Upload imatrix.log with huggingface_hub

imatrix.log

@@ -0,0 +1,139 @@
+llama_model_loader: loaded meta data with 23 key-value pairs and 479 tensors from Qwen2-57B-A14B-Instruct-IMat-GGUF/Qwen2-57B-A14B-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              = qwen2moe
+llama_model_loader: - kv   1:                               general.name str              = Qwen2-57B-A14B-Instruct
+llama_model_loader: - kv   2:                       qwen2moe.block_count u32              = 28
+llama_model_loader: - kv   3:                    qwen2moe.context_length u32              = 32768
+llama_model_loader: - kv   4:                  qwen2moe.embedding_length u32              = 3584
+llama_model_loader: - kv   5:               qwen2moe.feed_forward_length u32              = 20480
+llama_model_loader: - kv   6:              qwen2moe.attention.head_count u32              = 28
+llama_model_loader: - kv   7:           qwen2moe.attention.head_count_kv u32              = 4
+llama_model_loader: - kv   8:                    qwen2moe.rope.freq_base f32              = 1000000.000000
+llama_model_loader: - kv   9:  qwen2moe.attention.layer_norm_rms_epsilon f32              = 0.000001
+llama_model_loader: - kv  10:                 qwen2moe.expert_used_count u32              = 8
+llama_model_loader: - kv  11:                          general.file_type u32              = 7
+llama_model_loader: - kv  12:                      qwen2moe.expert_count u32              = 64
+llama_model_loader: - kv  13:                       tokenizer.ggml.model str              = gpt2
+llama_model_loader: - kv  14:                         tokenizer.ggml.pre str              = qwen2
+llama_model_loader: - kv  15:                      tokenizer.ggml.tokens arr[str,151936]  = ["!", "\"", "#", "$", "%", "&", "'", ...
+llama_model_loader: - kv  16:                  tokenizer.ggml.token_type arr[i32,151936]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
+llama_model_loader: - kv  17:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
+llama_model_loader: - kv  18:                tokenizer.ggml.eos_token_id u32              = 151645
+llama_model_loader: - kv  19:            tokenizer.ggml.padding_token_id u32              = 151643
+llama_model_loader: - kv  20:                tokenizer.ggml.bos_token_id u32              = 151643
+llama_model_loader: - kv  21:                    tokenizer.chat_template str              = {% for message in messages %}{% if lo...
+llama_model_loader: - kv  22:               general.quantization_version u32              = 2
+llama_model_loader: - type  f32:  197 tensors
+llama_model_loader: - type q8_0:  282 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             = qwen2moe
+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           = 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             = 20480
+llm_load_print_meta: n_expert         = 64
+llm_load_print_meta: n_expert_used    = 8
+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_ctx_orig_yarn  = 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      = Q8_0
+llm_load_print_meta: model params     = 57.41 B
+llm_load_print_meta: model size       = 56.83 GiB (8.50 BPW) 
+llm_load_print_meta: general.name     = Qwen2-57B-A14B-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: GGML_CUDA_FORCE_MMQ:   no
+ggml_cuda_init: CUDA_USE_TENSOR_CORES: yes
+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 =    0.43 MiB
+llm_load_tensors: offloading 10 repeating layers to GPU
+llm_load_tensors: offloaded 10/29 layers to GPU
+llm_load_tensors:        CPU buffer size = 58190.19 MiB
+llm_load_tensors:      CUDA0 buffer size = 20388.09 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
+llama_kv_cache_init:  CUDA_Host KV buffer size =    18.00 MiB
+llama_kv_cache_init:      CUDA0 KV buffer size =    10.00 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 =   862.52 MiB
+llama_new_context_with_model:  CUDA_Host compute buffer size =     8.01 MiB
+llama_new_context_with_model: graph nodes  = 1910
+llama_new_context_with_model: graph splits = 346
+
+system_info: n_threads = 32 / 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 182.937 ms
+compute_imatrix: computing over 128 chunks with batch_size 512
+compute_imatrix: 4.26 seconds per pass - ETA 9.08 minutes
+[1]4.9575,[2]3.4740,[3]3.1781,[4]3.5055,[5]3.4223,[6]3.1119,[7]3.2700,[8]3.2929,[9]3.7110,
+save_imatrix: stored collected data after 10 chunks in Qwen2-57B-A14B-Instruct-IMat-GGUF/imatrix.dat
+[10]3.6668,[11]3.6189,[12]3.9895,[13]4.4287,[14]4.6725,[15]5.0404,[16]5.3116,[17]5.4825,[18]5.6501,[19]5.4929,
+save_imatrix: stored collected data after 20 chunks in Qwen2-57B-A14B-Instruct-IMat-GGUF/imatrix.dat
+[20]5.6098,[21]5.6066,[22]5.6538,[23]5.6008,[24]5.8175,[25]5.9804,[26]5.8777,[27]5.9822,[28]6.0379,[29]6.1864,
+save_imatrix: stored collected data after 30 chunks in Qwen2-57B-A14B-Instruct-IMat-GGUF/imatrix.dat
+[30]6.1506,[31]5.9725,[32]5.7566,[33]5.6509,[34]5.5608,[35]5.5154,[36]5.5215,[37]5.5629,[38]5.6044,[39]5.5722,
+save_imatrix: stored collected data after 40 chunks in Qwen2-57B-A14B-Instruct-IMat-GGUF/imatrix.dat
+[40]5.6990,[41]5.7423,[42]5.9444,[43]6.1088,[44]6.2754,[45]6.4090,[46]6.5149,[47]6.4206,[48]6.4557,[49]6.5417,
+save_imatrix: stored collected data after 50 chunks in Qwen2-57B-A14B-Instruct-IMat-GGUF/imatrix.dat
+[50]6.6096,[51]6.5266,[52]6.5961,[53]6.7232,[54]6.8086,[55]6.8662,[56]6.9126,[57]6.9567,[58]6.9946,[59]7.0255,
+save_imatrix: stored collected data after 60 chunks in Qwen2-57B-A14B-Instruct-IMat-GGUF/imatrix.dat
+[60]7.0625,[61]7.0266,[62]6.9920,[63]7.0473,[64]7.1158,[65]7.0680,[66]7.0670,[67]7.0863,[68]7.0229,[69]6.9689,
+save_imatrix: stored collected data after 70 chunks in Qwen2-57B-A14B-Instruct-IMat-GGUF/imatrix.dat
+[70]6.9623,[71]6.9463,[72]6.9431,[73]6.9588,[74]6.9001,[75]6.8524,[76]6.8061,[77]6.7868,[78]6.7740,[79]6.7511,
+save_imatrix: stored collected data after 80 chunks in Qwen2-57B-A14B-Instruct-IMat-GGUF/imatrix.dat
+[80]6.6806,[81]6.7077,[82]6.7016,[83]6.6616,[84]6.6788,[85]6.6970,[86]6.6610,[87]6.6396,[88]6.6213,[89]6.6418,
+save_imatrix: stored collected data after 90 chunks in Qwen2-57B-A14B-Instruct-IMat-GGUF/imatrix.dat
+[90]6.6657,[91]6.6567,[92]6.6193,[93]6.5897,[94]6.5406,[95]6.5056,[96]6.4673,[97]6.4356,[98]6.3961,[99]6.3680,
+save_imatrix: stored collected data after 100 chunks in Qwen2-57B-A14B-Instruct-IMat-GGUF/imatrix.dat
+[100]6.3803,[101]6.4046,[102]6.4739,[103]6.5511,[104]6.6015,[105]6.7051,[106]6.7713,[107]6.8045,[108]6.7913,[109]6.7797,
+save_imatrix: stored collected data after 110 chunks in Qwen2-57B-A14B-Instruct-IMat-GGUF/imatrix.dat
+[110]6.7746,[111]6.7326,[112]6.6627,[113]6.6131,[114]6.6655,[115]6.6699,[116]6.6776,[117]6.6962,[118]6.7280,[119]6.7310,
+save_imatrix: stored collected data after 120 chunks in Qwen2-57B-A14B-Instruct-IMat-GGUF/imatrix.dat
+[120]6.7268,[121]6.7397,[122]6.7134,[123]6.7513,[124]6.7813,[125]6.8029,[126]6.8390,[127]6.8695,[128]6.9092,
+save_imatrix: stored collected data after 128 chunks in Qwen2-57B-A14B-Instruct-IMat-GGUF/imatrix.dat
+
+llama_print_timings:        load time =    7331.82 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 =  541654.75 ms / 65536 tokens (    8.26 ms per token,   120.99 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 =  545922.50 ms / 65537 tokens
+
+Final estimate: PPL = 6.9092 +/- 0.09472