Upload imatrix.log with huggingface_hub

imatrix.log

@@ -0,0 +1,140 @@
+llama_model_loader: loaded meta data with 23 key-value pairs and 291 tensors from RoLlama3-8b-Instruct-IMat-GGUF/RoLlama3-8b-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              = llama
+llama_model_loader: - kv   1:                               general.name str              = RoLlama3-8b-Instruct
+llama_model_loader: - kv   2:                          llama.block_count u32              = 32
+llama_model_loader: - kv   3:                       llama.context_length u32              = 8192
+llama_model_loader: - kv   4:                     llama.embedding_length u32              = 4096
+llama_model_loader: - kv   5:                  llama.feed_forward_length u32              = 14336
+llama_model_loader: - kv   6:                 llama.attention.head_count u32              = 32
+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.ggml.padding_token_id u32              = 128009
+llama_model_loader: - kv  21:                    tokenizer.chat_template str              = {% set system_message = 'Ești un asi...
+llama_model_loader: - kv  22:               general.quantization_version u32              = 2
+llama_model_loader: - type  f32:   65 tensors
+llama_model_loader: - type q8_0:  226 tensors
+llm_load_vocab: special tokens cache size = 256
+llm_load_vocab: token to piece cache size = 0.8000 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           = 4096
+llm_load_print_meta: n_head           = 32
+llm_load_print_meta: n_head_kv        = 8
+llm_load_print_meta: n_layer          = 32
+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            = 4
+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             = 14336
+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  = 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       = 8B
+llm_load_print_meta: model ftype      = Q8_0
+llm_load_print_meta: model params     = 8.03 B
+llm_load_print_meta: model size       = 7.95 GiB (8.50 BPW) 
+llm_load_print_meta: general.name     = RoLlama3-8b-Instruct
+llm_load_print_meta: BOS token        = 128000 '<|begin_of_text|>'
+llm_load_print_meta: EOS token        = 128009 '<|eot_id|>'
+llm_load_print_meta: PAD token        = 128009 '<|eot_id|>'
+llm_load_print_meta: LF token         = 128 'Ä'
+llm_load_print_meta: EOT token        = 128009 '<|eot_id|>'
+llm_load_print_meta: max token length = 256
+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 =    0.30 MiB
+llm_load_tensors: offloading 32 repeating layers to GPU
+llm_load_tensors: offloading non-repeating layers to GPU
+llm_load_tensors: offloaded 33/33 layers to GPU
+llm_load_tensors:        CPU buffer size =   532.31 MiB
+llm_load_tensors:      CUDA0 buffer size =  7605.33 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:      CUDA0 KV buffer size =    64.00 MiB
+llama_new_context_with_model: KV self size  =   64.00 MiB, K (f16):   32.00 MiB, V (f16):   32.00 MiB
+llama_new_context_with_model:  CUDA_Host  output buffer size =     0.49 MiB
+llama_new_context_with_model:      CUDA0 compute buffer size =   258.50 MiB
+llama_new_context_with_model:  CUDA_Host compute buffer size =     9.01 MiB
+llama_new_context_with_model: graph nodes  = 1030
+llama_new_context_with_model: graph splits = 2
+
+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 41.879 ms
+compute_imatrix: computing over 125 chunks with batch_size 512
+compute_imatrix: 0.73 seconds per pass - ETA 1.52 minutes
+[1]5.3197,[2]4.1203,[3]3.7466,[4]4.6688,[5]4.7522,[6]4.0511,[7]4.3325,[8]4.7194,[9]4.9221,
+save_imatrix: stored collected data after 10 chunks in RoLlama3-8b-Instruct-IMat-GGUF/imatrix.dat
+[10]4.5371,[11]4.9454,[12]5.3936,[13]5.7982,[14]6.1836,[15]6.4117,[16]6.6886,[17]6.8575,[18]6.6066,[19]6.3120,
+save_imatrix: stored collected data after 20 chunks in RoLlama3-8b-Instruct-IMat-GGUF/imatrix.dat
+[20]6.3036,[21]6.4335,[22]6.3724,[23]6.6187,[24]6.5874,[25]6.8862,[26]6.8678,[27]6.6280,[28]6.5552,[29]6.5581,
+save_imatrix: stored collected data after 30 chunks in RoLlama3-8b-Instruct-IMat-GGUF/imatrix.dat
+[30]6.5409,[31]6.2219,[32]5.9307,[33]5.8011,[34]5.7020,[35]5.7571,[36]5.8205,[37]5.7797,[38]5.8361,[39]5.9567,
+save_imatrix: stored collected data after 40 chunks in RoLlama3-8b-Instruct-IMat-GGUF/imatrix.dat
+[40]6.0255,[41]5.9107,[42]5.7491,[43]5.7262,[44]5.6353,[45]5.6632,[46]5.5978,[47]5.7036,[48]5.7899,[49]5.8828,
+save_imatrix: stored collected data after 50 chunks in RoLlama3-8b-Instruct-IMat-GGUF/imatrix.dat
+[50]5.8221,[51]5.9057,[52]6.0108,[53]6.0854,[54]6.1489,[55]6.2118,[56]6.2579,[57]6.3263,[58]6.3467,[59]6.3636,
+save_imatrix: stored collected data after 60 chunks in RoLlama3-8b-Instruct-IMat-GGUF/imatrix.dat
+[60]6.3386,[61]6.3349,[62]6.3772,[63]6.4250,[64]6.3709,[65]6.3589,[66]6.3773,[67]6.3664,[68]6.3711,[69]6.3702,
+save_imatrix: stored collected data after 70 chunks in RoLlama3-8b-Instruct-IMat-GGUF/imatrix.dat
+[70]6.3837,[71]6.3912,[72]6.4015,[73]6.3856,[74]6.3523,[75]6.3589,[76]6.3727,[77]6.3558,[78]6.3552,[79]6.3900,
+save_imatrix: stored collected data after 80 chunks in RoLlama3-8b-Instruct-IMat-GGUF/imatrix.dat
+[80]6.4211,[81]6.4179,[82]6.4221,[83]6.4511,[84]6.3773,[85]6.3770,[86]6.3915,[87]6.4025,[88]6.4275,[89]6.4389,
+save_imatrix: stored collected data after 90 chunks in RoLlama3-8b-Instruct-IMat-GGUF/imatrix.dat
+[90]6.3974,[91]6.3435,[92]6.2970,[93]6.2533,[94]6.2075,[95]6.1652,[96]6.1383,[97]6.1492,[98]6.1894,[99]6.2637,
+save_imatrix: stored collected data after 100 chunks in RoLlama3-8b-Instruct-IMat-GGUF/imatrix.dat
+[100]6.3332,[101]6.3741,[102]6.4802,[103]6.5092,[104]6.5449,[105]6.4910,[106]6.5028,[107]6.4773,[108]6.4371,[109]6.3888,
+save_imatrix: stored collected data after 110 chunks in RoLlama3-8b-Instruct-IMat-GGUF/imatrix.dat
+[110]6.4299,[111]6.4773,[112]6.4889,[113]6.4877,[114]6.5176,[115]6.5522,[116]6.5670,[117]6.5873,[118]6.6148,[119]6.5830,
+save_imatrix: stored collected data after 120 chunks in RoLlama3-8b-Instruct-IMat-GGUF/imatrix.dat
+[120]6.5531,[121]6.5227,[122]6.5207,[123]6.5083,[124]6.5082,[125]6.4824,
+save_imatrix: stored collected data after 125 chunks in RoLlama3-8b-Instruct-IMat-GGUF/imatrix.dat
+
+llama_print_timings:        load time =    9645.06 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 =   78767.49 ms / 64000 tokens (    1.23 ms per token,   812.52 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 =   88484.18 ms / 64001 tokens
+
+Final estimate: PPL = 6.4824 +/- 0.08632