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 338 tensors from Qwen2.5-Math-1.5B-Instruct-IMat-GGUF/Qwen2.5-Math-1.5B-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 1.5B 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              = 1.5B
+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 1.5B
+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              = 1536
+llama_model_loader: - kv  17:                  qwen2.feed_forward_length u32              = 8960
+llama_model_loader: - kv  18:                 qwen2.attention.head_count u32              = 12
+llama_model_loader: - kv  19:              qwen2.attention.head_count_kv u32              = 2
+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,151936]  = ["!", "\"", "#", "$", "%", "&", "'", ...
+llama_model_loader: - kv  26:                  tokenizer.ggml.token_type arr[i32,151936]  = [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:  197 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          = 151936
+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           = 1536
+llm_load_print_meta: n_layer          = 28
+llm_load_print_meta: n_head           = 12
+llm_load_print_meta: n_head_kv        = 2
+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            = 6
+llm_load_print_meta: n_embd_k_gqa     = 256
+llm_load_print_meta: n_embd_v_gqa     = 256
+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             = 8960
+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     = 1.54 B
+llm_load_print_meta: model size       = 1.53 GiB (8.50 BPW) 
+llm_load_print_meta: general.name     = Qwen2.5 Math 1.5B 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 =   236.47 MiB
+llm_load_tensors:      CUDA0 buffer size =  1564.63 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 =    14.00 MiB
+llama_new_context_with_model: KV self size  =   14.00 MiB, K (f16):    7.00 MiB, V (f16):    7.00 MiB
+llama_new_context_with_model:  CUDA_Host  output buffer size =     0.58 MiB
+llama_new_context_with_model:      CUDA0 compute buffer size =   299.75 MiB
+llama_new_context_with_model:  CUDA_Host compute buffer size =     4.01 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 135.209 ms
+compute_imatrix: computing over 128 chunks with batch_size 512
+compute_imatrix: 0.39 seconds per pass - ETA 0.82 minutes
+[1]76.3534,[2]44.0303,[3]31.6350,[4]37.0097,[5]36.9772,[6]40.0268,[7]38.6530,[8]39.8474,[9]41.0920,[10]39.7125,[11]35.6288,[12]37.8969,[13]41.1135,[14]41.3761,[15]45.6199,[16]46.1514,[17]47.9945,[18]51.2402,[19]50.3270,[20]49.3483,[21]58.2344,[22]62.7025,[23]62.9567,[24]64.2388,[25]63.9855,[26]65.5560,[27]68.5196,[28]71.2349,[29]73.9642,[30]78.4475,[31]83.2389,[32]83.4088,[33]79.8979,[34]76.4622,[35]72.9805,[36]82.5251,[37]94.8080,[38]101.6563,[39]101.6932,[40]102.5662,[41]102.5259,[42]105.8845,[43]107.2122,[44]108.9494,[45]110.5805,[46]111.8862,[47]109.9830,[48]107.9592,[49]106.6537,[50]105.1476,[51]104.0614,[52]103.1540,[53]106.6089,[54]106.5142,[55]108.6973,[56]108.7682,[57]107.6624,[58]106.6510,[59]105.5954,[60]105.6071,[61]104.0959,[62]103.6760,[63]104.2393,[64]105.8032,[65]105.3703,[66]103.8000,[67]102.4559,[68]100.5003,[69]100.1043,[70]98.5139,[71]96.2124,[72]94.4408,[73]93.1674,[74]90.8032,[75]88.3730,[76]86.1229,[77]84.7100,[78]83.7798,[79]83.0234,[80]81.6884,[81]81.0501,[82]80.2872,[83]79.1985,[84]79.5808,[85]79.0158,[86]80.0719,[87]79.2331,[88]78.5611,[89]78.4093,[90]78.2067,[91]77.6363,[92]75.3036,[93]73.1595,[94]70.9507,[95]68.8827,[96]66.9942,[97]65.1730,[98]63.3927,[99]64.1802,[100]64.3003,[101]64.0369,[102]64.5606,[103]64.9922,[104]65.3317,[105]66.1201,[106]66.9926,[107]67.1652,[108]66.6607,[109]66.7239,[110]66.8040,[111]65.5796,[112]64.5900,[113]64.3368,[114]64.3996,[115]64.6678,[116]64.7223,[117]65.0348,[118]65.3331,[119]65.3733,[120]65.2025,[121]65.0798,[122]64.4611,[123]64.6898,[124]65.0316,[125]65.5398,[126]66.2413,[127]66.7434,[128]67.0922,
+Final estimate: PPL = 67.0922 +/- 1.51836
+
+llama_perf_context_print:        load time =    1153.45 ms
+llama_perf_context_print: prompt eval time =   30925.78 ms / 65536 tokens (    0.47 ms per token,  2119.14 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 =   32688.54 ms / 65537 tokens