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 255 tensors from Llama-3.2-3B-Instruct-IMat-GGUF/Llama-3.2-3B-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 3B 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 = 3B 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 = 28 llama_model_loader: - kv 10: llama.context_length u32 = 131072 llama_model_loader: - kv 11: llama.embedding_length u32 = 3072 llama_model_loader: - kv 12: llama.feed_forward_length u32 = 8192 llama_model_loader: - kv 13: llama.attention.head_count u32 = 24 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 = 128 llama_model_loader: - kv 18: llama.attention.value_length u32 = 128 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 = 128 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: 58 tensors llama_model_loader: - type q8_0: 197 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 = 3072 llm_load_print_meta: n_layer = 28 llm_load_print_meta: n_head = 24 llm_load_print_meta: n_head_kv = 8 llm_load_print_meta: n_rot = 128 llm_load_print_meta: n_swa = 0 llm_load_print_meta: n_embd_head_k = 128 llm_load_print_meta: n_embd_head_v = 128 llm_load_print_meta: n_gqa = 3 llm_load_print_meta: n_embd_k_gqa = 1024 llm_load_print_meta: n_embd_v_gqa = 1024 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 = 3.21 B llm_load_print_meta: model size = 3.18 GiB (8.50 BPW) llm_load_print_meta: general.name = Llama 3.2 3B 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 = 0.24 MiB llm_load_tensors: offloading 28 repeating layers to GPU llm_load_tensors: offloading non-repeating layers to GPU llm_load_tensors: offloaded 29/29 layers to GPU llm_load_tensors: CPU buffer size = 399.23 MiB llm_load_tensors: CUDA0 buffer size = 3255.91 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 = 56.00 MiB llama_new_context_with_model: KV self size = 56.00 MiB, K (f16): 28.00 MiB, V (f16): 28.00 MiB llama_new_context_with_model: CUDA_Host output buffer size = 0.49 MiB llama_new_context_with_model: CUDA0 compute buffer size = 256.50 MiB llama_new_context_with_model: CUDA_Host compute buffer size = 7.01 MiB llama_new_context_with_model: graph nodes = 902 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 41.918 ms compute_imatrix: computing over 125 chunks with batch_size 512 compute_imatrix: 0.42 seconds per pass - ETA 0.87 minutes [1]7.2119,[2]6.1829,[3]5.5587,[4]7.1510,[5]7.5023,[6]6.2757,[7]6.8649,[8]7.4348,[9]7.5568,[10]6.8180,[11]7.3905,[12]8.1158,[13]8.7121,[14]9.2089,[15]9.5275,[16]9.8991,[17]10.1629,[18]9.7576,[19]9.2350,[20]9.1956,[21]9.4054,[22]9.3676,[23]9.7558,[24]9.8068,[25]10.1746,[26]10.2128,[27]10.4085,[28]10.8121,[29]10.8333,[30]10.8456,[31]10.2018,[32]9.6355,[33]9.3259,[34]9.0651,[35]9.2008,[36]9.4165,[37]9.3327,[38]9.3945,[39]9.6091,[40]9.7163,[41]10.0393,[42]10.3529,[43]10.7471,[44]10.9938,[45]11.3462,[46]11.1015,[47]11.2469,[48]11.3189,[49]11.4312,[50]11.2293,[51]11.3600,[52]11.5344,[53]11.6684,[54]11.8114,[55]11.8667,[56]11.8661,[57]11.9075,[58]11.8854,[59]11.8940,[60]11.7947,[61]11.7427,[62]11.7873,[63]11.8043,[64]11.6918,[65]11.6620,[66]11.6606,[67]11.5863,[68]11.5385,[69]11.4857,[70]11.4535,[71]11.4153,[72]11.3756,[73]11.3061,[74]11.2030,[75]11.1858,[76]11.1992,[77]11.1501,[78]11.1214,[79]11.1589,[80]11.1833,[81]11.1465,[82]11.1473,[83]11.1596,[84]10.9894,[85]11.0081,[86]11.0141,[87]10.9985,[88]11.0211,[89]11.0068,[90]10.9066,[91]10.7907,[92]10.6795,[93]10.5833,[94]10.4785,[95]10.3893,[96]10.3235,[97]10.3154,[98]10.3446,[99]10.4593,[100]10.5527,[101]10.6176,[102]10.7876,[103]10.8245,[104]10.8644,[105]10.7447,[106]10.7327,[107]10.6605,[108]10.6070,[109]10.5245,[110]10.5766,[111]10.6507,[112]10.6395,[113]10.6415,[114]10.6915,[115]10.7430,[116]10.7440,[117]10.7599,[118]10.7841,[119]10.6990,[120]10.7534,[121]10.8431,[122]10.8934,[123]10.9826,[124]11.0632,[125]11.1480, Final estimate: PPL = 11.1480 +/- 0.17302 llama_perf_context_print: load time = 1375.36 ms llama_perf_context_print: prompt eval time = 38403.22 ms / 64000 tokens ( 0.60 ms per token, 1666.53 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 = 40237.27 ms / 64001 tokens