Upload imatrix.log with huggingface_hub

imatrix.log

@@ -0,0 +1,147 @@
+llama_model_loader: loaded meta data with 28 key-value pairs and 339 tensors from Qwen2-Math-7B-Instruct-IMat-GGUF/Qwen2-Math-7B-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 Math 7B Instruct
+llama_model_loader: - kv   3:                           general.finetune str              = Instruct
+llama_model_loader: - kv   4:                           general.basename str              = Qwen2-Math
+llama_model_loader: - kv   5:                         general.size_label str              = 7B
+llama_model_loader: - kv   6:                            general.license str              = apache-2.0
+llama_model_loader: - kv   7:                               general.tags arr[str,2]       = ["chat", "text-generation"]
+llama_model_loader: - kv   8:                          general.languages arr[str,1]       = ["en"]
+llama_model_loader: - kv   9:                          qwen2.block_count u32              = 28
+llama_model_loader: - kv  10:                       qwen2.context_length u32              = 4096
+llama_model_loader: - kv  11:                     qwen2.embedding_length u32              = 3584
+llama_model_loader: - kv  12:                  qwen2.feed_forward_length u32              = 18944
+llama_model_loader: - kv  13:                 qwen2.attention.head_count u32              = 28
+llama_model_loader: - kv  14:              qwen2.attention.head_count_kv u32              = 4
+llama_model_loader: - kv  15:                       qwen2.rope.freq_base f32              = 10000.000000
+llama_model_loader: - kv  16:     qwen2.attention.layer_norm_rms_epsilon f32              = 0.000001
+llama_model_loader: - kv  17:                          general.file_type u32              = 7
+llama_model_loader: - kv  18:                       tokenizer.ggml.model str              = gpt2
+llama_model_loader: - kv  19:                         tokenizer.ggml.pre str              = qwen2
+llama_model_loader: - kv  20:                      tokenizer.ggml.tokens arr[str,152064]  = ["!", "\"", "#", "$", "%", "&", "'", ...
+llama_model_loader: - kv  21:                  tokenizer.ggml.token_type arr[i32,152064]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
+llama_model_loader: - kv  22:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
+llama_model_loader: - kv  23:                tokenizer.ggml.eos_token_id u32              = 151645
+llama_model_loader: - kv  24:            tokenizer.ggml.padding_token_id u32              = 151643
+llama_model_loader: - kv  25:                tokenizer.ggml.bos_token_id u32              = 151643
+llama_model_loader: - kv  26:                    tokenizer.chat_template str              = {% for message in messages %}{% if lo...
+llama_model_loader: - kv  27:               general.quantization_version u32              = 2
+llama_model_loader: - type  f32:  141 tensors
+llama_model_loader: - type q8_0:  198 tensors
+llm_load_vocab: special tokens cache size = 3
+llm_load_vocab: token to piece cache size = 0.9308 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      = 4096
+llm_load_print_meta: n_embd           = 3584
+llm_load_print_meta: n_layer          = 28
+llm_load_print_meta: n_head           = 28
+llm_load_print_meta: n_head_kv        = 4
+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            = 7
+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             = 18944
+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  = 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       = ?B
+llm_load_print_meta: model ftype      = Q8_0
+llm_load_print_meta: model params     = 7.62 B
+llm_load_print_meta: model size       = 7.54 GiB (8.50 BPW) 
+llm_load_print_meta: general.name     = Qwen2 Math 7B 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 =    0.30 MiB
+llm_load_tensors: offloading 28 repeating layers to GPU
+llm_load_tensors: offloading non-repeating layers to GPU
+llm_load_tensors: offloaded 29/29 layers to GPU
+llm_load_tensors:        CPU buffer size =   552.23 MiB
+llm_load_tensors:      CUDA0 buffer size =  7165.44 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 =    28.00 MiB
+llama_new_context_with_model: KV self size  =   28.00 MiB, K (f16):   14.00 MiB, V (f16):   14.00 MiB
+llama_new_context_with_model:  CUDA_Host  output buffer size =     0.58 MiB
+llama_new_context_with_model:      CUDA0 compute buffer size =   304.00 MiB
+llama_new_context_with_model:  CUDA_Host compute buffer size =     8.01 MiB
+llama_new_context_with_model: graph nodes  = 986
+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 134.361 ms
+compute_imatrix: computing over 128 chunks with batch_size 512
+compute_imatrix: 0.70 seconds per pass - ETA 1.48 minutes
+[1]18.0590,[2]11.2011,[3]9.5899,[4]11.0452,[5]10.6825,[6]10.1264,[7]10.3411,[8]10.2988,[9]11.3523,
+save_imatrix: stored collected data after 10 chunks in Qwen2-Math-7B-Instruct-IMat-GGUF/imatrix.dat
+[10]10.7695,[11]10.1874,[12]11.2178,[13]12.6955,[14]13.1547,[15]14.7406,[16]15.3128,[17]15.8186,[18]17.0696,[19]16.6457,
+save_imatrix: stored collected data after 20 chunks in Qwen2-Math-7B-Instruct-IMat-GGUF/imatrix.dat
+[20]16.5903,[21]17.5665,[22]17.8621,[23]17.8537,[24]18.4056,[25]18.9724,[26]19.0466,[27]20.0233,[28]20.7322,[29]21.5257,
+save_imatrix: stored collected data after 30 chunks in Qwen2-Math-7B-Instruct-IMat-GGUF/imatrix.dat
+[30]21.4964,[31]21.5009,[32]20.7806,[33]20.2614,[34]19.6217,[35]19.2250,[36]19.5374,[37]20.5638,[38]21.1323,[39]21.3799,
+save_imatrix: stored collected data after 40 chunks in Qwen2-Math-7B-Instruct-IMat-GGUF/imatrix.dat
+[40]21.8888,[41]22.0149,[42]23.1586,[43]23.9396,[44]24.8159,[45]25.5009,[46]25.9405,[47]25.5047,[48]25.5574,[49]25.6802,
+save_imatrix: stored collected data after 50 chunks in Qwen2-Math-7B-Instruct-IMat-GGUF/imatrix.dat
+[50]25.6914,[51]25.3650,[52]25.5112,[53]26.1704,[54]26.4285,[55]27.0047,[56]27.2073,[57]27.2955,[58]27.4467,[59]27.3533,
+save_imatrix: stored collected data after 60 chunks in Qwen2-Math-7B-Instruct-IMat-GGUF/imatrix.dat
+[60]27.4828,[61]27.2780,[62]27.0881,[63]27.2735,[64]27.5393,[65]27.3328,[66]27.1882,[67]27.0582,[68]26.5715,[69]26.3075,
+save_imatrix: stored collected data after 70 chunks in Qwen2-Math-7B-Instruct-IMat-GGUF/imatrix.dat
+[70]26.0733,[71]25.7333,[72]25.5042,[73]25.3687,[74]24.9236,[75]24.4856,[76]24.0797,[77]23.8348,[78]23.6856,[79]23.5075,
+save_imatrix: stored collected data after 80 chunks in Qwen2-Math-7B-Instruct-IMat-GGUF/imatrix.dat
+[80]23.2261,[81]23.1967,[82]23.0807,[83]22.8498,[84]22.8795,[85]22.8150,[86]22.7432,[87]22.5736,[88]22.4748,[89]22.5302,
+save_imatrix: stored collected data after 90 chunks in Qwen2-Math-7B-Instruct-IMat-GGUF/imatrix.dat
+[90]22.6007,[91]22.5752,[92]22.2275,[93]22.0666,[94]21.7474,[95]21.4864,[96]21.3032,[97]21.0089,[98]20.7840,[99]20.7967,
+save_imatrix: stored collected data after 100 chunks in Qwen2-Math-7B-Instruct-IMat-GGUF/imatrix.dat
+[100]20.7888,[101]20.7904,[102]21.0381,[103]21.3159,[104]21.5573,[105]21.9637,[106]22.3012,[107]22.3843,[108]22.2405,[109]22.2636,
+save_imatrix: stored collected data after 110 chunks in Qwen2-Math-7B-Instruct-IMat-GGUF/imatrix.dat
+[110]22.2668,[111]22.0337,[112]21.7606,[113]21.6516,[114]21.7166,[115]21.7715,[116]21.8111,[117]21.8969,[118]21.9941,[119]21.9955,
+save_imatrix: stored collected data after 120 chunks in Qwen2-Math-7B-Instruct-IMat-GGUF/imatrix.dat
+[120]21.9721,[121]21.9586,[122]21.7884,[123]21.8810,[124]22.0677,[125]22.2065,[126]22.4323,[127]22.6586,[128]22.8041,
+save_imatrix: stored collected data after 128 chunks in Qwen2-Math-7B-Instruct-IMat-GGUF/imatrix.dat
+
+llama_print_timings:        load time =    2190.72 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 =   68655.99 ms / 65536 tokens (    1.05 ms per token,   954.56 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 =   71144.16 ms / 65537 tokens
+
+Final estimate: PPL = 22.8041 +/- 0.48532