|
llama_model_loader: loaded meta data with 26 key-value pairs and 508 tensors from gemma-2-27b-it-IMat-GGUF/gemma-2-27b-it.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 = gemma2 |
|
llama_model_loader: - kv 1: general.name str = gemma-2-27b-it |
|
llama_model_loader: - kv 2: gemma2.context_length u32 = 8192 |
|
llama_model_loader: - kv 3: gemma2.embedding_length u32 = 4608 |
|
llama_model_loader: - kv 4: gemma2.block_count u32 = 46 |
|
llama_model_loader: - kv 5: gemma2.feed_forward_length u32 = 36864 |
|
llama_model_loader: - kv 6: gemma2.attention.head_count u32 = 32 |
|
llama_model_loader: - kv 7: gemma2.attention.head_count_kv u32 = 16 |
|
llama_model_loader: - kv 8: gemma2.attention.layer_norm_rms_epsilon f32 = 0.000001 |
|
llama_model_loader: - kv 9: gemma2.attention.key_length u32 = 128 |
|
llama_model_loader: - kv 10: gemma2.attention.value_length u32 = 128 |
|
llama_model_loader: - kv 11: general.file_type u32 = 7 |
|
llama_model_loader: - kv 12: tokenizer.ggml.model str = llama |
|
llama_model_loader: - kv 13: tokenizer.ggml.pre str = default |
|
llama_model_loader: - kv 14: tokenizer.ggml.tokens arr[str,256000] = ["<pad>", "<eos>", "<bos>", "<unk>", ... |
|
llama_model_loader: - kv 15: tokenizer.ggml.scores arr[f32,256000] = [-1000.000000, -1000.000000, -1000.00... |
|
llama_model_loader: - kv 16: tokenizer.ggml.token_type arr[i32,256000] = [3, 3, 3, 3, 1, 1, 1, 1, 1, 1, 1, 1, ... |
|
llama_model_loader: - kv 17: tokenizer.ggml.bos_token_id u32 = 2 |
|
llama_model_loader: - kv 18: tokenizer.ggml.eos_token_id u32 = 1 |
|
llama_model_loader: - kv 19: tokenizer.ggml.unknown_token_id u32 = 3 |
|
llama_model_loader: - kv 20: tokenizer.ggml.padding_token_id u32 = 0 |
|
llama_model_loader: - kv 21: tokenizer.ggml.add_bos_token bool = true |
|
llama_model_loader: - kv 22: tokenizer.ggml.add_eos_token bool = false |
|
llama_model_loader: - kv 23: tokenizer.chat_template str = {{ bos_token }}{% if messages[0]['rol... |
|
llama_model_loader: - kv 24: tokenizer.ggml.add_space_prefix bool = false |
|
llama_model_loader: - kv 25: general.quantization_version u32 = 2 |
|
llama_model_loader: - type f32: 185 tensors |
|
llama_model_loader: - type q8_0: 323 tensors |
|
llm_load_vocab: special tokens cache size = 261 |
|
llm_load_vocab: token to piece cache size = 1.6014 MB |
|
llm_load_print_meta: format = GGUF V3 (latest) |
|
llm_load_print_meta: arch = gemma2 |
|
llm_load_print_meta: vocab type = SPM |
|
llm_load_print_meta: n_vocab = 256000 |
|
llm_load_print_meta: n_merges = 0 |
|
llm_load_print_meta: n_ctx_train = 8192 |
|
llm_load_print_meta: n_embd = 4608 |
|
llm_load_print_meta: n_head = 32 |
|
llm_load_print_meta: n_head_kv = 16 |
|
llm_load_print_meta: n_layer = 46 |
|
llm_load_print_meta: n_rot = 144 |
|
llm_load_print_meta: n_embd_head_k = 128 |
|
llm_load_print_meta: n_embd_head_v = 128 |
|
llm_load_print_meta: n_gqa = 2 |
|
llm_load_print_meta: n_embd_k_gqa = 2048 |
|
llm_load_print_meta: n_embd_v_gqa = 2048 |
|
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 = 36864 |
|
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 = 2 |
|
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_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 = 27B |
|
llm_load_print_meta: model ftype = Q8_0 |
|
llm_load_print_meta: model params = 27.23 B |
|
llm_load_print_meta: model size = 26.94 GiB (8.50 BPW) |
|
llm_load_print_meta: general.name = gemma-2-27b-it |
|
llm_load_print_meta: BOS token = 2 '<bos>' |
|
llm_load_print_meta: EOS token = 1 '<eos>' |
|
llm_load_print_meta: UNK token = 3 '<unk>' |
|
llm_load_print_meta: PAD token = 0 '<pad>' |
|
llm_load_print_meta: LF token = 227 '<0x0A>' |
|
llm_load_print_meta: EOT token = 107 '<end_of_turn>' |
|
llm_load_print_meta: max token length = 93 |
|
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 = 0.45 MiB |
|
llm_load_tensors: offloading 37 repeating layers to GPU |
|
llm_load_tensors: offloaded 37/47 layers to GPU |
|
llm_load_tensors: CPU buffer size = 27591.06 MiB |
|
llm_load_tensors: CUDA0 buffer size = 21231.35 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 = 36.00 MiB |
|
llama_kv_cache_init: CUDA0 KV buffer size = 148.00 MiB |
|
llama_new_context_with_model: KV self size = 184.00 MiB, K (f16): 92.00 MiB, V (f16): 92.00 MiB |
|
llama_new_context_with_model: CUDA_Host output buffer size = 0.98 MiB |
|
llama_new_context_with_model: CUDA0 compute buffer size = 1704.31 MiB |
|
llama_new_context_with_model: CUDA_Host compute buffer size = 10.01 MiB |
|
llama_new_context_with_model: graph nodes = 1709 |
|
llama_new_context_with_model: graph splits = 121 |
|
|
|
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 102.378 ms |
|
compute_imatrix: computing over 128 chunks with batch_size 512 |
|
compute_imatrix: 1.92 seconds per pass - ETA 4.08 minutes |
|
[1]39.6511,[2]16.5757,[3]13.6939,[4]15.6944,[5]16.8349,[6]17.6097,[7]19.6449,[8]21.2138,[9]22.7663, |
|
save_imatrix: stored collected data after 10 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat |
|
[10]19.5954,[11]18.7601,[12]20.1620,[13]21.1839,[14]21.3214,[15]22.4495,[16]22.5613,[17]22.7834,[18]23.9931,[19]23.7468, |
|
save_imatrix: stored collected data after 20 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat |
|
[20]23.8365,[21]26.0599,[22]25.6103,[23]25.1318,[24]25.6891,[25]25.7517,[26]25.1686,[27]25.8776,[28]26.5172,[29]26.5127, |
|
save_imatrix: stored collected data after 30 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat |
|
[30]27.2144,[31]24.9851,[32]23.7414,[33]22.8572,[34]22.1536,[35]21.5105,[36]22.1975,[37]23.0630,[38]23.1560,[39]23.3739, |
|
save_imatrix: stored collected data after 40 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat |
|
[40]23.4627,[41]23.6640,[42]25.0051,[43]25.9131,[44]26.9078,[45]27.6585,[46]27.0582,[47]26.4096,[48]26.8484,[49]27.2839, |
|
save_imatrix: stored collected data after 50 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat |
|
[50]26.9025,[51]26.6051,[52]26.6338,[53]27.0460,[54]27.5828,[55]28.1862,[56]28.5826,[57]28.5708,[58]28.5400,[59]28.0093, |
|
save_imatrix: stored collected data after 60 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat |
|
[60]27.6445,[61]27.2285,[62]27.0626,[63]27.1479,[64]27.4686,[65]27.1084,[66]27.0599,[67]27.0251,[68]26.9609,[69]26.8687, |
|
save_imatrix: stored collected data after 70 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat |
|
[70]26.7705,[71]26.7926,[72]26.7099,[73]26.7881,[74]26.7220,[75]26.5072,[76]26.5858,[77]26.7008,[78]26.6471,[79]26.4994, |
|
save_imatrix: stored collected data after 80 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat |
|
[80]26.6450,[81]26.7715,[82]26.8064,[83]27.0250,[84]27.0770,[85]26.6203,[86]26.4729,[87]26.2858,[88]26.3698,[89]26.3433, |
|
save_imatrix: stored collected data after 90 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat |
|
[90]26.5397,[91]26.5333,[92]26.4208,[93]26.3047,[94]26.1210,[95]26.0503,[96]25.8447,[97]25.8144,[98]25.7297,[99]25.7554, |
|
save_imatrix: stored collected data after 100 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat |
|
[100]25.6738,[101]25.8975,[102]26.0385,[103]26.1709,[104]26.5591,[105]26.8560,[106]26.8766,[107]26.8606,[108]26.7007,[109]26.6811, |
|
save_imatrix: stored collected data after 110 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat |
|
[110]26.4028,[111]26.0091,[112]25.5502,[113]25.6821,[114]25.7196,[115]25.6433,[116]25.5595,[117]25.5877,[118]25.6440,[119]25.6503, |
|
save_imatrix: stored collected data after 120 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat |
|
[120]25.6006,[121]25.5261,[122]25.4242,[123]25.4475,[124]25.6331,[125]25.8680,[126]26.1323,[127]26.2467,[128]26.3842, |
|
save_imatrix: stored collected data after 128 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat |
|
|
|
llama_print_timings: load time = 4083.77 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 = 232410.77 ms / 65536 tokens ( 3.55 ms per token, 281.98 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 = 236107.85 ms / 65537 tokens |
|
|
|
Final estimate: PPL = 26.3842 +/- 0.60805 |
|
|
