Upload imatrix.log with huggingface_hub

imatrix.log

@@ -0,0 +1,137 @@
+main: build = 3086 (554c247c)
+main: built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
+main: seed  = 1717699094
+llama_model_loader: loaded meta data with 21 key-value pairs and 338 tensors from Qwen2-1.5B-Instruct-IMat-GGUF/Qwen2-1.5B-Instruct.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.name str              = Qwen2-1.5B-Instruct
+llama_model_loader: - kv   2:                          qwen2.block_count u32              = 28
+llama_model_loader: - kv   3:                       qwen2.context_length u32              = 32768
+llama_model_loader: - kv   4:                     qwen2.embedding_length u32              = 1536
+llama_model_loader: - kv   5:                  qwen2.feed_forward_length u32              = 8960
+llama_model_loader: - kv   6:                 qwen2.attention.head_count u32              = 12
+llama_model_loader: - kv   7:              qwen2.attention.head_count_kv u32              = 2
+llama_model_loader: - kv   8:                       qwen2.rope.freq_base f32              = 1000000.000000
+llama_model_loader: - kv   9:     qwen2.attention.layer_norm_rms_epsilon f32              = 0.000001
+llama_model_loader: - kv  10:                          general.file_type u32              = 0
+llama_model_loader: - kv  11:                       tokenizer.ggml.model str              = gpt2
+llama_model_loader: - kv  12:                         tokenizer.ggml.pre str              = qwen2
+llama_model_loader: - kv  13:                      tokenizer.ggml.tokens arr[str,151936]  = ["!", "\"", "#", "$", "%", "&", "'", ...
+llama_model_loader: - kv  14:                  tokenizer.ggml.token_type arr[i32,151936]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
+llama_model_loader: - kv  15:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
+llama_model_loader: - kv  16:                tokenizer.ggml.eos_token_id u32              = 151645
+llama_model_loader: - kv  17:            tokenizer.ggml.padding_token_id u32              = 151643
+llama_model_loader: - kv  18:                tokenizer.ggml.bos_token_id u32              = 151643
+llama_model_loader: - kv  19:                    tokenizer.chat_template str              = {% for message in messages %}{% if lo...
+llama_model_loader: - kv  20:               general.quantization_version u32              = 2
+llama_model_loader: - type  f32:  338 tensors
+llm_load_vocab: special tokens cache size = 293
+llm_load_vocab: token to piece cache size = 0.9338 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: n_ctx_train      = 32768
+llm_load_print_meta: n_embd           = 1536
+llm_load_print_meta: n_head           = 12
+llm_load_print_meta: n_head_kv        = 2
+llm_load_print_meta: n_layer          = 28
+llm_load_print_meta: n_rot            = 128
+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  = 1000000.0
+llm_load_print_meta: freq_scale_train = 1
+llm_load_print_meta: n_yarn_orig_ctx  = 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: model type       = ?B
+llm_load_print_meta: model ftype      = all F32
+llm_load_print_meta: model params     = 1.54 B
+llm_load_print_meta: model size       = 5.75 GiB (32.00 BPW) 
+llm_load_print_meta: general.name     = Qwen2-1.5B-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|>'
+ggml_cuda_init: failed to initialize CUDA: no CUDA-capable device is detected
+llm_load_tensors: ggml ctx size =    0.16 MiB
+llm_load_tensors: offloading 0 repeating layers to GPU
+llm_load_tensors: offloaded 0/29 layers to GPU
+llm_load_tensors:        CPU buffer size =  5888.80 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
+ggml_cuda_host_malloc: failed to allocate 14.00 MiB of pinned memory: no CUDA-capable device is detected
+llama_kv_cache_init:        CPU 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
+ggml_cuda_host_malloc: failed to allocate 0.58 MiB of pinned memory: no CUDA-capable device is detected
+llama_new_context_with_model:        CPU  output buffer size =     0.58 MiB
+ggml_cuda_host_malloc: failed to allocate 299.75 MiB of pinned memory: no CUDA-capable device is detected
+llama_new_context_with_model:  CUDA_Host compute buffer size =   299.75 MiB
+llama_new_context_with_model: graph nodes  = 986
+llama_new_context_with_model: graph splits = 1
+
+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 186.265 ms
+compute_imatrix: computing over 128 chunks with batch_size 512
+ggml_cuda_host_malloc: failed to allocate 296.75 MiB of pinned memory: no CUDA-capable device is detected
+compute_imatrix: 2.29 seconds per pass - ETA 4.87 minutes
+[1]7.1794,[2]5.3199,[3]5.0981,[4]5.9752,[5]5.7835,[6]5.2552,[7]5.7864,[8]6.0622,[9]6.6684,
+save_imatrix: stored collected data after 10 chunks in Qwen2-1.5B-Instruct-IMat-GGUF/imatrix.dat
+[10]6.3131,[11]6.1593,[12]6.6159,[13]7.3010,[14]7.5457,[15]8.1246,[16]8.5172,[17]8.6254,[18]9.1089,[19]8.7735,
+save_imatrix: stored collected data after 20 chunks in Qwen2-1.5B-Instruct-IMat-GGUF/imatrix.dat
+[20]8.8735,[21]8.9815,[22]8.9399,[23]8.8281,[24]9.1095,[25]9.2579,[26]9.1932,[27]9.4461,[28]9.6855,[29]9.9663,
+save_imatrix: stored collected data after 30 chunks in Qwen2-1.5B-Instruct-IMat-GGUF/imatrix.dat
+[30]9.8592,[31]9.4931,[32]9.0860,[33]8.8363,[34]8.6863,[35]8.5233,[36]8.5521,[37]8.6577,[38]8.7731,[39]8.8116,
+save_imatrix: stored collected data after 40 chunks in Qwen2-1.5B-Instruct-IMat-GGUF/imatrix.dat
+[40]8.9578,[41]9.0102,[42]9.3965,[43]9.7582,[44]10.0824,[45]10.3412,[46]10.4822,[47]10.2945,[48]10.3357,[49]10.4302,
+save_imatrix: stored collected data after 50 chunks in Qwen2-1.5B-Instruct-IMat-GGUF/imatrix.dat
+[50]10.4853,[51]10.3433,[52]10.4344,[53]10.6284,[54]10.7379,[55]10.8603,[56]10.8917,[57]10.9144,[58]10.9545,[59]10.9503,
+save_imatrix: stored collected data after 60 chunks in Qwen2-1.5B-Instruct-IMat-GGUF/imatrix.dat
+[60]10.9594,[61]10.8658,[62]10.8120,[63]10.8641,[64]10.9371,[65]10.8705,[66]10.8679,[67]10.8664,[68]10.7898,[69]10.7536,
+save_imatrix: stored collected data after 70 chunks in Qwen2-1.5B-Instruct-IMat-GGUF/imatrix.dat
+[70]10.7331,[71]10.6848,[72]10.6564,[73]10.6672,[74]10.5752,[75]10.4921,[76]10.4074,[77]10.3769,[78]10.3653,[79]10.3378,
+save_imatrix: stored collected data after 80 chunks in Qwen2-1.5B-Instruct-IMat-GGUF/imatrix.dat
+[80]10.2752,[81]10.2969,[82]10.2784,[83]10.2086,[84]10.2478,[85]10.2686,[86]10.2003,[87]10.1497,[88]10.1223,[89]10.1420,
+save_imatrix: stored collected data after 90 chunks in Qwen2-1.5B-Instruct-IMat-GGUF/imatrix.dat
+[90]10.1469,[91]10.1228,[92]10.0276,[93]9.9300,[94]9.8304,[95]9.7334,[96]9.6549,[97]9.5611,[98]9.4757,[99]9.4329,
+save_imatrix: stored collected data after 100 chunks in Qwen2-1.5B-Instruct-IMat-GGUF/imatrix.dat
+[100]9.4376,[101]9.4618,[102]9.5825,[103]9.6851,[104]9.7748,[105]9.9226,[106]10.0201,[107]10.0571,[108]10.0244,[109]10.0150,
+save_imatrix: stored collected data after 110 chunks in Qwen2-1.5B-Instruct-IMat-GGUF/imatrix.dat
+[110]10.0121,[111]9.9965,[112]9.9513,[113]9.9758,[114]10.0245,[115]10.0159,[116]10.0171,[117]10.0315,[118]10.0678,[119]10.0564,
+save_imatrix: stored collected data after 120 chunks in Qwen2-1.5B-Instruct-IMat-GGUF/imatrix.dat
+[120]10.0484,[121]10.0499,[122]10.0063,[123]10.0592,[124]10.1353,[125]10.1928,[126]10.2749,[127]10.3396,[128]10.4061,
+save_imatrix: stored collected data after 128 chunks in Qwen2-1.5B-Instruct-IMat-GGUF/imatrix.dat
+
+llama_print_timings:        load time =    2730.80 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 = 1324946.47 ms / 65536 tokens (   20.22 ms per token,    49.46 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 = 1327865.09 ms / 65537 tokens
+
+Final estimate: PPL = 10.4061 +/- 0.15435