llama_model_loader: loaded meta data with 25 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] = ["", "", "", "", ... llama_model_loader: - kv 15: tokenizer.ggml.scores arr[f32,256000] = [0.000000, 0.000000, 0.000000, 0.0000... llama_model_loader: - kv 16: tokenizer.ggml.token_type arr[i32,256000] = [3, 3, 3, 2, 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: 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 = 260 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 = ?B 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 '' llm_load_print_meta: EOS token = 1 '' llm_load_print_meta: UNK token = 3 '' llm_load_print_meta: PAD token = 0 '' llm_load_print_meta: LF token = 227 '<0x0A>' llm_load_print_meta: EOT token = 107 '' 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 126.52 ms compute_imatrix: computing over 128 chunks with batch_size 512 compute_imatrix: 1.97 seconds per pass - ETA 4.20 minutes [1]16.8060,[2]10.0388,[3]8.6860,[4]10.8551,[5]10.6816,[6]8.5806,[7]9.5274,[8]10.0565,[9]10.8304, save_imatrix: stored collected data after 10 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat [10]9.2142,[11]9.3787,[12]10.2510,[13]11.1856,[14]11.6859,[15]12.6435,[16]13.3837,[17]13.5288,[18]14.3690,[19]13.6140, save_imatrix: stored collected data after 20 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat [20]13.8628,[21]14.2014,[22]13.9559,[23]14.2008,[24]14.3894,[25]14.7491,[26]14.2443,[27]14.6796,[28]15.1159,[29]14.8935, save_imatrix: stored collected data after 30 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat [30]14.7781,[31]13.7545,[32]13.2662,[33]13.0484,[34]12.8644,[35]12.7189,[36]12.9116,[37]12.9272,[38]12.9377,[39]13.1664, save_imatrix: stored collected data after 40 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat [40]13.3908,[41]13.7261,[42]14.3809,[43]15.0405,[44]15.6225,[45]16.0831,[46]15.7899,[47]15.8613,[48]16.2568,[49]16.5927, save_imatrix: stored collected data after 50 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat [50]16.2484,[51]16.2360,[52]16.3678,[53]16.6269,[54]16.9455,[55]17.2366,[56]17.3912,[57]17.4234,[58]17.5112,[59]17.2045, save_imatrix: stored collected data after 60 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat [60]16.9565,[61]16.6263,[62]16.5667,[63]16.5981,[64]16.5561,[65]16.4957,[66]16.4538,[67]16.3132,[68]16.1684,[69]16.2471, save_imatrix: stored collected data after 70 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat [70]16.2391,[71]16.2548,[72]16.2723,[73]16.2170,[74]16.1591,[75]16.1024,[76]16.1478,[77]16.2332,[78]16.2062,[79]16.1531, save_imatrix: stored collected data after 80 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat [80]16.2953,[81]16.3488,[82]16.3215,[83]16.3536,[84]16.4559,[85]16.2309,[86]16.1677,[87]16.0908,[88]16.1282,[89]16.2161, save_imatrix: stored collected data after 90 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat [90]16.2864,[91]16.1855,[92]16.0805,[93]15.9261,[94]15.7792,[95]15.6751,[96]15.5429,[97]15.3907,[98]15.2958,[99]15.3161, save_imatrix: stored collected data after 100 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat [100]15.3213,[101]15.4828,[102]15.6273,[103]15.7855,[104]16.1017,[105]16.3573,[106]16.4126,[107]16.4446,[108]16.5071,[109]16.4200, save_imatrix: stored collected data after 110 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat [110]16.3406,[111]16.1420,[112]15.9301,[113]16.0263,[114]16.0351,[115]16.0151,[116]16.0227,[117]16.0788,[118]16.0826,[119]16.0903, save_imatrix: stored collected data after 120 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat [120]16.0969,[121]16.1101,[122]16.0417,[123]16.1350,[124]16.2564,[125]16.3835,[126]16.5740,[127]16.7243,[128]16.8485, save_imatrix: stored collected data after 128 chunks in gemma-2-27b-it-IMat-GGUF/imatrix.dat llama_print_timings: load time = 4135.04 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 = 235882.68 ms / 65536 tokens ( 3.60 ms per token, 277.83 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 = 239612.08 ms / 65537 tokens Final estimate: PPL = 16.8485 +/- 0.33601