Upload imatrix.log with huggingface_hub

imatrix.log

@@ -0,0 +1,152 @@
+llama_model_loader: loaded meta data with 33 key-value pairs and 724 tensors from Hermes-3-Llama-3.1-70B-IMat-GGUF/Hermes-3-Llama-3.1-70B.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              = llama
+llama_model_loader: - kv   1:                               general.type str              = model
+llama_model_loader: - kv   2:                               general.name str              = Hermes 3 Llama 3.1 70B
+llama_model_loader: - kv   3:                           general.basename str              = Hermes-3-Llama-3.1
+llama_model_loader: - kv   4:                         general.size_label str              = 70B
+llama_model_loader: - kv   5:                            general.license str              = llama3
+llama_model_loader: - kv   6:                   general.base_model.count u32              = 1
+llama_model_loader: - kv   7:                  general.base_model.0.name str              = Meta Llama 3.1 70B
+llama_model_loader: - kv   8:          general.base_model.0.organization str              = Meta Llama
+llama_model_loader: - kv   9:              general.base_model.0.repo_url str              = https://huggingface.co/meta-llama/Met...
+llama_model_loader: - kv  10:                               general.tags arr[str,12]      = ["Llama-3", "instruct", "finetune", "...
+llama_model_loader: - kv  11:                          general.languages arr[str,1]       = ["en"]
+llama_model_loader: - kv  12:                          llama.block_count u32              = 80
+llama_model_loader: - kv  13:                       llama.context_length u32              = 131072
+llama_model_loader: - kv  14:                     llama.embedding_length u32              = 8192
+llama_model_loader: - kv  15:                  llama.feed_forward_length u32              = 28672
+llama_model_loader: - kv  16:                 llama.attention.head_count u32              = 64
+llama_model_loader: - kv  17:              llama.attention.head_count_kv u32              = 8
+llama_model_loader: - kv  18:                       llama.rope.freq_base f32              = 500000.000000
+llama_model_loader: - kv  19:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
+llama_model_loader: - kv  20:                          general.file_type u32              = 7
+llama_model_loader: - kv  21:                           llama.vocab_size u32              = 128256
+llama_model_loader: - kv  22:                 llama.rope.dimension_count u32              = 128
+llama_model_loader: - kv  23:                       tokenizer.ggml.model str              = gpt2
+llama_model_loader: - kv  24:                         tokenizer.ggml.pre str              = llama-bpe
+llama_model_loader: - kv  25:                      tokenizer.ggml.tokens arr[str,128256]  = ["!", "\"", "#", "$", "%", "&", "'", ...
+llama_model_loader: - kv  26:                  tokenizer.ggml.token_type arr[i32,128256]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
+llama_model_loader: - kv  27:                      tokenizer.ggml.merges arr[str,280147]  = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
+llama_model_loader: - kv  28:                tokenizer.ggml.bos_token_id u32              = 128000
+llama_model_loader: - kv  29:                tokenizer.ggml.eos_token_id u32              = 128039
+llama_model_loader: - kv  30:            tokenizer.ggml.padding_token_id u32              = 128001
+llama_model_loader: - kv  31:                    tokenizer.chat_template str              = {{bos_token}}{% for message in messag...
+llama_model_loader: - kv  32:               general.quantization_version u32              = 2
+llama_model_loader: - type  f32:  162 tensors
+llama_model_loader: - type q8_0:  562 tensors
+llm_load_vocab: special tokens cache size = 256
+llm_load_vocab: token to piece cache size = 0.7994 MB
+llm_load_print_meta: format           = GGUF V3 (latest)
+llm_load_print_meta: arch             = llama
+llm_load_print_meta: vocab type       = BPE
+llm_load_print_meta: n_vocab          = 128256
+llm_load_print_meta: n_merges         = 280147
+llm_load_print_meta: vocab_only       = 0
+llm_load_print_meta: n_ctx_train      = 131072
+llm_load_print_meta: n_embd           = 8192
+llm_load_print_meta: n_layer          = 80
+llm_load_print_meta: n_head           = 64
+llm_load_print_meta: n_head_kv        = 8
+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            = 8
+llm_load_print_meta: n_embd_k_gqa     = 1024
+llm_load_print_meta: n_embd_v_gqa     = 1024
+llm_load_print_meta: f_norm_eps       = 0.0e+00
+llm_load_print_meta: f_norm_rms_eps   = 1.0e-05
+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             = 28672
+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        = 0
+llm_load_print_meta: rope scaling     = linear
+llm_load_print_meta: freq_base_train  = 500000.0
+llm_load_print_meta: freq_scale_train = 1
+llm_load_print_meta: n_ctx_orig_yarn  = 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       = 70B
+llm_load_print_meta: model ftype      = Q8_0
+llm_load_print_meta: model params     = 70.55 B
+llm_load_print_meta: model size       = 69.82 GiB (8.50 BPW) 
+llm_load_print_meta: general.name     = Hermes 3 Llama 3.1 70B
+llm_load_print_meta: BOS token        = 128000 '<|begin_of_text|>'
+llm_load_print_meta: EOS token        = 128039 '<|im_end|>'
+llm_load_print_meta: PAD token        = 128001 '<|end_of_text|>'
+llm_load_print_meta: LF token         = 128 'Ä'
+llm_load_print_meta: EOT token        = 128039 '<|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 =    0.68 MiB
+llm_load_tensors: offloading 25 repeating layers to GPU
+llm_load_tensors: offloaded 25/81 layers to GPU
+llm_load_tensors:        CPU buffer size = 71494.28 MiB
+llm_load_tensors:      CUDA0 buffer size = 21676.57 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  = 500000.0
+llama_new_context_with_model: freq_scale = 1
+llama_kv_cache_init:  CUDA_Host KV buffer size =   110.00 MiB
+llama_kv_cache_init:      CUDA0 KV buffer size =    50.00 MiB
+llama_new_context_with_model: KV self size  =  160.00 MiB, K (f16):   80.00 MiB, V (f16):   80.00 MiB
+llama_new_context_with_model:  CUDA_Host  output buffer size =     0.49 MiB
+llama_new_context_with_model:      CUDA0 compute buffer size =  1331.12 MiB
+llama_new_context_with_model:  CUDA_Host compute buffer size =    17.01 MiB
+llama_new_context_with_model: graph nodes  = 2566
+llama_new_context_with_model: graph splits = 719
+
+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 42.062 ms
+compute_imatrix: computing over 125 chunks with batch_size 512
+compute_imatrix: 6.17 seconds per pass - ETA 12.85 minutes
+[1]5.5350,[2]4.3772,[3]3.8197,[4]4.6004,[5]4.6317,[6]3.9145,[7]3.8311,[8]4.2072,[9]4.4117,
+save_imatrix: stored collected data after 10 chunks in Hermes-3-Llama-3.1-70B-IMat-GGUF/imatrix.dat
+[10]4.0759,[11]4.4896,[12]4.9017,[13]5.2563,[14]5.6161,[15]5.8285,[16]6.1324,[17]6.2960,[18]6.0750,[19]5.8143,
+save_imatrix: stored collected data after 20 chunks in Hermes-3-Llama-3.1-70B-IMat-GGUF/imatrix.dat
+[20]5.8144,[21]5.8849,[22]5.8756,[23]6.0320,[24]6.0210,[25]6.3261,[26]6.3191,[27]5.9113,[28]5.5892,[29]5.5933,
+save_imatrix: stored collected data after 30 chunks in Hermes-3-Llama-3.1-70B-IMat-GGUF/imatrix.dat
+[30]5.5664,[31]5.3252,[32]5.1001,[33]4.9893,[34]4.9118,[35]4.9732,[36]5.0064,[37]4.9847,[38]5.0464,[39]5.1761,
+save_imatrix: stored collected data after 40 chunks in Hermes-3-Llama-3.1-70B-IMat-GGUF/imatrix.dat
+[40]5.2587,[41]5.0658,[42]4.8822,[43]4.7117,[44]4.5586,[45]4.4981,[46]4.4530,[47]4.5595,[48]4.6451,[49]4.7463,
+save_imatrix: stored collected data after 50 chunks in Hermes-3-Llama-3.1-70B-IMat-GGUF/imatrix.dat
+[50]4.6968,[51]4.7996,[52]4.9034,[53]4.9806,[54]5.0345,[55]5.0484,[56]5.0379,[57]5.0703,[58]5.0689,[59]5.0908,
+save_imatrix: stored collected data after 60 chunks in Hermes-3-Llama-3.1-70B-IMat-GGUF/imatrix.dat
+[60]5.0870,[61]5.0991,[62]5.1406,[63]5.1984,[64]5.1646,[65]5.1586,[66]5.1768,[67]5.1865,[68]5.1912,[69]5.1962,
+save_imatrix: stored collected data after 70 chunks in Hermes-3-Llama-3.1-70B-IMat-GGUF/imatrix.dat
+[70]5.2210,[71]5.2371,[72]5.2564,[73]5.2562,[74]5.2432,[75]5.2579,[76]5.2687,[77]5.2661,[78]5.2628,[79]5.3063,
+save_imatrix: stored collected data after 80 chunks in Hermes-3-Llama-3.1-70B-IMat-GGUF/imatrix.dat
+[80]5.3389,[81]5.3465,[82]5.3624,[83]5.3993,[84]5.3458,[85]5.3456,[86]5.3547,[87]5.3843,[88]5.4268,[89]5.4569,
+save_imatrix: stored collected data after 90 chunks in Hermes-3-Llama-3.1-70B-IMat-GGUF/imatrix.dat
+[90]5.4428,[91]5.4191,[92]5.3993,[93]5.3862,[94]5.3646,[95]5.3502,[96]5.3324,[97]5.3531,[98]5.3941,[99]5.4577,
+save_imatrix: stored collected data after 100 chunks in Hermes-3-Llama-3.1-70B-IMat-GGUF/imatrix.dat
+[100]5.5153,[101]5.5593,[102]5.6484,[103]5.6790,[104]5.7133,[105]5.6708,[106]5.6876,[107]5.6561,[108]5.5959,[109]5.5353,
+save_imatrix: stored collected data after 110 chunks in Hermes-3-Llama-3.1-70B-IMat-GGUF/imatrix.dat
+[110]5.5757,[111]5.6069,[112]5.6253,[113]5.6315,[114]5.6624,[115]5.7002,[116]5.7168,[117]5.7379,[118]5.7737,[119]5.7478,
+save_imatrix: stored collected data after 120 chunks in Hermes-3-Llama-3.1-70B-IMat-GGUF/imatrix.dat
+[120]5.6694,[121]5.5910,[122]5.5181,[123]5.4504,[124]5.3941,[125]5.3246,
+save_imatrix: stored collected data after 125 chunks in Hermes-3-Llama-3.1-70B-IMat-GGUF/imatrix.dat
+
+llama_print_timings:        load time =   32580.75 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 =  723343.07 ms / 64000 tokens (   11.30 ms per token,    88.48 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 =  751504.95 ms / 64001 tokens
+
+Final estimate: PPL = 5.3246 +/- 0.07650