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 30 key-value pairs and 148 tensors from Llama-Guard-3-1B-IMat-GGUF/Llama-Guard-3-1B.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 Guard 3 1B llama_model_loader: - kv 3: general.basename str = Llama-Guard-3 llama_model_loader: - kv 4: general.size_label str = 1B llama_model_loader: - kv 5: general.license str = llama3.2 llama_model_loader: - kv 6: general.tags arr[str,6] = ["facebook", "meta", "pytorch", "llam... llama_model_loader: - kv 7: general.languages arr[str,8] = ["en", "de", "fr", "it", "pt", "hi", ... llama_model_loader: - kv 8: llama.block_count u32 = 16 llama_model_loader: - kv 9: llama.context_length u32 = 131072 llama_model_loader: - kv 10: llama.embedding_length u32 = 2048 llama_model_loader: - kv 11: llama.feed_forward_length u32 = 8192 llama_model_loader: - kv 12: llama.attention.head_count u32 = 32 llama_model_loader: - kv 13: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 14: llama.rope.freq_base f32 = 500000.000000 llama_model_loader: - kv 15: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 16: llama.attention.key_length u32 = 64 llama_model_loader: - kv 17: llama.attention.value_length u32 = 64 llama_model_loader: - kv 18: general.file_type u32 = 7 llama_model_loader: - kv 19: llama.vocab_size u32 = 128256 llama_model_loader: - kv 20: llama.rope.dimension_count u32 = 64 llama_model_loader: - kv 21: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 22: tokenizer.ggml.pre str = llama-bpe llama_model_loader: - kv 23: tokenizer.ggml.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 24: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 25: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "... llama_model_loader: - kv 26: tokenizer.ggml.bos_token_id u32 = 128000 llama_model_loader: - kv 27: tokenizer.ggml.eos_token_id u32 = 128009 llama_model_loader: - kv 28: tokenizer.chat_template str = {%- if messages|length % 2 == 0 -%}\n ... llama_model_loader: - kv 29: general.quantization_version u32 = 2 llama_model_loader: - type f32: 34 tensors llama_model_loader: - type q8_0: 114 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 = 1.50 B llm_load_print_meta: model size = 1.48 GiB (8.50 BPW) llm_load_print_meta: general.name = Llama Guard 3 1B 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 41.7 ms compute_imatrix: computing over 125 chunks with batch_size 512 compute_imatrix: 0.26 seconds per pass - ETA 0.53 minutes [1]12.6981,[2]11.2023,[3]10.1980,[4]12.5026,[5]13.2416,[6]11.1191,[7]11.6862,[8]12.6711,[9]12.3544,[10]11.0861,[11]11.9575,[12]13.0696,[13]13.7919,[14]14.3594,[15]14.8069,[16]15.3642,[17]15.5152,[18]15.0535,[19]14.2616,[20]14.0102,[21]14.2288,[22]14.3777,[23]14.9627,[24]15.2010,[25]15.7363,[26]15.6310,[27]15.7498,[28]16.2149,[29]16.2048,[30]15.9883,[31]14.9849,[32]14.4200,[33]14.0878,[34]13.7783,[35]13.9568,[36]14.1931,[37]14.0283,[38]14.0189,[39]14.3262,[40]14.4825,[41]14.8521,[42]15.2848,[43]15.7827,[44]16.1563,[45]16.6374,[46]16.3597,[47]16.5542,[48]16.6284,[49]16.7525,[50]16.5988,[51]16.8583,[52]17.0215,[53]17.2505,[54]17.4594,[55]17.6825,[56]17.7626,[57]17.9108,[58]17.9600,[59]18.2017,[60]18.0045,[61]17.8883,[62]18.0668,[63]18.0690,[64]17.8717,[65]17.8126,[66]17.7703,[67]17.7398,[68]17.7826,[69]17.7080,[70]17.6097,[71]17.5217,[72]17.5573,[73]17.5261,[74]17.4918,[75]17.4773,[76]17.5200,[77]17.4191,[78]17.4381,[79]17.4517,[80]17.4695,[81]17.3574,[82]17.3725,[83]17.3748,[84]17.1655,[85]17.1321,[86]17.1689,[87]17.1813,[88]17.2473,[89]17.3173,[90]17.1617,[91]17.0510,[92]16.9346,[93]16.8425,[94]16.7132,[95]16.6337,[96]16.5423,[97]16.5106,[98]16.5533,[99]16.6885,[100]16.8052,[101]16.9002,[102]17.1638,[103]17.1933,[104]17.2173,[105]17.1397,[106]17.1190,[107]17.1367,[108]17.1499,[109]17.1273,[110]17.2097,[111]17.2813,[112]17.2230,[113]17.1821,[114]17.2224,[115]17.2968,[116]17.2962,[117]17.2898,[118]17.3580,[119]17.2641,[120]17.3443,[121]17.4507,[122]17.5163,[123]17.6180,[124]17.7018,[125]17.8182, Final estimate: PPL = 17.8182 +/- 0.29274 llama_perf_context_print: load time = 924.47 ms llama_perf_context_print: prompt eval time = 18281.11 ms / 64000 tokens ( 0.29 ms per token, 3500.88 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 = 19801.33 ms / 64001 tokens