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 33 key-value pairs and 219 tensors from salamandra-2b_IQ3_XS.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 = 22 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: - kv 29: quantize.imatrix.file str = imatrix/oscar/imatrix.dat llama_model_loader: - kv 30: quantize.imatrix.dataset str = ./imatrix/oscar/imatrix-dataset.txt llama_model_loader: - kv 31: quantize.imatrix.entries_count i32 = 168 llama_model_loader: - kv 32: quantize.imatrix.chunks_count i32 = 44176 llama_model_loader: - type f32: 49 tensors llama_model_loader: - type iq3_xxs: 84 tensors llama_model_loader: - type iq4_nl: 24 tensors llama_model_loader: - type iq3_s: 61 tensors llama_model_loader: - type bf16: 1 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 = IQ3_XS - 3.3 bpw llm_load_print_meta: model params = 2.25 B llm_load_print_meta: model size = 1.68 GiB (6.39 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 = 1715.88 MiB llm_load_tensors: CPU buffer size = 214.84 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 = 3 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 2898.3 ms perplexity: calculating perplexity over 134 chunks, n_ctx=8192, batch_size=512, n_seq=1 perplexity: 11.52 seconds per pass - ETA 25.72 minutes [1]18.7794,[2]19.1032,[3]17.1315,[4]16.7952,[5]16.0003,[6]15.4513,[7]16.3470,[8]15.8079,[9]15.4916,[10]14.7659,[11]15.4848,[12]15.5849,[13]16.7073,[14]17.0137,[15]17.0237,[16]17.5811,[17]17.8925,[18]17.8166,[19]17.8461,[20]18.1781,[21]18.1888,[22]16.2421,[23]16.4269,[24]15.9990,[25]15.4450,[26]14.9809,[27]14.7772,[28]14.5806,[29]14.5174,[30]14.2881,[31]14.5335,[32]14.6332,[33]15.1139,[34]15.4279,[35]15.7392,[36]15.4877,[37]15.4619,[38]15.5268,[39]15.3498,[40]15.3611,[41]15.3463,[42]15.1371,[43]15.0717,[44]15.2442,[45]15.4502,[46]15.2895,[47]15.5599,[48]15.7126,[49]16.0394,[50]16.3178,[51]16.3600,[52]16.5920,[53]16.9293,[54]17.2638,[55]17.4015,[56]17.2239,[57]17.1326,[58]16.8399,[59]16.7161,[60]16.5116,[61]16.5507,[62]16.7029,[63]16.9081,[64]16.9650,[65]16.9876,[66]17.1888,[67]17.1652,[68]17.0581,[69]16.9106,[70]16.8024,[71]16.8093,[72]16.7575,[73]16.7712,[74]16.7158,[75]16.6911,[76]16.6282,[77]16.6845,[78]16.6764,[79]16.6846,[80]16.7164,[81]16.4185,[82]16.3942,[83]16.2586,[84]16.3045,[85]16.3614,[86]16.5757,[87]16.6118,[88]16.7800,[89]16.8425,[90]16.9749,[91]17.0446,[92]16.8687,[93]16.9390,[94]16.9172,[95]17.0643,[96]17.2712,[97]17.3516,[98]17.4538,[99]17.5864,[100]17.6344,[101]17.6619,[102]17.6272,[103]17.5880,[104]17.5704,[105]17.5447,[106]17.4046,[107]17.2638,[108]17.3319,[109]17.3600,[110]17.2628,[111]17.2275,[112]17.0681,[113]16.9175,[114]16.9062,[115]16.8724,[116]16.8766,[117]16.7634,[118]16.6207,[119]16.6164,[120]16.6826,[121]16.7024,[122]16.7304,[123]16.7759,[124]16.7975,[125]16.7985,[126]16.8251,[127]16.8578,[128]16.9415,[129]16.9315,[130]16.9064,[131]16.9649,[132]16.9388,[133]16.8816,[134]16.7197, Final estimate: PPL = 16.7197 +/- 0.06758 llama_perf_context_print: load time = 1185.44 ms llama_perf_context_print: prompt eval time = 1564010.06 ms / 1097728 tokens ( 1.42 ms per token, 701.87 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 = 1626475.44 ms / 1097729 tokens ggml_metal_free: deallocating