build: 3825 (1e436302) with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu llama_model_loader: loaded meta data with 31 key-value pairs and 147 tensors from Llama-3.2-1B-Instruct-IMat-GGUF/Llama-3.2-1B-Instruct.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 = llama llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = Llama 3.2 1B Instruct llama_model_loader: - kv 3: general.finetune str = Instruct llama_model_loader: - kv 4: general.basename str = Llama-3.2 llama_model_loader: - kv 5: general.size_label str = 1B llama_model_loader: - kv 6: general.license str = llama3.2 llama_model_loader: - kv 7: general.tags arr[str,6] = ["facebook", "meta", "pytorch", "llam... llama_model_loader: - kv 8: general.languages arr[str,8] = ["en", "de", "fr", "it", "pt", "hi", ... llama_model_loader: - kv 9: llama.block_count u32 = 16 llama_model_loader: - kv 10: llama.context_length u32 = 131072 llama_model_loader: - kv 11: llama.embedding_length u32 = 2048 llama_model_loader: - kv 12: llama.feed_forward_length u32 = 8192 llama_model_loader: - kv 13: llama.attention.head_count u32 = 32 llama_model_loader: - kv 14: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 15: llama.rope.freq_base f32 = 500000.000000 llama_model_loader: - kv 16: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 17: llama.attention.key_length u32 = 64 llama_model_loader: - kv 18: llama.attention.value_length u32 = 64 llama_model_loader: - kv 19: general.file_type u32 = 7 llama_model_loader: - kv 20: llama.vocab_size u32 = 128256 llama_model_loader: - kv 21: llama.rope.dimension_count u32 = 64 llama_model_loader: - kv 22: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 23: tokenizer.ggml.pre str = llama-bpe llama_model_loader: - kv 24: tokenizer.ggml.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 25: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 26: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "... llama_model_loader: - kv 27: tokenizer.ggml.bos_token_id u32 = 128000 llama_model_loader: - kv 28: tokenizer.ggml.eos_token_id u32 = 128009 llama_model_loader: - kv 29: tokenizer.chat_template str = {{- bos_token }}\n{%- if custom_tools ... llama_model_loader: - kv 30: general.quantization_version u32 = 2 llama_model_loader: - type f32: 34 tensors llama_model_loader: - type q8_0: 113 tensors llm_load_vocab: special tokens cache size = 256 llm_load_vocab: token to piece cache size = 0.7999 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = llama llm_load_print_meta: vocab type = BPE llm_load_print_meta: n_vocab = 128256 llm_load_print_meta: n_merges = 280147 llm_load_print_meta: vocab_only = 0 llm_load_print_meta: n_ctx_train = 131072 llm_load_print_meta: n_embd = 2048 llm_load_print_meta: n_layer = 16 llm_load_print_meta: n_head = 32 llm_load_print_meta: n_head_kv = 8 llm_load_print_meta: n_rot = 64 llm_load_print_meta: n_swa = 0 llm_load_print_meta: n_embd_head_k = 64 llm_load_print_meta: n_embd_head_v = 64 llm_load_print_meta: n_gqa = 4 llm_load_print_meta: n_embd_k_gqa = 512 llm_load_print_meta: n_embd_v_gqa = 512 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 = 8192 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 = 500000.0 llm_load_print_meta: freq_scale_train = 1 llm_load_print_meta: n_ctx_orig_yarn = 131072 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 = ?B llm_load_print_meta: model ftype = Q8_0 llm_load_print_meta: model params = 1.24 B llm_load_print_meta: model size = 1.22 GiB (8.50 BPW) llm_load_print_meta: general.name = Llama 3.2 1B Instruct llm_load_print_meta: BOS token = 128000 '<|begin_of_text|>' llm_load_print_meta: EOS token = 128009 '<|eot_id|>' llm_load_print_meta: LF token = 128 'Ä' llm_load_print_meta: EOT token = 128009 '<|eot_id|>' llm_load_print_meta: EOM token = 128008 '<|eom_id|>' llm_load_print_meta: EOG token = 128008 '<|eom_id|>' llm_load_print_meta: EOG token = 128009 '<|eot_id|>' llm_load_print_meta: max token length = 256 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 = 0.14 MiB llm_load_tensors: offloading 16 repeating layers to GPU llm_load_tensors: offloading non-repeating layers to GPU llm_load_tensors: offloaded 17/17 layers to GPU llm_load_tensors: CPU buffer size = 266.16 MiB llm_load_tensors: CUDA0 buffer size = 1252.42 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 = 500000.0 llama_new_context_with_model: freq_scale = 1 llama_kv_cache_init: CUDA0 KV buffer size = 16.00 MiB llama_new_context_with_model: KV self size = 16.00 MiB, K (f16): 8.00 MiB, V (f16): 8.00 MiB llama_new_context_with_model: CUDA_Host output buffer size = 0.49 MiB llama_new_context_with_model: CUDA0 compute buffer size = 254.50 MiB llama_new_context_with_model: CUDA_Host compute buffer size = 5.01 MiB llama_new_context_with_model: graph nodes = 518 llama_new_context_with_model: graph splits = 2 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 41.228 ms compute_imatrix: computing over 125 chunks with batch_size 512 compute_imatrix: 0.27 seconds per pass - ETA 0.55 minutes [1]10.1003,[2]8.7720,[3]7.6214,[4]9.5709,[5]9.9748,[6]8.1803,[7]8.9931,[8]9.8189,[9]9.8290,[10]8.8016,[11]9.5176,[12]10.4471,[13]11.0957,[14]11.5884,[15]11.9080,[16]12.2895,[17]12.5080,[18]12.0233,[19]11.3547,[20]11.3911,[21]11.7520,[22]11.6329,[23]12.1215,[24]12.1673,[25]12.5908,[26]12.6425,[27]12.8542,[28]13.3951,[29]13.4406,[30]13.4958,[31]12.6603,[32]11.9421,[33]11.5444,[34]11.1900,[35]11.4356,[36]11.7923,[37]11.7055,[38]11.7950,[39]12.0074,[40]12.1217,[41]12.5260,[42]12.9512,[43]13.4504,[44]13.7702,[45]14.1608,[46]13.8227,[47]14.0141,[48]14.1086,[49]14.2237,[50]13.9614,[51]14.0995,[52]14.3164,[53]14.4866,[54]14.6511,[55]14.7375,[56]14.7230,[57]14.7250,[58]14.6895,[59]14.7109,[60]14.5806,[61]14.4905,[62]14.5499,[63]14.5756,[64]14.4582,[65]14.4160,[66]14.4073,[67]14.3236,[68]14.2669,[69]14.2115,[70]14.1506,[71]14.0868,[72]14.0321,[73]13.9478,[74]13.8268,[75]13.8096,[76]13.8170,[77]13.7423,[78]13.7053,[79]13.7641,[80]13.7904,[81]13.7380,[82]13.7433,[83]13.7881,[84]13.5757,[85]13.6192,[86]13.6431,[87]13.6291,[88]13.6536,[89]13.6300,[90]13.4896,[91]13.3255,[92]13.1715,[93]13.0364,[94]12.9000,[95]12.7725,[96]12.6925,[97]12.6859,[98]12.7142,[99]12.8512,[100]12.9701,[101]13.0520,[102]13.2456,[103]13.2737,[104]13.3239,[105]13.1657,[106]13.1447,[107]13.0611,[108]12.9922,[109]12.9131,[110]12.9894,[111]13.0774,[112]13.0733,[113]13.0816,[114]13.1270,[115]13.1905,[116]13.1885,[117]13.1985,[118]13.2109,[119]13.1053,[120]13.2112,[121]13.3304,[122]13.3987,[123]13.5091,[124]13.6236,[125]13.7181, Final estimate: PPL = 13.7181 +/- 0.21967 llama_perf_context_print: load time = 892.41 ms llama_perf_context_print: prompt eval time = 18897.20 ms / 64000 tokens ( 0.30 ms per token, 3386.75 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 = 20329.73 ms / 64001 tokens