,[101]13.0520,[102]13.2456,[103]13.2737,[104]13.3239,[105]13.1657,[106]13.1447,[107]13.0611,[108]12.9922,[109]12.9131,[110]12.9894,[111]13.0774,[112]13.0733,[113]13.0816,[114]13.1270,[115]13.1905,[116]13.1885,[117]13.1985,[118]13.2109,[119]13.1053,[120]13.2112,[121]13.3304,[122]13.3987,[123]13.5091,[124]13.6236,[125]13.7181,
+Final estimate: PPL = 13.7181 +/- 0.21967
+
+llama_perf_context_print:        load time =     892.41 ms
+llama_perf_context_print: prompt eval time =   18897.20 ms / 64000 tokens (    0.30 ms per token,  3386.75 tokens per second)
+llama_perf_context_print:        eval time =       0.00 ms /     1 runs   (    0.00 ms per token,      inf tokens per second)
+llama_perf_context_print:       total time =   20329.73 ms / 64001 tokens