build: 3790 (5cb12f68) with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu llama_model_loader: loaded meta data with 39 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.type str = model llama_model_loader: - kv 2: general.name str = Gemma 2 27b It llama_model_loader: - kv 3: general.finetune str = it llama_model_loader: - kv 4: general.basename str = gemma-2 llama_model_loader: - kv 5: general.size_label str = 27B llama_model_loader: - kv 6: general.license str = gemma llama_model_loader: - kv 7: general.base_model.count u32 = 1 llama_model_loader: - kv 8: general.base_model.0.name str = Gemma 2 27b llama_model_loader: - kv 9: general.base_model.0.organization str = Google llama_model_loader: - kv 10: general.base_model.0.repo_url str = https://huggingface.co/google/gemma-2... llama_model_loader: - kv 11: general.tags arr[str,1] = ["text-generation"] llama_model_loader: - kv 12: gemma2.context_length u32 = 8192 llama_model_loader: - kv 13: gemma2.embedding_length u32 = 4608 llama_model_loader: - kv 14: gemma2.block_count u32 = 46 llama_model_loader: - kv 15: gemma2.feed_forward_length u32 = 36864 llama_model_loader: - kv 16: gemma2.attention.head_count u32 = 32 llama_model_loader: - kv 17: gemma2.attention.head_count_kv u32 = 16 llama_model_loader: - kv 18: gemma2.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 19: gemma2.attention.key_length u32 = 128 llama_model_loader: - kv 20: gemma2.attention.value_length u32 = 128 llama_model_loader: - kv 21: general.file_type u32 = 7 llama_model_loader: - kv 22: gemma2.attn_logit_softcapping f32 = 50.000000 llama_model_loader: - kv 23: gemma2.final_logit_softcapping f32 = 30.000000 llama_model_loader: - kv 24: gemma2.attention.sliding_window u32 = 4096 llama_model_loader: - kv 25: tokenizer.ggml.model str = llama llama_model_loader: - kv 26: tokenizer.ggml.pre str = default llama_model_loader: - kv 27: tokenizer.ggml.tokens arr[str,256000] = ["", "", "", "", ... llama_model_loader: - kv 28: tokenizer.ggml.scores arr[f32,256000] = [-1000.000000, -1000.000000, -1000.00... llama_model_loader: - kv 29: tokenizer.ggml.token_type arr[i32,256000] = [3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, ... llama_model_loader: - kv 30: tokenizer.ggml.bos_token_id u32 = 2 llama_model_loader: - kv 31: tokenizer.ggml.eos_token_id u32 = 1 llama_model_loader: - kv 32: tokenizer.ggml.unknown_token_id u32 = 3 llama_model_loader: - kv 33: tokenizer.ggml.padding_token_id u32 = 0 llama_model_loader: - kv 34: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 35: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 36: tokenizer.chat_template str = {{ bos_token }}{% if messages[0]['rol... llama_model_loader: - kv 37: tokenizer.ggml.add_space_prefix bool = false llama_model_loader: - kv 38: 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 = 249 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: vocab_only = 0 llm_load_print_meta: n_ctx_train = 8192 llm_load_print_meta: n_embd = 4608 llm_load_print_meta: n_layer = 46 llm_load_print_meta: n_head = 32 llm_load_print_meta: n_head_kv = 16 llm_load_print_meta: n_rot = 128 llm_load_print_meta: n_swa = 4096 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: ssm_dt_b_c_rms = 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 '' 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 = 48 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 = 11.01 MiB llama_new_context_with_model: graph nodes = 1850 llama_new_context_with_model: graph splits = 121 system_info: n_threads = 25 (n_threads_batch = 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 | RISCV_VECT = 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 125.601 ms compute_imatrix: computing over 128 chunks with batch_size 512 compute_imatrix: 2.33 seconds per pass - ETA 4.95 minutes [1]6.5578,[2]4.3832,[3]3.8146,[4]4.7295,[5]4.8558,[6]4.2129,[7]4.5158,[8]4.7571,[9]4.9990,[10]4.4817,[11]4.6395,[12]5.0579,[13]5.5302,[14]5.7411,[15]6.1889,[16]6.4760,[17]6.6184,[18]6.9135,[19]6.6034,[20]6.7227,[21]6.8527,[22]6.8112,[23]6.9548,[24]6.9825,[25]7.1554,[26]6.9450,[27]7.1144,[28]7.2338,[29]7.1511,[30]7.1380,[31]6.7390,[32]6.5218,[33]6.4390,[34]6.3315,[35]6.2964,[36]6.3155,[37]6.3346,[38]6.3824,[39]6.5202,[40]6.6510,[41]6.7730,[42]7.0004,[43]7.2346,[44]7.4522,[45]7.5993,[46]7.4966,[47]7.5276,[48]7.6901,[49]7.8164,[50]7.6607,[51]7.6948,[52]7.7278,[53]7.8302,[54]7.9708,[55]8.0723,[56]8.1382,[57]8.1527,[58]8.1844,[59]8.0526,[60]7.9599,[61]7.8446,[62]7.8175,[63]7.8454,[64]7.8452,[65]7.8189,[66]7.8290,[67]7.7794,[68]7.7266,[69]7.7449,[70]7.7104,[71]7.6979,[72]7.7069,[73]7.6929,[74]7.6497,[75]7.6120,[76]7.6072,[77]7.6029,[78]7.5971,[79]7.5538,[80]7.6036,[81]7.6355,[82]7.6205,[83]7.6298,[84]7.6690,[85]7.5607,[86]7.5246,[87]7.4642,[88]7.4749,[89]7.5126,[90]7.5311,[91]7.4788,[92]7.4214,[93]7.3542,[94]7.2928,[95]7.2487,[96]7.1886,[97]7.1361,[98]7.0910,[99]7.1216,[100]7.1453,[101]7.2155,[102]7.2828,[103]7.3533,[104]7.4761,[105]7.5655,[106]7.5829,[107]7.6048,[108]7.6214,[109]7.5943,[110]7.5657,[111]7.4757,[112]7.3784,[113]7.4231,[114]7.4466,[115]7.4463,[116]7.4460,[117]7.4808,[118]7.4960,[119]7.5066,[120]7.5191,[121]7.5362,[122]7.5135,[123]7.5547,[124]7.6026,[125]7.6386,[126]7.7025,[127]7.7520,[128]7.7917, Final estimate: PPL = 7.7917 +/- 0.11823 llama_perf_context_print: load time = 5557.94 ms llama_perf_context_print: prompt eval time = 238949.63 ms / 65536 tokens ( 3.65 ms per token, 274.27 tokens per second) llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second) llama_perf_context_print: total time = 243783.26 ms / 65537 tokens