build: 3906 (7eee341b) with Apple clang version 15.0.0 (clang-1500.3.9.4) for arm64-apple-darwin23.6.0 llama_model_loader: loaded meta data with 29 key-value pairs and 219 tensors from salamandra-2b_bf16.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.size_label str = 2.3B llama_model_loader: - kv 3: general.license str = apache-2.0 llama_model_loader: - kv 4: general.tags arr[str,1] = ["text-generation"] llama_model_loader: - kv 5: general.languages arr[str,36] = ["bg", "ca", "code", "cs", "cy", "da"... llama_model_loader: - kv 6: llama.block_count u32 = 24 llama_model_loader: - kv 7: llama.context_length u32 = 8192 llama_model_loader: - kv 8: llama.embedding_length u32 = 2048 llama_model_loader: - kv 9: llama.feed_forward_length u32 = 5440 llama_model_loader: - kv 10: llama.attention.head_count u32 = 16 llama_model_loader: - kv 11: llama.attention.head_count_kv u32 = 16 llama_model_loader: - kv 12: llama.rope.freq_base f32 = 10000.000000 llama_model_loader: - kv 13: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 14: general.file_type u32 = 32 llama_model_loader: - kv 15: llama.vocab_size u32 = 256000 llama_model_loader: - kv 16: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 17: tokenizer.ggml.add_space_prefix bool = true llama_model_loader: - kv 18: tokenizer.ggml.model str = llama llama_model_loader: - kv 19: tokenizer.ggml.pre str = default llama_model_loader: - kv 20: tokenizer.ggml.tokens arr[str,256000] = ["", "~~", "~~", "", "<|... llama_model_loader: - kv 21: tokenizer.ggml.scores arr[f32,256000] = [-1000.000000, -1000.000000, -1000.00... llama_model_loader: - kv 22: tokenizer.ggml.token_type arr[i32,256000] = [3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, ... llama_model_loader: - kv 23: tokenizer.ggml.bos_token_id u32 = 1 llama_model_loader: - kv 24: tokenizer.ggml.eos_token_id u32 = 2 llama_model_loader: - kv 25: tokenizer.ggml.unknown_token_id u32 = 0 llama_model_loader: - kv 26: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 27: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 28: general.quantization_version u32 = 2 llama_model_loader: - type f32: 49 tensors llama_model_loader: - type bf16: 170 tensors llm_load_vocab: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect llm_load_vocab: special tokens cache size = 104 llm_load_vocab: token to piece cache size = 1.8842 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = llama 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 = 2048 llm_load_print_meta: n_layer = 24 llm_load_print_meta: n_head = 16 llm_load_print_meta: n_head_kv = 16 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 = 1 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-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 = 5440 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 = 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 = ?B llm_load_print_meta: model ftype = BF16 llm_load_print_meta: model params = 2.25 B llm_load_print_meta: model size = 4.20 GiB (16.00 BPW) llm_load_print_meta: general.name = n/a llm_load_print_meta: BOS token = 1 '~~' llm_load_print_meta: EOS token = 2 '~~' llm_load_print_meta: UNK token = 0 '' llm_load_print_meta: LF token = 145 '<0x0A>' llm_load_print_meta: EOT token = 5 '<|im_end|>' llm_load_print_meta: EOG token = 2 '' llm_load_print_meta: EOG token = 5 '<|im_end|>' llm_load_print_meta: max token length = 72 llm_load_tensors: ggml ctx size = 0.20 MiB llm_load_tensors: offloading 24 repeating layers to GPU llm_load_tensors: offloading non-repeating layers to GPU llm_load_tensors: offloaded 25/25 layers to GPU llm_load_tensors: Metal buffer size = 4298.39 MiB llm_load_tensors: CPU buffer size = 1000.00 MiB ....................................................... llama_new_context_with_model: n_ctx = 8192 llama_new_context_with_model: n_batch = 512 llama_new_context_with_model: n_ubatch = 128 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 ggml_metal_init: allocating ggml_metal_init: found device: Apple M3 Max ggml_metal_init: picking default device: Apple M3 Max ggml_metal_init: using embedded metal library ggml_metal_init: GPU name: Apple M3 Max ggml_metal_init: GPU family: MTLGPUFamilyApple9 (1009) ggml_metal_init: GPU family: MTLGPUFamilyCommon3 (3003) ggml_metal_init: GPU family: MTLGPUFamilyMetal3 (5001) ggml_metal_init: simdgroup reduction support = true ggml_metal_init: simdgroup matrix mul. support = true ggml_metal_init: hasUnifiedMemory = true ggml_metal_init: recommendedMaxWorkingSetSize = 42949.67 MB llama_kv_cache_init: Metal KV buffer size = 1536.00 MiB llama_new_context_with_model: KV self size = 1536.00 MiB, K (f16): 768.00 MiB, V (f16): 768.00 MiB llama_new_context_with_model: CPU output buffer size = 0.98 MiB llama_new_context_with_model: Metal compute buffer size = 72.00 MiB llama_new_context_with_model: CPU compute buffer size = 125.00 MiB llama_new_context_with_model: graph nodes = 774 llama_new_context_with_model: graph splits = 339 common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable) system_info: n_threads = 15 (n_threads_batch = 15) / 16 | AVX = 0 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 0 | NEON = 1 | SVE = 0 | ARM_FMA = 1 | F16C = 0 | FP16_VA = 1 | RISCV_VECT = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 0 | SSSE3 = 0 | VSX = 0 | MATMUL_INT8 = 1 | LLAMAFILE = 1 | perplexity: tokenizing the input .. perplexity: tokenization took 2944.83 ms perplexity: calculating perplexity over 134 chunks, n_ctx=8192, batch_size=512, n_seq=1 perplexity: 84.94 seconds per pass - ETA 3 hours 9.68 minutes [1]15.5521,[2]15.5243,[3]14.1791,[4]14.0080,[5]13.4279,[6]13.0750,[7]13.7702,[8]13.2641,[9]13.0322,[10]12.4282,[11]13.0141,[12]13.0853,[13]14.0004,[14]14.2411,[15]14.2616,[16]14.7586,[17]15.0186,[18]14.9545,[19]15.0044,[20]15.2855,[21]15.3281,[22]13.5810,[23]13.7417,[24]13.4025,[25]12.9526,[26]12.5733,[27]12.4107,[28]12.2631,[29]12.2225,[30]12.0474,[31]12.2514,[32]12.3563,[33]12.7661,[34]13.0445,[35]13.3131,[36]13.1171,[37]13.1134,[38]13.1810,[39]13.0497,[40]13.0761,[41]13.0474,[42]12.8878,[43]12.8415,[44]12.9932,[45]13.1760,[46]13.0445,[47]13.2584,[48]13.3618,[49]13.6099,[50]13.8153,[51]13.8471,[52]14.0284,[53]14.3018,[54]14.5755,[55]14.6680,[56]14.5193,[57]14.4274,[58]14.1963,[59]14.1032,[60]13.9283,[61]13.9695,[62]14.0852,[63]14.2446,[64]14.2908,[65]14.3094,[66]14.4704,[67]14.4544,[68]14.3628,[69]14.2428,[70]14.1527,[71]14.1504,[72]14.1043,[73]14.1130,[74]14.0605,[75]14.0155,[76]13.9607,[77]14.0114,[78]14.0080,[79]14.0166,[80]14.0461,[81]13.8192,[82]13.8070,[83]13.6942,[84]13.7219,[85]13.7631,[86]13.9343,[87]13.9542,[88]14.0887,[89]14.1345,[90]14.2424,[91]14.2909,[92]14.1519,[93]14.2109,[94]14.2008,[95]14.3206,[96]14.4896,[97]14.5541,[98]14.6379,[99]14.7395,[100]14.7771,[101]14.8052,[102]14.7742,[103]14.7484,[104]14.7321,[105]14.7171,[106]14.6035,[107]14.4934,[108]14.5517,[109]14.5712,[110]14.4924,[111]14.4610,[112]14.3247,[113]14.2038,[114]14.1982,[115]14.1747,[116]14.1834,[117]14.0911,[118]13.9783,[119]13.9760,[120]14.0290,[121]14.0448,[122]14.0646,[123]14.0971,[124]14.1110,[125]14.1068,[126]14.1296,[127]14.1528,[128]14.2222,[129]14.2136,[130]14.1948,[131]14.2436,[132]14.2216,[133]14.1743,[134]14.0431, Final estimate: PPL = 14.0431 +/- 0.05588 llama_perf_context_print: load time = 1415.12 ms llama_perf_context_print: prompt eval time = 9867305.31 ms / 1097728 tokens ( 8.99 ms per token, 111.25 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 = 9911124.59 ms / 1097729 tokens ggml_metal_free: deallocating