llama_model_loader: loaded meta data with 26 key-value pairs and 464 tensors from gemma-2-9b-it-IMat-GGUF/gemma-2-9b-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-2-9b-it llama_model_loader: - kv 2: gemma2.context_length u32 = 8192 llama_model_loader: - kv 3: gemma2.embedding_length u32 = 3584 llama_model_loader: - kv 4: gemma2.block_count u32 = 42 llama_model_loader: - kv 5: gemma2.feed_forward_length u32 = 14336 llama_model_loader: - kv 6: gemma2.attention.head_count u32 = 16 llama_model_loader: - kv 7: gemma2.attention.head_count_kv u32 = 8 llama_model_loader: - kv 8: gemma2.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 9: gemma2.attention.key_length u32 = 256 llama_model_loader: - kv 10: gemma2.attention.value_length u32 = 256 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] = [-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: 169 tensors llama_model_loader: - type q8_0: 295 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 = 3584 llm_load_print_meta: n_head = 16 llm_load_print_meta: n_head_kv = 8 llm_load_print_meta: n_layer = 42 llm_load_print_meta: n_rot = 224 llm_load_print_meta: n_embd_head_k = 256 llm_load_print_meta: n_embd_head_v = 256 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 = 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 = 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 = 9B llm_load_print_meta: model ftype = Q8_0 llm_load_print_meta: model params = 9.24 B llm_load_print_meta: model size = 9.15 GiB (8.50 BPW) llm_load_print_meta: general.name = gemma-2-9b-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 = 0.41 MiB llm_load_tensors: offloading 42 repeating layers to GPU llm_load_tensors: offloading non-repeating layers to GPU llm_load_tensors: offloaded 43/43 layers to GPU llm_load_tensors: CPU buffer size = 929.69 MiB llm_load_tensors: CUDA0 buffer size = 9366.12 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: CUDA0 KV buffer size = 168.00 MiB llama_new_context_with_model: KV self size = 168.00 MiB, K (f16): 84.00 MiB, V (f16): 84.00 MiB llama_new_context_with_model: CUDA_Host output buffer size = 0.98 MiB llama_new_context_with_model: CUDA0 compute buffer size = 507.00 MiB llama_new_context_with_model: CUDA_Host compute buffer size = 8.01 MiB llama_new_context_with_model: graph nodes = 1561 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 97.236 ms compute_imatrix: computing over 128 chunks with batch_size 512 compute_imatrix: 0.79 seconds per pass - ETA 1.67 minutes [1]25.5555,[2]11.3371,[3]9.6572,[4]12.0692,[5]13.4088,[6]14.1829,[7]15.8326,[8]17.3340,[9]17.9398, save_imatrix: stored collected data after 10 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat [10]15.2815,[11]14.8649,[12]16.5897,[13]17.6261,[14]17.7479,[15]19.0873,[16]19.1682,[17]19.2087,[18]19.9391,[19]19.7468, save_imatrix: stored collected data after 20 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat [20]20.1653,[21]22.1505,[22]22.3124,[23]21.8212,[24]22.2676,[25]22.0063,[26]21.5170,[27]21.9266,[28]22.2449,[29]22.2217, save_imatrix: stored collected data after 30 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat [30]22.6759,[31]20.7289,[32]19.6957,[33]18.9266,[34]18.2634,[35]17.8145,[36]17.9976,[37]18.5187,[38]18.8666,[39]19.1825, save_imatrix: stored collected data after 40 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat [40]19.3533,[41]19.4193,[42]20.3610,[43]20.9211,[44]21.5207,[45]21.8640,[46]21.3869,[47]21.0216,[48]21.4183,[49]21.8035, save_imatrix: stored collected data after 50 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat [50]21.4532,[51]21.2299,[52]21.3418,[53]21.7373,[54]22.2971,[55]22.7546,[56]22.9648,[57]22.9028,[58]22.8850,[59]22.5015, save_imatrix: stored collected data after 60 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat [60]22.1941,[61]21.8891,[62]21.6051,[63]21.7991,[64]22.0817,[65]21.8311,[66]21.8910,[67]21.8394,[68]21.7671,[69]21.6403, save_imatrix: stored collected data after 70 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat [70]21.5486,[71]21.5095,[72]21.4334,[73]21.5543,[74]21.4526,[75]21.2407,[76]21.2201,[77]21.2480,[78]21.1739,[79]21.0144, save_imatrix: stored collected data after 80 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat [80]21.1184,[81]21.2594,[82]21.3021,[83]21.4948,[84]21.5654,[85]21.2021,[86]21.0964,[87]20.8221,[88]20.8641,[89]20.8093, save_imatrix: stored collected data after 90 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat [90]20.9594,[91]20.8774,[92]20.7254,[93]20.5958,[94]20.4042,[95]20.3073,[96]20.1582,[97]20.0437,[98]19.8836,[99]19.9673, save_imatrix: stored collected data after 100 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat [100]19.9773,[101]20.2196,[102]20.3460,[103]20.4376,[104]20.7373,[105]20.9656,[106]20.9967,[107]21.0194,[108]20.9206,[109]20.9610, save_imatrix: stored collected data after 110 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat [110]20.7368,[111]20.5050,[112]20.2327,[113]20.3919,[114]20.4664,[115]20.4441,[116]20.4104,[117]20.5285,[118]20.5751,[119]20.6017, save_imatrix: stored collected data after 120 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat [120]20.5870,[121]20.6010,[122]20.5378,[123]20.5777,[124]20.7099,[125]20.8429,[126]21.0201,[127]21.0849,[128]21.1542, save_imatrix: stored collected data after 128 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat llama_print_timings: load time = 2307.06 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 = 87159.32 ms / 65536 tokens ( 1.33 ms per token, 751.91 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 = 90163.64 ms / 65537 tokens Final estimate: PPL = 21.1542 +/- 0.50274