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 31 key-value pairs and 219 tensors from salamandra-2b-instruct_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.padding_token_id u32 = 0 llama_model_loader: - kv 27: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 28: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 29: tokenizer.chat_template str = {%- if not date_string is defined %}{... llama_model_loader: - kv 30: 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: PAD 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 2392.75 ms perplexity: calculating perplexity over 134 chunks, n_ctx=8192, batch_size=512, n_seq=1 perplexity: 26.29 seconds per pass - ETA 58.72 minutes [1]17.0945,[2]17.2430,[3]15.6983,[4]15.5040,[5]14.8664,[6]14.4292,[7]15.3001,[8]14.7921,[9]14.5097,[10]13.8068,[11]14.4200,[12]14.4767,[13]15.5006,[14]15.7598,[15]15.7466,[16]16.2740,[17]16.5636,[18]16.4667,[19]16.5097,[20]16.8117,[21]16.8507,[22]14.8782,[23]15.0531,[24]14.6859,[25]14.1819,[26]13.7495,[27]13.5620,[28]13.3912,[29]13.3431,[30]13.1431,[31]13.3738,[32]13.4801,[33]13.9456,[34]14.2441,[35]14.5410,[36]14.3118,[37]14.3020,[38]14.3775,[39]14.2297,[40]14.2632,[41]14.2385,[42]14.0548,[43]14.0045,[44]14.1658,[45]14.3670,[46]14.2237,[47]14.4546,[48]14.5655,[49]14.8335,[50]15.1038,[51]15.1372,[52]15.3426,[53]15.6530,[54]15.9634,[55]16.0689,[56]15.9065,[57]15.8118,[58]15.5488,[59]15.4459,[60]15.2578,[61]15.3081,[62]15.4391,[63]15.6192,[64]15.6799,[65]15.7079,[66]15.8906,[67]15.8656,[68]15.7574,[69]15.6198,[70]15.5156,[71]15.5100,[72]15.4556,[73]15.4652,[74]15.4087,[75]15.3826,[76]15.3231,[77]15.3801,[78]15.3798,[79]15.3887,[80]15.4246,[81]15.1447,[82]15.1232,[83]14.9963,[84]15.0280,[85]15.0748,[86]15.2635,[87]15.2864,[88]15.4369,[89]15.4888,[90]15.6106,[91]15.6644,[92]15.5051,[93]15.5691,[94]15.5571,[95]15.6902,[96]15.8767,[97]15.9505,[98]16.0444,[99]16.1795,[100]16.2202,[101]16.2466,[102]16.2088,[103]16.1811,[104]16.1649,[105]16.1516,[106]16.0264,[107]15.9021,[108]15.9615,[109]15.9784,[110]15.8923,[111]15.8568,[112]15.7114,[113]15.5749,[114]15.5696,[115]15.5445,[116]15.5536,[117]15.4501,[118]15.3239,[119]15.3171,[120]15.3751,[121]15.3897,[122]15.4121,[123]15.4467,[124]15.4623,[125]15.4566,[126]15.4812,[127]15.5047,[128]15.5819,[129]15.5723,[130]15.5502,[131]15.6053,[132]15.5812,[133]15.5268,[134]15.3799, Final estimate: PPL = 15.3799 +/- 0.06263 llama_perf_context_print: load time = 757.14 ms llama_perf_context_print: prompt eval time = 4094189.23 ms / 1097728 tokens ( 3.73 ms per token, 268.12 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 = 4170459.06 ms / 1097729 tokens ggml_metal_free: deallocating