Upload imatrix.log with huggingface_hub

imatrix.log

@@ -0,0 +1,129 @@
+build: 3787 (6026da52) with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
+llama_model_loader: loaded meta data with 35 key-value pairs and 963 tensors from Qwen2.5-72B-Instruct-IMat-GGUF/Qwen2.5-72B-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              = qwen2
+llama_model_loader: - kv   1:                               general.type str              = model
+llama_model_loader: - kv   2:                               general.name str              = Qwen2.5 72B Instruct
+llama_model_loader: - kv   3:                           general.finetune str              = Instruct
+llama_model_loader: - kv   4:                           general.basename str              = Qwen2.5
+llama_model_loader: - kv   5:                         general.size_label str              = 72B
+llama_model_loader: - kv   6:                            general.license str              = other
+llama_model_loader: - kv   7:                       general.license.name str              = qwen
+llama_model_loader: - kv   8:                       general.license.link str              = https://huggingface.co/Qwen/Qwen2.5-7...
+llama_model_loader: - kv   9:                   general.base_model.count u32              = 1
+llama_model_loader: - kv  10:                  general.base_model.0.name str              = Qwen2.5 72B
+llama_model_loader: - kv  11:          general.base_model.0.organization str              = Qwen
+llama_model_loader: - kv  12:              general.base_model.0.repo_url str              = https://huggingface.co/Qwen/Qwen2.5-72B
+llama_model_loader: - kv  13:                               general.tags arr[str,2]       = ["chat", "text-generation"]
+llama_model_loader: - kv  14:                          general.languages arr[str,1]       = ["en"]
+llama_model_loader: - kv  15:                          qwen2.block_count u32              = 80
+llama_model_loader: - kv  16:                       qwen2.context_length u32              = 32768
+llama_model_loader: - kv  17:                     qwen2.embedding_length u32              = 8192
+llama_model_loader: - kv  18:                  qwen2.feed_forward_length u32              = 29568
+llama_model_loader: - kv  19:                 qwen2.attention.head_count u32              = 64
+llama_model_loader: - kv  20:              qwen2.attention.head_count_kv u32              = 8
+llama_model_loader: - kv  21:                       qwen2.rope.freq_base f32              = 1000000.000000
+llama_model_loader: - kv  22:     qwen2.attention.layer_norm_rms_epsilon f32              = 0.000001
+llama_model_loader: - kv  23:                          general.file_type u32              = 7
+llama_model_loader: - kv  24:                       tokenizer.ggml.model str              = gpt2
+llama_model_loader: - kv  25:                         tokenizer.ggml.pre str              = qwen2
+llama_model_loader: - kv  26:                      tokenizer.ggml.tokens arr[str,152064]  = ["!", "\"", "#", "$", "%", "&", "'", ...
+llama_model_loader: - kv  27:                  tokenizer.ggml.token_type arr[i32,152064]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
+llama_model_loader: - kv  28:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
+llama_model_loader: - kv  29:                tokenizer.ggml.eos_token_id u32              = 151645
+llama_model_loader: - kv  30:            tokenizer.ggml.padding_token_id u32              = 151643
+llama_model_loader: - kv  31:                tokenizer.ggml.bos_token_id u32              = 151643
+llama_model_loader: - kv  32:               tokenizer.ggml.add_bos_token bool             = false
+llama_model_loader: - kv  33:                    tokenizer.chat_template str              = {%- if tools %}\n    {{- '<|im_start|>...
+llama_model_loader: - kv  34:               general.quantization_version u32              = 2
+llama_model_loader: - type  f32:  401 tensors
+llama_model_loader: - type q8_0:  562 tensors
+llm_load_vocab: special tokens cache size = 22
+llm_load_vocab: token to piece cache size = 0.9310 MB
+llm_load_print_meta: format           = GGUF V3 (latest)
+llm_load_print_meta: arch             = qwen2
+llm_load_print_meta: vocab type       = BPE
+llm_load_print_meta: n_vocab          = 152064
+llm_load_print_meta: n_merges         = 151387
+llm_load_print_meta: vocab_only       = 0
+llm_load_print_meta: n_ctx_train      = 32768
+llm_load_print_meta: n_embd           = 8192
+llm_load_print_meta: n_layer          = 80
+llm_load_print_meta: n_head           = 64
+llm_load_print_meta: n_head_kv        = 8
+llm_load_print_meta: n_rot            = 128
+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            = 8
+llm_load_print_meta: n_embd_k_gqa     = 1024
+llm_load_print_meta: n_embd_v_gqa     = 1024
+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             = 29568
+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  = 1000000.0
+llm_load_print_meta: freq_scale_train = 1
+llm_load_print_meta: n_ctx_orig_yarn  = 32768
+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       = 70B
+llm_load_print_meta: model ftype      = Q8_0
+llm_load_print_meta: model params     = 72.71 B
+llm_load_print_meta: model size       = 71.95 GiB (8.50 BPW) 
+llm_load_print_meta: general.name     = Qwen2.5 72B Instruct
+llm_load_print_meta: BOS token        = 151643 '<|endoftext|>'
+llm_load_print_meta: EOS token        = 151645 '<|im_end|>'
+llm_load_print_meta: PAD token        = 151643 '<|endoftext|>'
+llm_load_print_meta: LF token         = 148848 'ÄĬ'
+llm_load_print_meta: EOT token        = 151645 '<|im_end|>'
+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 =    0.85 MiB
+llm_load_tensors: offloading 24 repeating layers to GPU
+llm_load_tensors: offloaded 24/81 layers to GPU
+llm_load_tensors:        CPU buffer size = 73677.66 MiB
+llm_load_tensors:      CUDA0 buffer size = 21345.94 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:  CUDA_Host KV buffer size =   112.00 MiB
+llama_kv_cache_init:      CUDA0 KV buffer size =    48.00 MiB
+llama_new_context_with_model: KV self size  =  160.00 MiB, K (f16):   80.00 MiB, V (f16):   80.00 MiB
+llama_new_context_with_model:  CUDA_Host  output buffer size =     0.58 MiB
+llama_new_context_with_model:      CUDA0 compute buffer size =  1575.25 MiB
+llama_new_context_with_model:  CUDA_Host compute buffer size =    17.01 MiB
+llama_new_context_with_model: graph nodes  = 2806
+llama_new_context_with_model: graph splits = 788
+
+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 125.949 ms
+compute_imatrix: computing over 128 chunks with batch_size 512
+compute_imatrix: 9.39 seconds per pass - ETA 20.03 minutes
+[1]4.0467,[2]2.9873,[3]2.8087,[4]3.0234,[5]2.9891,[6]2.7538,[7]2.9255,[8]2.9496,[9]3.3081,[10]3.2863,[11]3.3080,[12]3.6255,[13]4.0152,[14]4.2567,[15]4.6175,[16]4.8913,[17]5.1014,[18]5.4834,[19]5.3059,[20]5.4344,[21]5.4322,[22]5.4811,[23]5.4042,[24]5.5849,[25]5.7222,[26]5.6376,[27]5.4498,[28]5.1735,[29]5.0485,[30]5.0490,[31]4.9413,[32]4.7763,[33]4.6960,[34]4.6488,[35]4.6337,[36]4.6216,[37]4.6191,[38]4.6656,[39]4.6504,[40]4.7819,[41]4.8328,[42]4.6855,[43]4.5342,[44]4.4345,[45]4.3131,[46]4.3076,[47]4.2861,[48]4.3629,[49]4.4574,[50]4.5277,[51]4.4941,[52]4.5846,[53]4.6879,[54]4.7710,[55]4.8245,[56]4.8975,[57]4.9536,[58]5.0200,[59]5.0692,[60]5.1019,[61]5.1107,[62]5.1081,[63]5.1540,[64]5.2393,[65]5.2118,[66]5.2220,[67]5.2454,[68]5.2070,[69]5.1820,[70]5.1878,[71]5.1802,[72]5.1822,[73]5.1937,[74]5.1624,[75]5.1332,[76]5.1107,[77]5.1126,[78]5.1093,[79]5.1015,[80]5.0576,[81]5.0862,[82]5.0871,[83]5.0631,[84]5.0764,[85]5.0904,[86]5.0784,[87]5.0733,[88]5.0705,[89]5.0957,[90]5.1264,[91]5.1309,[92]5.1142,[93]5.0933,[94]5.0644,[95]5.0430,[96]5.0226,[97]4.9991,[98]4.9784,[99]4.9671,[100]4.9869,[101]5.0155,[102]5.0910,[103]5.1626,[104]5.2165,[105]5.3081,[106]5.3701,[107]5.3980,[108]5.4013,[109]5.4127,[110]5.4034,[111]5.3518,[112]5.2911,[113]5.2462,[114]5.2897,[115]5.3100,[116]5.3263,[117]5.3479,[118]5.3805,[119]5.3877,[120]5.3941,[121]5.4189,[122]5.3992,[123]5.4158,[124]5.3764,[125]5.3364,[126]5.2911,[127]5.2408,[128]5.1974,
+Final estimate: PPL = 5.1974 +/- 0.06975
+
+llama_perf_context_print:        load time =   39800.68 ms
+llama_perf_context_print: prompt eval time =  809653.10 ms / 65536 tokens (   12.35 ms per token,    80.94 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 =  841419.99 ms / 65537 tokens