Upload imatrix.log with huggingface_hub

imatrix.log

@@ -0,0 +1,143 @@
+main: build = 3058 (30e238b2)
+main: built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
+main: seed  = 1717189635
+llama_model_loader: loaded meta data with 25 key-value pairs and 723 tensors from Meta-Llama-3-70B-Instruct-abliterated-v3.5.Q8_0.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.name str              = Meta-Llama-3-70B-Instruct-abliterated...
+llama_model_loader: - kv   2:                          llama.block_count u32              = 80
+llama_model_loader: - kv   3:                       llama.context_length u32              = 8192
+llama_model_loader: - kv   4:                     llama.embedding_length u32              = 8192
+llama_model_loader: - kv   5:                  llama.feed_forward_length u32              = 28672
+llama_model_loader: - kv   6:                 llama.attention.head_count u32              = 64
+llama_model_loader: - kv   7:              llama.attention.head_count_kv u32              = 8
+llama_model_loader: - kv   8:                       llama.rope.freq_base f32              = 500000.000000
+llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
+llama_model_loader: - kv  10:                          general.file_type u32              = 7
+llama_model_loader: - kv  11:                           llama.vocab_size u32              = 128256
+llama_model_loader: - kv  12:                 llama.rope.dimension_count u32              = 128
+llama_model_loader: - kv  13:                       tokenizer.ggml.model str              = gpt2
+llama_model_loader: - kv  14:                         tokenizer.ggml.pre str              = llama-bpe
+llama_model_loader: - kv  15:                      tokenizer.ggml.tokens arr[str,128256]  = ["!", "\"", "#", "$", "%", "&", "'", ...
+llama_model_loader: - kv  16:                  tokenizer.ggml.token_type arr[i32,128256]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
+llama_model_loader: - kv  17:                      tokenizer.ggml.merges arr[str,280147]  = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
+llama_model_loader: - kv  18:                tokenizer.ggml.bos_token_id u32              = 128000
+llama_model_loader: - kv  19:                tokenizer.ggml.eos_token_id u32              = 128009
+llama_model_loader: - kv  20:                    tokenizer.chat_template str              = {% set loop_messages = messages %}{% ...
+llama_model_loader: - kv  21:               general.quantization_version u32              = 2
+llama_model_loader: - kv  22:                                   split.no u16              = 0
+llama_model_loader: - kv  23:                                split.count u16              = 0
+llama_model_loader: - kv  24:                        split.tensors.count i32              = 723
+llama_model_loader: - type  f32:  161 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 = 1.5928 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: n_ctx_train      = 8192
+llm_load_print_meta: n_embd           = 8192
+llm_load_print_meta: n_head           = 64
+llm_load_print_meta: n_head_kv        = 8
+llm_load_print_meta: n_layer          = 80
+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            = 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_yarn_orig_ctx  = 8192
+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     = Meta-Llama-3-70B-Instruct-abliterated-v3.5
+llm_load_print_meta: BOS token        = 128000 '<|begin_of_text|>'
+llm_load_print_meta: EOS token        = 128009 '<|eot_id|>'
+llm_load_print_meta: LF token         = 128 'Ä'
+llm_load_print_meta: EOT token        = 128009 '<|eot_id|>'
+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 =    0.74 MiB
+llm_load_tensors: offloading 23 repeating layers to GPU
+llm_load_tensors: offloaded 23/81 layers to GPU
+llm_load_tensors:        CPU buffer size = 71494.28 MiB
+llm_load_tensors:      CUDA0 buffer size = 19942.44 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 =   114.00 MiB
+llama_kv_cache_init:      CUDA0 KV buffer size =    46.00 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 = 631
+
+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 43.919 ms
+compute_imatrix: computing over 125 chunks with batch_size 512
+compute_imatrix: 5.03 seconds per pass - ETA 10.48 minutes
+[1]6.0299,[2]4.9246,[3]4.3350,[4]5.2603,[5]5.3356,[6]4.4245,[7]4.5128,[8]4.9960,[9]5.2117,
+save_imatrix: stored collected data after 10 chunks in Meta-Llama-3-70B-Instruct-abliterated-v3.5-IMat-GGUF/imatrix.dat
+[10]4.7652,[11]5.2864,[12]5.7827,[13]6.2313,[14]6.6502,[15]6.8963,[16]7.2162,[17]7.4192,[18]7.1377,[19]6.7935,
+save_imatrix: stored collected data after 20 chunks in Meta-Llama-3-70B-Instruct-abliterated-v3.5-IMat-GGUF/imatrix.dat
+[20]6.7903,[21]6.9130,[22]6.8973,[23]7.1753,[24]7.1424,[25]7.4987,[26]7.5153,[27]7.1168,[28]6.8683,[29]6.8810,
+save_imatrix: stored collected data after 30 chunks in Meta-Llama-3-70B-Instruct-abliterated-v3.5-IMat-GGUF/imatrix.dat
+[30]6.8435,[31]6.5088,[32]6.1927,[33]6.0464,[34]5.9345,[35]6.0107,[36]6.0695,[37]6.0254,[38]6.1048,[39]6.2725,
+save_imatrix: stored collected data after 40 chunks in Meta-Llama-3-70B-Instruct-abliterated-v3.5-IMat-GGUF/imatrix.dat
+[40]6.3660,[41]6.1815,[42]5.9769,[43]5.9275,[44]5.8078,[45]5.7785,[46]5.7151,[47]5.8522,[48]5.9435,[49]6.0425,
+save_imatrix: stored collected data after 50 chunks in Meta-Llama-3-70B-Instruct-abliterated-v3.5-IMat-GGUF/imatrix.dat
+[50]5.9779,[51]6.0886,[52]6.2123,[53]6.3082,[54]6.3799,[55]6.4696,[56]6.5283,[57]6.5963,[58]6.6250,[59]6.6484,
+save_imatrix: stored collected data after 60 chunks in Meta-Llama-3-70B-Instruct-abliterated-v3.5-IMat-GGUF/imatrix.dat
+[60]6.6355,[61]6.6356,[62]6.6859,[63]6.7479,[64]6.6837,[65]6.6598,[66]6.6695,[67]6.6561,[68]6.6521,[69]6.6417,
+save_imatrix: stored collected data after 70 chunks in Meta-Llama-3-70B-Instruct-abliterated-v3.5-IMat-GGUF/imatrix.dat
+[70]6.6508,[71]6.6521,[72]6.6629,[73]6.6454,[74]6.6165,[75]6.6284,[76]6.6360,[77]6.6234,[78]6.6200,[79]6.6617,
+save_imatrix: stored collected data after 80 chunks in Meta-Llama-3-70B-Instruct-abliterated-v3.5-IMat-GGUF/imatrix.dat
+[80]6.6900,[81]6.6857,[82]6.7030,[83]6.7294,[84]6.6462,[85]6.6509,[86]6.6529,[87]6.6708,[88]6.7142,[89]6.7299,
+save_imatrix: stored collected data after 90 chunks in Meta-Llama-3-70B-Instruct-abliterated-v3.5-IMat-GGUF/imatrix.dat
+[90]6.6917,[91]6.6476,[92]6.6037,[93]6.5698,[94]6.5286,[95]6.4881,[96]6.4893,[97]6.5106,[98]6.5497,[99]6.6270,
+save_imatrix: stored collected data after 100 chunks in Meta-Llama-3-70B-Instruct-abliterated-v3.5-IMat-GGUF/imatrix.dat
+[100]6.6900,[101]6.7389,[102]6.8478,[103]6.8841,[104]6.9202,[105]6.8548,[106]6.8672,[107]6.8289,[108]6.7632,[109]6.6914,
+save_imatrix: stored collected data after 110 chunks in Meta-Llama-3-70B-Instruct-abliterated-v3.5-IMat-GGUF/imatrix.dat
+[110]6.7287,[111]6.7779,[112]6.7930,[113]6.8060,[114]6.8440,[115]6.8934,[116]6.9108,[117]6.9391,[118]6.9750,[119]6.9357,
+save_imatrix: stored collected data after 120 chunks in Meta-Llama-3-70B-Instruct-abliterated-v3.5-IMat-GGUF/imatrix.dat
+[120]6.8696,[121]6.7890,[122]6.7378,[123]6.6867,[124]6.6589,[125]6.6244,
+save_imatrix: stored collected data after 125 chunks in Meta-Llama-3-70B-Instruct-abliterated-v3.5-IMat-GGUF/imatrix.dat
+
+llama_print_timings:        load time =    8534.89 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 =  797658.74 ms / 64000 tokens (   12.46 ms per token,    80.23 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 =  802631.68 ms / 64001 tokens
+
+Final estimate: PPL = 6.6244 +/- 0.10022