Upload imatrix.log with huggingface_hub

imatrix.log

@@ -0,0 +1,128 @@
+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 34 key-value pairs and 339 tensors from Qwen2.5-Math-7B-Instruct-IMat-GGUF/Qwen2.5-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              = Qwen2.5 Math 7B Instruct
+llama_model_loader: - kv   3:                           general.finetune str              = Instruct
+llama_model_loader: - kv   4:                           general.basename str              = Qwen2.5-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.license.link str              = https://huggingface.co/Qwen/Qwen2.5-M...
+llama_model_loader: - kv   8:                   general.base_model.count u32              = 1
+llama_model_loader: - kv   9:                  general.base_model.0.name str              = Qwen2.5 Math 7B
+llama_model_loader: - kv  10:          general.base_model.0.organization str              = Qwen
+llama_model_loader: - kv  11:              general.base_model.0.repo_url str              = https://huggingface.co/Qwen/Qwen2.5-M...
+llama_model_loader: - kv  12:                               general.tags arr[str,2]       = ["chat", "text-generation"]
+llama_model_loader: - kv  13:                          general.languages arr[str,1]       = ["en"]
+llama_model_loader: - kv  14:                          qwen2.block_count u32              = 28
+llama_model_loader: - kv  15:                       qwen2.context_length u32              = 4096
+llama_model_loader: - kv  16:                     qwen2.embedding_length u32              = 3584
+llama_model_loader: - kv  17:                  qwen2.feed_forward_length u32              = 18944
+llama_model_loader: - kv  18:                 qwen2.attention.head_count u32              = 28
+llama_model_loader: - kv  19:              qwen2.attention.head_count_kv u32              = 4
+llama_model_loader: - kv  20:                       qwen2.rope.freq_base f32              = 10000.000000
+llama_model_loader: - kv  21:     qwen2.attention.layer_norm_rms_epsilon f32              = 0.000001
+llama_model_loader: - kv  22:                          general.file_type u32              = 7
+llama_model_loader: - kv  23:                       tokenizer.ggml.model str              = gpt2
+llama_model_loader: - kv  24:                         tokenizer.ggml.pre str              = qwen2
+llama_model_loader: - kv  25:                      tokenizer.ggml.tokens arr[str,152064]  = ["!", "\"", "#", "$", "%", "&", "'", ...
+llama_model_loader: - kv  26:                  tokenizer.ggml.token_type arr[i32,152064]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
+llama_model_loader: - kv  27:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
+llama_model_loader: - kv  28:                tokenizer.ggml.eos_token_id u32              = 151645
+llama_model_loader: - kv  29:            tokenizer.ggml.padding_token_id u32              = 151643
+llama_model_loader: - kv  30:                tokenizer.ggml.bos_token_id u32              = 151643
+llama_model_loader: - kv  31:               tokenizer.ggml.add_bos_token bool             = false
+llama_model_loader: - kv  32:                    tokenizer.chat_template str              = {%- if tools %}\n    {{- '<|im_start|>...
+llama_model_loader: - kv  33:               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 = 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      = 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: 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     = 7.62 B
+llm_load_print_meta: model size       = 7.54 GiB (8.50 BPW) 
+llm_load_print_meta: general.name     = Qwen2.5 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 (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 131.5 ms
+compute_imatrix: computing over 128 chunks with batch_size 512
+compute_imatrix: 0.69 seconds per pass - ETA 1.47 minutes
+[1]28.7884,[2]18.5953,[3]16.3479,[4]20.1465,[5]19.5615,[6]20.3099,[7]21.3095,[8]20.8118,[9]23.2923,[10]22.3917,[11]20.9308,[12]24.0642,[13]28.6004,[14]30.3579,[15]34.0691,[16]36.3716,[17]38.2215,[18]42.9121,[19]43.4196,[20]43.9599,[21]48.1262,[22]49.1824,[23]49.4922,[24]51.4308,[25]53.2112,[26]54.2365,[27]58.6712,[28]61.5836,[29]64.8420,[30]65.0070,[31]65.2907,[32]62.9179,[33]60.2049,[34]57.5294,[35]55.2869,[36]63.1691,[37]74.8448,[38]76.4167,[39]75.7432,[40]77.4725,[41]77.4437,[42]81.9817,[43]85.9957,[44]90.6828,[45]94.4227,[46]95.9006,[47]94.7120,[48]94.5773,[49]93.7139,[50]93.1522,[51]91.8615,[52]91.9521,[53]94.8851,[54]95.4016,[55]98.0729,[56]99.5771,[57]99.4158,[58]100.0638,[59]100.1002,[60]100.4101,[61]98.6097,[62]97.6243,[63]97.8416,[64]99.3454,[65]97.8466,[66]96.3482,[67]95.1378,[68]92.5769,[69]91.1216,[70]89.6284,[71]87.5463,[72]86.2201,[73]84.8736,[74]82.5846,[75]80.3171,[76]78.4186,[77]77.2179,[78]76.3259,[79]75.0681,[80]73.5364,[81]73.1254,[82]72.6815,[83]71.3370,[84]71.2249,[85]70.7469,[86]70.5564,[87]69.6381,[88]69.1689,[89]69.6594,[90]69.8000,[91]69.6801,[92]68.1260,[93]66.6620,[94]64.8501,[95]63.2899,[96]61.9002,[97]60.3517,[98]58.9511,[99]58.9191,[100]58.8341,[101]58.8857,[102]59.9250,[103]61.2395,[104]62.2741,[105]64.0173,[106]65.3101,[107]65.5034,[108]64.8326,[109]64.9166,[110]65.0537,[111]64.1082,[112]63.1934,[113]62.8422,[114]63.3379,[115]63.4099,[116]63.3883,[117]63.7308,[118]64.1004,[119]63.9750,[120]63.7882,[121]63.7849,[122]62.9774,[123]63.4501,[124]64.2247,[125]65.0395,[126]66.1319,[127]66.9557,[128]67.6565,
+Final estimate: PPL = 67.6565 +/- 1.42709
+
+llama_perf_context_print:        load time =    2621.56 ms
+llama_perf_context_print: prompt eval time =   65452.29 ms / 65536 tokens (    1.00 ms per token,  1001.28 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 =   68380.69 ms / 65537 tokens