| 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_Q3_K_L.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 = 13 | |
| 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 q3_K: 97 tensors | |
| llama_model_loader: - type q5_K: 48 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 = Q3_K - Large | |
| llm_load_print_meta: model params = 2.25 B | |
| llm_load_print_meta: model size = 1.80 GiB (6.85 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 = 1840.13 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 2741.95 ms | |
| perplexity: calculating perplexity over 134 chunks, n_ctx=8192, batch_size=512, n_seq=1 | |
| perplexity: 10.33 seconds per pass - ETA 23.05 minutes | |
| [1]18.3751,[2]18.7063,[3]16.8806,[4]16.5903,[5]15.8444,[6]15.3400,[7]16.2943,[8]15.7614,[9]15.4661,[10]14.7455,[11]15.4058,[12]15.4707,[13]16.6022,[14]16.9078,[15]16.8926,[16]17.4456,[17]17.7709,[18]17.6703,[19]17.6898,[20]18.0172,[21]18.0413,[22]15.9789,[23]16.1688,[24]15.7649,[25]15.2233,[26]14.7550,[27]14.5496,[28]14.3645,[29]14.3079,[30]14.0839,[31]14.3321,[32]14.4502,[33]14.9338,[34]15.2396,[35]15.5478,[36]15.2922,[37]15.2753,[38]15.3457,[39]15.1808,[40]15.2087,[41]15.1848,[42]14.9793,[43]14.9167,[44]15.0906,[45]15.3037,[46]15.1467,[47]15.4100,[48]15.5334,[49]15.8348,[50]16.1429,[51]16.1849,[52]16.4173,[53]16.7558,[54]17.0960,[55]17.2191,[56]17.0438,[57]16.9502,[58]16.6601,[59]16.5426,[60]16.3405,[61]16.3897,[62]16.5398,[63]16.7419,[64]16.8083,[65]16.8394,[66]17.0364,[67]17.0094,[68]16.8909,[69]16.7384,[70]16.6228,[71]16.6213,[72]16.5604,[73]16.5666,[74]16.5139,[75]16.5047,[76]16.4420,[77]16.5047,[78]16.5027,[79]16.5087,[80]16.5418,[81]16.2233,[82]16.1985,[83]16.0625,[84]16.0991,[85]16.1511,[86]16.3592,[87]16.3892,[88]16.5549,[89]16.6120,[90]16.7460,[91]16.8066,[92]16.6348,[93]16.7024,[94]16.6877,[95]16.8355,[96]17.0351,[97]17.1187,[98]17.2222,[99]17.3725,[100]17.4156,[101]17.4451,[102]17.4032,[103]17.3732,[104]17.3571,[105]17.3399,[106]17.2031,[107]17.0649,[108]17.1284,[109]17.1473,[110]17.0546,[111]17.0157,[112]16.8633,[113]16.7129,[114]16.7039,[115]16.6748,[116]16.6818,[117]16.5711,[118]16.4363,[119]16.4301,[120]16.4939,[121]16.5105,[122]16.5380,[123]16.5775,[124]16.5954,[125]16.5914,[126]16.6190,[127]16.6449,[128]16.7290,[129]16.7188,[130]16.6922,[131]16.7515,[132]16.7253,[133]16.6661,[134]16.5067, | |
| Final estimate: PPL = 16.5067 +/- 0.06740 | |
| llama_perf_context_print: load time = 1256.77 ms | |
| llama_perf_context_print: prompt eval time = 1373342.06 ms / 1097728 tokens ( 1.25 ms per token, 799.31 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 = 1414333.17 ms / 1097729 tokens | |
| ggml_metal_free: deallocating | |