legraphista
/

dolphin-2.9.2-Phi-3-Medium-abliterated-IMat-GGUF

+main: build = 3072 (549279d8)
+main: built with cc (Ubuntu 13.2.0-23ubuntu4) 13.2.0 for x86_64-linux-gnu
+main: seed  = 1717403919
+llama_model_loader: loaded meta data with 26 key-value pairs and 363 tensors from dolphin-2.9.2-Phi-3-Medium-abliterated-IMat-GGUF/dolphin-2.9.2-Phi-3-Medium-abliterated.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              = dolphin-2.9.2-Phi-3-Medium-abliterated
+llama_model_loader: - kv   2:                          llama.block_count u32              = 40
+llama_model_loader: - kv   3:                       llama.context_length u32              = 4096
+llama_model_loader: - kv   4:                     llama.embedding_length u32              = 5120
+llama_model_loader: - kv   5:                  llama.feed_forward_length u32              = 17920
+llama_model_loader: - kv   6:                 llama.attention.head_count u32              = 40
+llama_model_loader: - kv   7:              llama.attention.head_count_kv u32              = 10
+llama_model_loader: - kv   8:                       llama.rope.freq_base f32              = 10000.000000
+llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
+llama_model_loader: - kv  10:                          general.file_type u32              = 0
+llama_model_loader: - kv  11:                           llama.vocab_size u32              = 32064
+llama_model_loader: - kv  12:                 llama.rope.dimension_count u32              = 128
+llama_model_loader: - kv  13:                       tokenizer.ggml.model str              = llama
+llama_model_loader: - kv  14:                         tokenizer.ggml.pre str              = default
+llama_model_loader: - kv  15:                      tokenizer.ggml.tokens arr[str,32064]   = ["<unk>", "<s>", "</s>", "<0x00>", "<...
+llama_model_loader: - kv  16:                      tokenizer.ggml.scores arr[f32,32064]   = [0.000000, 0.000000, 0.000000, 0.0000...
+llama_model_loader: - kv  17:                  tokenizer.ggml.token_type arr[i32,32064]   = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
+llama_model_loader: - kv  18:                tokenizer.ggml.bos_token_id u32              = 1
+llama_model_loader: - kv  19:                tokenizer.ggml.eos_token_id u32              = 32011
+llama_model_loader: - kv  20:            tokenizer.ggml.unknown_token_id u32              = 0
+llama_model_loader: - kv  21:            tokenizer.ggml.padding_token_id u32              = 32009
+llama_model_loader: - kv  22:               tokenizer.ggml.add_bos_token bool             = false
+llama_model_loader: - kv  23:               tokenizer.ggml.add_eos_token bool             = false
+llama_model_loader: - kv  24:                    tokenizer.chat_template str              = {% if not add_generation_prompt is de...
+llama_model_loader: - kv  25:               general.quantization_version u32              = 2
+llama_model_loader: - type  f32:  363 tensors
+llm_load_vocab: special tokens cache size = 323
+llm_load_vocab: token to piece cache size = 0.1687 MB
+llm_load_print_meta: format           = GGUF V3 (latest)
+llm_load_print_meta: arch             = llama
+llm_load_print_meta: vocab type       = SPM
+llm_load_print_meta: n_vocab          = 32064
+llm_load_print_meta: n_merges         = 0
+llm_load_print_meta: n_ctx_train      = 4096
+llm_load_print_meta: n_embd           = 5120
+llm_load_print_meta: n_head           = 40
+llm_load_print_meta: n_head_kv        = 10
+llm_load_print_meta: n_layer          = 40
+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     = 1280
+llm_load_print_meta: n_embd_v_gqa     = 1280
+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             = 17920
+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  = 10000.0
+llm_load_print_meta: freq_scale_train = 1
+llm_load_print_meta: n_yarn_orig_ctx  = 4096
+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       = 13B
+llm_load_print_meta: model ftype      = all F32
+llm_load_print_meta: model params     = 13.96 B
+llm_load_print_meta: model size       = 52.01 GiB (32.00 BPW)
+llm_load_print_meta: general.name     = dolphin-2.9.2-Phi-3-Medium-abliterated
+llm_load_print_meta: BOS token        = 1 '<s>'
+llm_load_print_meta: EOS token        = 32011 '<|im_end|>'
+llm_load_print_meta: UNK token        = 0 '<unk>'
+llm_load_print_meta: PAD token        = 32009 '<|placeholder6|>'
+llm_load_print_meta: LF token         = 13 '<0x0A>'
+llm_load_print_meta: EOT token        = 32007 '<|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 =    0.37 MiB
+llm_load_tensors: offloading 16 repeating layers to GPU
+llm_load_tensors: offloaded 16/41 layers to GPU
+llm_load_tensors:        CPU buffer size = 53254.08 MiB
+llm_load_tensors:      CUDA0 buffer size = 20800.62 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  = 10000.0
+llama_new_context_with_model: freq_scale = 1
+llama_kv_cache_init:  CUDA_Host KV buffer size =    60.00 MiB
+llama_kv_cache_init:      CUDA0 KV buffer size =    40.00 MiB
+llama_new_context_with_model: KV self size  =  100.00 MiB, K (f16):   50.00 MiB, V (f16):   50.00 MiB
+llama_new_context_with_model:  CUDA_Host  output buffer size =     0.12 MiB
+llama_new_context_with_model:      CUDA0 compute buffer size =   698.88 MiB
+llama_new_context_with_model:  CUDA_Host compute buffer size =    11.01 MiB
+llama_new_context_with_model: graph nodes  = 1286
+llama_new_context_with_model: graph splits = 268
+system_info: n_threads = 25 / 32 | AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | 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 103.872 ms
+compute_imatrix: computing over 151 chunks with batch_size 512
+compute_imatrix: 30.08 seconds per pass - ETA 1 hours 15.68 minutes
+[1]5.5209,[2]4.2369,[3]4.1303,[4]4.5098,[5]4.9651,[6]5.0892,[7]4.5975,[8]5.0183,[9]5.3814,
+save_imatrix: stored collected data after 10 chunks in dolphin-2.9.2-Phi-3-Medium-abliterated-IMat-GGUF/imatrix.dat
+[10]5.7366,[11]5.6958,[12]5.3171,[13]5.2155,[14]5.3907,[15]5.8044,[16]5.9303,[17]6.2729,[18]6.4081,[19]6.5270,
+save_imatrix: stored collected data after 20 chunks in dolphin-2.9.2-Phi-3-Medium-abliterated-IMat-GGUF/imatrix.dat
+[20]6.6309,[21]6.8403,[22]6.6006,[23]6.3256,[24]6.4012,[25]6.4397,[26]6.3371,[27]6.2671,[28]6.3576,[29]6.5325,
+save_imatrix: stored collected data after 30 chunks in dolphin-2.9.2-Phi-3-Medium-abliterated-IMat-GGUF/imatrix.dat
+[30]6.6488,[31]6.6023,[32]6.7093,[33]6.8190,[34]6.9812,[35]6.9775,[36]6.9287,[37]6.6669,[38]6.4958,[39]6.3857,
+save_imatrix: stored collected data after 40 chunks in dolphin-2.9.2-Phi-3-Medium-abliterated-IMat-GGUF/imatrix.dat
+[40]6.2716,[41]6.1735,[42]6.1914,[43]6.1399,[44]6.1571,[45]6.1433,[46]6.0983,[47]6.0972,[48]6.1712,[49]6.2425,
+save_imatrix: stored collected data after 50 chunks in dolphin-2.9.2-Phi-3-Medium-abliterated-IMat-GGUF/imatrix.dat
+[50]6.2475,[51]6.4119,[52]6.5501,[53]6.7235,[54]6.8715,[55]6.9538,[56]6.8636,[57]6.7603,[58]6.7651,[59]6.8131,
+save_imatrix: stored collected data after 60 chunks in dolphin-2.9.2-Phi-3-Medium-abliterated-IMat-GGUF/imatrix.dat
+[60]6.8962,[61]6.7693,[62]6.7858,[63]6.8348,[64]6.9229,[65]6.9803,[66]7.0066,[67]7.0609,[68]7.1048,[69]7.0949,
+save_imatrix: stored collected data after 70 chunks in dolphin-2.9.2-Phi-3-Medium-abliterated-IMat-GGUF/imatrix.dat
+[70]7.0890,[71]7.0915,[72]7.1405,[73]7.0880,[74]7.0181,[75]6.9959,[76]7.0408,[77]7.0332,[78]6.9995,[79]6.9902,
+save_imatrix: stored collected data after 80 chunks in dolphin-2.9.2-Phi-3-Medium-abliterated-IMat-GGUF/imatrix.dat
+[80]7.0031,[81]6.9634,[82]6.9378,[83]6.9098,[84]6.9072,[85]6.9110,[86]6.8996,[87]6.9036,[88]6.8956,[89]6.8828,
+save_imatrix: stored collected data after 90 chunks in dolphin-2.9.2-Phi-3-Medium-abliterated-IMat-GGUF/imatrix.dat
+[90]6.8658,[91]6.8735,[92]6.8379,[93]6.8379,[94]6.8107,[95]6.7672,[96]6.7778,[97]6.7565,[98]6.7636,[99]6.7329,
+save_imatrix: stored collected data after 100 chunks in dolphin-2.9.2-Phi-3-Medium-abliterated-IMat-GGUF/imatrix.dat
+[100]6.7254,[101]6.7334,[102]6.7096,[103]6.6804,[104]6.6572,[105]6.6656,[106]6.6603,[107]6.6857,[108]6.7052,[109]6.6576,
+save_imatrix: stored collected data after 110 chunks in dolphin-2.9.2-Phi-3-Medium-abliterated-IMat-GGUF/imatrix.dat
+[110]6.6115,[111]6.5634,[112]6.5150,[113]6.4675,[114]6.4279,[115]6.3860,[116]6.3417,[117]6.3150,[118]6.3233,[119]6.3293,
+save_imatrix: stored collected data after 120 chunks in dolphin-2.9.2-Phi-3-Medium-abliterated-IMat-GGUF/imatrix.dat
+[120]6.3715,[121]6.4091,[122]6.4562,[123]6.5050,[124]6.5819,[125]6.6454,[126]6.6561,[127]6.6646,[128]6.6121,[129]6.6050,
+save_imatrix: stored collected data after 130 chunks in dolphin-2.9.2-Phi-3-Medium-abliterated-IMat-GGUF/imatrix.dat
+[130]6.5712,[131]6.5364,[132]6.4850,[133]6.4141,[134]6.4276,[135]6.4500,[136]6.4480,[137]6.4417,[138]6.4512,[139]6.4614,
+save_imatrix: stored collected data after 140 chunks in dolphin-2.9.2-Phi-3-Medium-abliterated-IMat-GGUF/imatrix.dat
+[140]6.4745,[141]6.4761,[142]6.4800,[143]6.4706,[144]6.4510,[145]6.4725,[146]6.5015,[147]6.5357,[148]6.5681,[149]6.6067,
+save_imatrix: stored collected data after 150 chunks in dolphin-2.9.2-Phi-3-Medium-abliterated-IMat-GGUF/imatrix.dat
+[150]6.6392,[151]6.6730,
+save_imatrix: stored collected data after 151 chunks in dolphin-2.9.2-Phi-3-Medium-abliterated-IMat-GGUF/imatrix.dat
+llama_print_timings:        load time =   82696.61 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 =  560820.89 ms / 77312 tokens (    7.25 ms per token,   137.86 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 =  615183.59 ms / 77313 tokens
+Final estimate: PPL = 6.6730 +/- 0.08813