| 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 35 key-value pairs and 219 tensors from salamandra-2b-instruct_Q5_K_S.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 = 16 | |
| 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] = ["<unk>", "<s>", "</s>", "<pad>", "<|... | |
| 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: - kv 31: quantize.imatrix.file str = imatrix/oscar/imatrix.dat | |
| llama_model_loader: - kv 32: quantize.imatrix.dataset str = ./imatrix/oscar/imatrix-dataset.txt | |
| llama_model_loader: - kv 33: quantize.imatrix.entries_count i32 = 168 | |
| llama_model_loader: - kv 34: quantize.imatrix.chunks_count i32 = 44176 | |
| llama_model_loader: - type f32: 49 tensors | |
| llama_model_loader: - type q5_1: 24 tensors | |
| llama_model_loader: - type q5_K: 145 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 = Q5_K - Small | |
| llm_load_print_meta: model params = 2.25 B | |
| llm_load_print_meta: model size = 2.10 GiB (8.00 BPW) | |
| llm_load_print_meta: general.name = n/a | |
| llm_load_print_meta: BOS token = 1 '<s>' | |
| llm_load_print_meta: EOS token = 2 '</s>' | |
| llm_load_print_meta: UNK token = 0 '<unk>' | |
| llm_load_print_meta: PAD token = 0 '<unk>' | |
| llm_load_print_meta: LF token = 145 '<0x0A>' | |
| llm_load_print_meta: EOT token = 5 '<|im_end|>' | |
| llm_load_print_meta: EOG token = 2 '</s>' | |
| 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 = 2150.02 MiB | |
| llm_load_tensors: CPU buffer size = 343.75 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 2882.91 ms | |
| perplexity: calculating perplexity over 134 chunks, n_ctx=8192, batch_size=512, n_seq=1 | |
| perplexity: 10.23 seconds per pass - ETA 22.83 minutes | |
| [1]17.2785,[2]17.3956,[3]15.8182,[4]15.6253,[5]14.9784,[6]14.5289,[7]15.4024,[8]14.8970,[9]14.6110,[10]13.9083,[11]14.5294,[12]14.5847,[13]15.6201,[14]15.8849,[15]15.8689,[16]16.3995,[17]16.6897,[18]16.5927,[19]16.6344,[20]16.9387,[21]16.9762,[22]14.9908,[23]15.1671,[24]14.7960,[25]14.2906,[26]13.8526,[27]13.6621,[28]13.4899,[29]13.4404,[30]13.2374,[31]13.4688,[32]13.5754,[33]14.0416,[34]14.3413,[35]14.6406,[36]14.4104,[37]14.3984,[38]14.4738,[39]14.3237,[40]14.3586,[41]14.3349,[42]14.1493,[43]14.0986,[44]14.2616,[45]14.4640,[46]14.3193,[47]14.5523,[48]14.6647,[49]14.9375,[50]15.2097,[51]15.2433,[52]15.4516,[53]15.7659,[54]16.0790,[55]16.1869,[56]16.0226,[57]15.9270,[58]15.6618,[59]15.5568,[60]15.3672,[61]15.4177,[62]15.5506,[63]15.7337,[64]15.7943,[65]15.8222,[66]16.0057,[67]15.9803,[68]15.8701,[69]15.7304,[70]15.6239,[71]15.6188,[72]15.5632,[73]15.5726,[74]15.5157,[75]15.4888,[76]15.4294,[77]15.4869,[78]15.4861,[79]15.4939,[80]15.5303,[81]15.2465,[82]15.2241,[83]15.0971,[84]15.1296,[85]15.1765,[86]15.3665,[87]15.3904,[88]15.5424,[89]15.5955,[90]15.7196,[91]15.7749,[92]15.6150,[93]15.6800,[94]15.6679,[95]15.8016,[96]15.9901,[97]16.0644,[98]16.1586,[99]16.2961,[100]16.3372,[101]16.3631,[102]16.3251,[103]16.2967,[104]16.2805,[105]16.2670,[106]16.1406,[107]16.0144,[108]16.0742,[109]16.0908,[110]16.0044,[111]15.9691,[112]15.8230,[113]15.6850,[114]15.6798,[115]15.6547,[116]15.6632,[117]15.5585,[118]15.4314,[119]15.4247,[120]15.4835,[121]15.4987,[122]15.5208,[123]15.5565,[124]15.5727,[125]15.5673,[126]15.5925,[127]15.6164,[128]15.6942,[129]15.6844,[130]15.6618,[131]15.7177,[132]15.6932,[133]15.6385,[134]15.4901, | |
| Final estimate: PPL = 15.4901 +/- 0.06304 | |
| llama_perf_context_print: load time = 1379.17 ms | |
| llama_perf_context_print: prompt eval time = 1395400.59 ms / 1097728 tokens ( 1.27 ms per token, 786.68 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 = 1436395.92 ms / 1097729 tokens | |
| ggml_metal_free: deallocating | |