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  = 1717701641
+llama_model_loader: loaded meta data with 21 key-value pairs and 339 tensors from Qwen2-7B-IMat-GGUF/Qwen2-7B.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              = Qwen2-7B
+llama_model_loader: - kv   2:                          qwen2.block_count u32              = 28
+llama_model_loader: - kv   3:                       qwen2.context_length u32              = 131072
+llama_model_loader: - kv   4:                     qwen2.embedding_length u32              = 3584
+llama_model_loader: - kv   5:                  qwen2.feed_forward_length u32              = 18944
+llama_model_loader: - kv   6:                 qwen2.attention.head_count u32              = 28
+llama_model_loader: - kv   7:              qwen2.attention.head_count_kv u32              = 4
+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,152064]  = ["!", "\"", "#", "$", "%", "&", "'", ...
+llama_model_loader: - kv  14:                  tokenizer.ggml.token_type arr[i32,152064]  = [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              = 151643
+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:  339 tensors
+llm_load_vocab: special tokens cache size = 421
+llm_load_vocab: token to piece cache size = 0.9352 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: n_ctx_train      = 131072
+llm_load_print_meta: n_embd           = 3584
+llm_load_print_meta: n_head           = 28
+llm_load_print_meta: n_head_kv        = 4
+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            = 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  = 1000000.0
+llm_load_print_meta: freq_scale_train = 1
+llm_load_print_meta: n_yarn_orig_ctx  = 131072
+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     = 7.62 B
+llm_load_print_meta: model size       = 28.37 GiB (32.00 BPW) 
+llm_load_print_meta: general.name     = Qwen2-7B
+llm_load_print_meta: BOS token        = 151643 '<|endoftext|>'
+llm_load_print_meta: EOS token        = 151643 '<|endoftext|>'
+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 = 29051.27 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 28.00 MiB of pinned memory: no CUDA-capable device is detected
+llama_kv_cache_init:        CPU 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
+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 304.00 MiB of pinned memory: no CUDA-capable device is detected
+llama_new_context_with_model:  CUDA_Host compute buffer size =   304.00 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 219.84 ms
+compute_imatrix: computing over 128 chunks with batch_size 512
+ggml_cuda_host_malloc: failed to allocate 297.00 MiB of pinned memory: no CUDA-capable device is detected
+compute_imatrix: 9.51 seconds per pass - ETA 20.28 minutes
+[1]4.9695,[2]3.4956,[3]3.3621,[4]3.8896,[5]3.7145,[6]3.4291,[7]3.7806,[8]3.8305,[9]4.3013,
+save_imatrix: stored collected data after 10 chunks in Qwen2-7B-IMat-GGUF/imatrix.dat
+[10]4.2099,[11]4.1511,[12]4.5306,[13]5.0314,[14]5.2554,[15]5.6803,[16]5.9606,[17]6.1168,[18]6.4450,[19]6.2415,
+save_imatrix: stored collected data after 20 chunks in Qwen2-7B-IMat-GGUF/imatrix.dat
+[20]6.3804,[21]6.4032,[22]6.4033,[23]6.2858,[24]6.4758,[25]6.5836,[26]6.4775,[27]6.6194,[28]6.7914,[29]6.9911,
+save_imatrix: stored collected data after 30 chunks in Qwen2-7B-IMat-GGUF/imatrix.dat
+[30]6.9298,[31]6.7189,[32]6.4771,[33]6.3337,[34]6.2158,[35]6.1245,[36]6.1354,[37]6.1898,[38]6.2409,[39]6.2013,
+save_imatrix: stored collected data after 40 chunks in Qwen2-7B-IMat-GGUF/imatrix.dat
+[40]6.3147,[41]6.3500,[42]6.5909,[43]6.8041,[44]6.9890,[45]7.1307,[46]7.2407,[47]7.1190,[48]7.1524,[49]7.2320,
+save_imatrix: stored collected data after 50 chunks in Qwen2-7B-IMat-GGUF/imatrix.dat
+[50]7.2824,[51]7.1739,[52]7.2446,[53]7.4010,[54]7.4913,[55]7.5556,[56]7.5991,[57]7.6379,[58]7.6734,[59]7.6771,
+save_imatrix: stored collected data after 60 chunks in Qwen2-7B-IMat-GGUF/imatrix.dat
+[60]7.7062,[61]7.6684,[62]7.6223,[63]7.6667,[64]7.7187,[65]7.6695,[66]7.6755,[67]7.6750,[68]7.6023,[69]7.5436,
+save_imatrix: stored collected data after 70 chunks in Qwen2-7B-IMat-GGUF/imatrix.dat
+[70]7.5346,[71]7.5090,[72]7.4932,[73]7.5051,[74]7.4376,[75]7.3725,[76]7.3107,[77]7.3027,[78]7.2859,[79]7.2677,
+save_imatrix: stored collected data after 80 chunks in Qwen2-7B-IMat-GGUF/imatrix.dat
+[80]7.1948,[81]7.2248,[82]7.2168,[83]7.1711,[84]7.1992,[85]7.2206,[86]7.1817,[87]7.1495,[88]7.1284,[89]7.1400,
+save_imatrix: stored collected data after 90 chunks in Qwen2-7B-IMat-GGUF/imatrix.dat
+[90]7.1519,[91]7.1352,[92]7.0875,[93]7.0347,[94]6.9792,[95]6.9292,[96]6.8871,[97]6.8372,[98]6.7926,[99]6.7673,
+save_imatrix: stored collected data after 100 chunks in Qwen2-7B-IMat-GGUF/imatrix.dat
+[100]6.7767,[101]6.8014,[102]6.8891,[103]6.9670,[104]7.0356,[105]7.1477,[106]7.2207,[107]7.2442,[108]7.2290,[109]7.2329,
+save_imatrix: stored collected data after 110 chunks in Qwen2-7B-IMat-GGUF/imatrix.dat
+[110]7.2256,[111]7.1904,[112]7.1256,[113]7.1172,[114]7.1617,[115]7.1613,[116]7.1671,[117]7.1805,[118]7.2152,[119]7.2127,
+save_imatrix: stored collected data after 120 chunks in Qwen2-7B-IMat-GGUF/imatrix.dat
+[120]7.2133,[121]7.2208,[122]7.1889,[123]7.2201,[124]7.2635,[125]7.2980,[126]7.3520,[127]7.3939,[128]7.4338,
+save_imatrix: stored collected data after 128 chunks in Qwen2-7B-IMat-GGUF/imatrix.dat
+
+llama_print_timings:        load time =   10640.81 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 = 1001145.84 ms / 65536 tokens (   15.28 ms per token,    65.46 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 = 1003431.71 ms / 65537 tokens
+
+Final estimate: PPL = 7.4338 +/- 0.10178