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_M.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 = 27 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 q5_0: 3 tensors llama_model_loader: - type q4_K: 48 tensors llama_model_loader: - type iq4_nl: 21 tensors llama_model_loader: - type iq3_s: 97 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_S mix - 3.66 bpw llm_load_print_meta: model params = 2.25 B llm_load_print_meta: model size = 1.73 GiB (6.60 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 = 1772.30 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 3229.2 ms perplexity: calculating perplexity over 134 chunks, n_ctx=8192, batch_size=512, n_seq=1 perplexity: 12.79 seconds per pass - ETA 28.57 minutes [1]16.7628,[2]16.8146,[3]15.2950,[4]15.0736,[5]14.3858,[6]13.9750,[7]14.7750,[8]14.2844,[9]14.0249,[10]13.3599,[11]14.0097,[12]14.0990,[13]15.1101,[14]15.3739,[15]15.3905,[16]15.9135,[17]16.1944,[18]16.1198,[19]16.1643,[20]16.4655,[21]16.4968,[22]14.6477,[23]14.8168,[24]14.4527,[25]13.9652,[26]13.5501,[27]13.3738,[28]13.2072,[29]13.1603,[30]12.9677,[31]13.1884,[32]13.2963,[33]13.7368,[34]14.0316,[35]14.3207,[36]14.0960,[37]14.0827,[38]14.1494,[39]13.9988,[40]14.0228,[41]13.9999,[42]13.8205,[43]13.7667,[44]13.9255,[45]14.1185,[46]13.9724,[47]14.2093,[48]14.3320,[49]14.6128,[50]14.8537,[51]14.8917,[52]15.0966,[53]15.3980,[54]15.7020,[55]15.8156,[56]15.6535,[57]15.5616,[58]15.3078,[59]15.2037,[60]15.0167,[61]15.0576,[62]15.1902,[63]15.3662,[64]15.4131,[65]15.4306,[66]15.6068,[67]15.5891,[68]15.4878,[69]15.3578,[70]15.2629,[71]15.2632,[72]15.2140,[73]15.2231,[74]15.1687,[75]15.1407,[76]15.0848,[77]15.1388,[78]15.1342,[79]15.1399,[80]15.1702,[81]14.9257,[82]14.9112,[83]14.7896,[84]14.8254,[85]14.8737,[86]15.0627,[87]15.0927,[88]15.2413,[89]15.2946,[90]15.4139,[91]15.4698,[92]15.3171,[93]15.3788,[94]15.3651,[95]15.4963,[96]15.6806,[97]15.7540,[98]15.8486,[99]15.9603,[100]15.9997,[101]16.0289,[102]15.9948,[103]15.9647,[104]15.9484,[105]15.9290,[106]15.8036,[107]15.6804,[108]15.7434,[109]15.7676,[110]15.6805,[111]15.6470,[112]15.5024,[113]15.3694,[114]15.3623,[115]15.3339,[116]15.3414,[117]15.2392,[118]15.1147,[119]15.1154,[120]15.1743,[121]15.1922,[122]15.2164,[123]15.2551,[124]15.2729,[125]15.2717,[126]15.2956,[127]15.3238,[128]15.3982,[129]15.3906,[130]15.3677,[131]15.4208,[132]15.3973,[133]15.3444,[134]15.1995, Final estimate: PPL = 15.1995 +/- 0.06031 llama_perf_context_print: load time = 1192.45 ms llama_perf_context_print: prompt eval time = 1556665.84 ms / 1097728 tokens ( 1.42 ms per token, 705.18 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 = 1618903.30 ms / 1097729 tokens ggml_metal_free: deallocating