| 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_Q4_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 = 14 | |
| 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.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: 21 tensors | |
| llama_model_loader: - type q5_1: 3 tensors | |
| llama_model_loader: - type q4_K: 141 tensors | |
| llama_model_loader: - type q5_K: 4 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 = Q4_K - Small | |
| llm_load_print_meta: model params = 2.25 B | |
| llm_load_print_meta: model size = 1.92 GiB (7.31 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: 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 = 1963.82 MiB | |
| llm_load_tensors: CPU buffer size = 281.25 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 2840.11 ms | |
| perplexity: calculating perplexity over 134 chunks, n_ctx=8192, batch_size=512, n_seq=1 | |
| perplexity: 12.00 seconds per pass - ETA 26.78 minutes | |
| [1]15.9446,[2]15.9810,[3]14.6034,[4]14.4054,[5]13.7911,[6]13.4109,[7]14.1312,[8]13.6264,[9]13.3898,[10]12.7653,[11]13.3737,[12]13.4439,[13]14.3921,[14]14.6483,[15]14.6682,[16]15.1769,[17]15.4375,[18]15.3667,[19]15.4192,[20]15.7055,[21]15.7428,[22]13.9408,[23]14.1081,[24]13.7646,[25]13.3032,[26]12.9112,[27]12.7439,[28]12.5933,[29]12.5524,[30]12.3724,[31]12.5840,[32]12.6820,[33]13.0993,[34]13.3825,[35]13.6573,[36]13.4513,[37]13.4450,[38]13.5125,[39]13.3761,[40]13.4030,[41]13.3755,[42]13.2085,[43]13.1589,[44]13.3146,[45]13.5021,[46]13.3675,[47]13.5890,[48]13.6982,[49]13.9591,[50]14.1762,[51]14.2097,[52]14.4006,[53]14.6837,[54]14.9674,[55]15.0637,[56]14.9112,[57]14.8169,[58]14.5769,[59]14.4804,[60]14.3013,[61]14.3429,[62]14.4645,[63]14.6301,[64]14.6783,[65]14.6953,[66]14.8631,[67]14.8457,[68]14.7521,[69]14.6287,[70]14.5380,[71]14.5369,[72]14.4895,[73]14.5000,[74]14.4474,[75]14.4055,[76]14.3498,[77]14.4012,[78]14.3988,[79]14.4077,[80]14.4364,[81]14.1989,[82]14.1829,[83]14.0666,[84]14.0964,[85]14.1386,[86]14.3158,[87]14.3392,[88]14.4779,[89]14.5266,[90]14.6380,[91]14.6900,[92]14.5463,[93]14.6068,[94]14.5950,[95]14.7180,[96]14.8931,[97]14.9613,[98]15.0495,[99]15.1554,[100]15.1936,[101]15.2222,[102]15.1894,[103]15.1627,[104]15.1452,[105]15.1293,[106]15.0116,[107]14.8971,[108]14.9574,[109]14.9781,[110]14.8969,[111]14.8642,[112]14.7244,[113]14.5989,[114]14.5930,[115]14.5687,[116]14.5772,[117]14.4804,[118]14.3638,[119]14.3616,[120]14.4167,[121]14.4325,[122]14.4539,[123]14.4883,[124]14.5032,[125]14.5001,[126]14.5234,[127]14.5474,[128]14.6191,[129]14.6109,[130]14.5912,[131]14.6422,[132]14.6192,[133]14.5697,[134]14.4338, | |
| Final estimate: PPL = 14.4338 +/- 0.05759 | |
| llama_perf_context_print: load time = 1476.08 ms | |
| llama_perf_context_print: prompt eval time = 1514913.38 ms / 1097728 tokens ( 1.38 ms per token, 724.61 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 = 1572921.63 ms / 1097729 tokens | |
| ggml_metal_free: deallocating | |