|
[1721889628] Log start |
|
[1721889628] Cmd: /home/maziyar/apps/fine-tuning/quantize/gguf/llama.cpp/llama-cli -m Mistral-Large-Instruct-2407.IQ1_M.gguf -p "I have 10 apples." -n 1024 -t 40 |
|
[1721889628] main: build = 3450 (b115105f) |
|
[1721889628] main: built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu |
|
[1721889628] main: seed = 1721889628 |
|
[1721889628] main: llama backend init |
|
[1721889628] main: load the model and apply lora adapter, if any |
|
[1721889628] llama_model_loader: loaded meta data with 38 key-value pairs and 795 tensors from Mistral-Large-Instruct-2407.IQ1_M.gguf (version GGUF V3 (latest)) |
|
[1721889628] llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. |
|
[1721889628] llama_model_loader: - kv 0: general.architecture str = llama |
|
[1721889628] llama_model_loader: - kv 1: general.type str = model |
|
[1721889628] llama_model_loader: - kv 2: general.name str = Models Mistralai Mistral Large Instru... |
|
[1721889628] llama_model_loader: - kv 3: general.version str = 2407 |
|
[1721889628] llama_model_loader: - kv 4: general.finetune str = Instruct |
|
[1721889628] llama_model_loader: - kv 5: general.basename str = models-mistralai-Mistral |
|
[1721889628] llama_model_loader: - kv 6: general.size_label str = Large |
|
[1721889628] llama_model_loader: - kv 7: general.license str = other |
|
[1721889628] llama_model_loader: - kv 8: general.license.name str = mrl |
|
[1721889628] llama_model_loader: - kv 9: general.license.link str = https: |
|
[1721889628] llama_model_loader: - kv 10: general.languages arr[str,10] = ["en", "fr", "de", "es", "it", "pt", ...[1721889628] llama_model_loader: - kv 11: llama.block_count u32 = 88 |
|
[1721889628] llama_model_loader: - kv 12: llama.context_length u32 = 32768 |
|
[1721889628] llama_model_loader: - kv 13: llama.embedding_length u32 = 12288 |
|
[1721889628] llama_model_loader: - kv 14: llama.feed_forward_length u32 = 28672 |
|
[1721889628] llama_model_loader: - kv 15: llama.attention.head_count u32 = 96 |
|
[1721889628] llama_model_loader: - kv 16: llama.attention.head_count_kv u32 = 8 |
|
[1721889628] llama_model_loader: - kv 17: llama.rope.freq_base f32 = 1000000.000000 |
|
[1721889628] llama_model_loader: - kv 18: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 |
|
[1721889628] llama_model_loader: - kv 19: general.file_type u32 = 31 |
|
[1721889628] llama_model_loader: - kv 20: llama.vocab_size u32 = 32768 |
|
[1721889628] llama_model_loader: - kv 21: llama.rope.dimension_count u32 = 128 |
|
[1721889628] llama_model_loader: - kv 22: tokenizer.ggml.add_space_prefix bool = false |
|
[1721889628] llama_model_loader: - kv 23: tokenizer.ggml.model str = llama |
|
[1721889628] llama_model_loader: - kv 24: tokenizer.ggml.pre str = default |
|
[1721889628] llama_model_loader: - kv 25: tokenizer.ggml.tokens arr[str,32768] = ["<unk>", "<s>", "</s>", "[INST]", "[... |
|
[1721889628] llama_model_loader: - kv 26: tokenizer.ggml.scores arr[f32,32768] = [-1000.000000, -1000.000000, -1000.00... |
|
[1721889628] llama_model_loader: - kv 27: tokenizer.ggml.token_type arr[i32,32768] = [3, 3, 3, 4, 4, 4, 4, 4, 4, 4, 4, 4, ... |
|
[1721889628] llama_model_loader: - kv 28: tokenizer.ggml.bos_token_id u32 = 1 |
|
[1721889628] llama_model_loader: - kv 29: tokenizer.ggml.eos_token_id u32 = 2 |
|
[1721889628] llama_model_loader: - kv 30: tokenizer.ggml.unknown_token_id u32 = 0 |
|
[1721889628] llama_model_loader: - kv 31: tokenizer.ggml.add_bos_token bool = true |
|
[1721889628] llama_model_loader: - kv 32: tokenizer.ggml.add_eos_token bool = false |
|
[1721889628] llama_model_loader: - kv 33: general.quantization_version u32 = 2 |
|
[1721889628] llama_model_loader: - kv 34: quantize.imatrix.file str = ./Mistral-Large-Instruct-2407-GGUF_im... |
|
[1721889628] llama_model_loader: - kv 35: quantize.imatrix.dataset str = group_40.txt |
|
[1721889628] llama_model_loader: - kv 36: quantize.imatrix.entries_count i32 = 616 |
|
[1721889628] llama_model_loader: - kv 37: quantize.imatrix.chunks_count i32 = 73 |
|
[1721889628] llama_model_loader: - type f32: 177 tensors |
|
[1721889628] llama_model_loader: - type q2_K: 12 tensors |
|
[1721889628] llama_model_loader: - type q4_K: 88 tensors |
|
[1721889628] llama_model_loader: - type q5_K: 1 tensors |
|
[1721889628] llama_model_loader: - type iq2_xxs: 88 tensors |
|
[1721889628] llama_model_loader: - type iq1_m: 429 tensors |
|
[1721889628] llm_load_vocab: special tokens cache size = 771 |
|
[1721889628] llm_load_vocab: token to piece cache size = 0.1732 MB |
|
[1721889628] llm_load_print_meta: format = GGUF V3 (latest) |
|
[1721889628] llm_load_print_meta: arch = llama |
|
[1721889628] llm_load_print_meta: vocab type = SPM |
|
[1721889628] llm_load_print_meta: n_vocab = 32768 |
|
[1721889628] llm_load_print_meta: n_merges = 0 |
|
[1721889628] llm_load_print_meta: vocab_only = 0 |
|
[1721889628] llm_load_print_meta: n_ctx_train = 32768 |
|
[1721889628] llm_load_print_meta: n_embd = 12288 |
|
[1721889628] llm_load_print_meta: n_layer = 88 |
|
[1721889628] llm_load_print_meta: n_head = 96 |
|
[1721889628] llm_load_print_meta: n_head_kv = 8 |
|
[1721889628] llm_load_print_meta: n_rot = 128 |
|
[1721889628] llm_load_print_meta: n_swa = 0 |
|
[1721889628] llm_load_print_meta: n_embd_head_k = 128 |
|
[1721889628] llm_load_print_meta: n_embd_head_v = 128 |
|
[1721889628] llm_load_print_meta: n_gqa = 12 |
|
[1721889628] llm_load_print_meta: n_embd_k_gqa = 1024 |
|
[1721889628] llm_load_print_meta: n_embd_v_gqa = 1024 |
|
[1721889628] llm_load_print_meta: f_norm_eps = 0.0e+00 |
|
[1721889628] llm_load_print_meta: f_norm_rms_eps = 1.0e-05 |
|
[1721889628] llm_load_print_meta: f_clamp_kqv = 0.0e+00 |
|
[1721889628] llm_load_print_meta: f_max_alibi_bias = 0.0e+00 |
|
[1721889628] llm_load_print_meta: f_logit_scale = 0.0e+00 |
|
[1721889628] llm_load_print_meta: n_ff = 28672 |
|
[1721889628] llm_load_print_meta: n_expert = 0 |
|
[1721889628] llm_load_print_meta: n_expert_used = 0 |
|
[1721889628] llm_load_print_meta: causal attn = 1 |
|
[1721889628] llm_load_print_meta: pooling type = 0 |
|
[1721889628] llm_load_print_meta: rope type = 0 |
|
[1721889628] llm_load_print_meta: rope scaling = linear |
|
[1721889628] llm_load_print_meta: freq_base_train = 1000000.0 |
|
[1721889628] llm_load_print_meta: freq_scale_train = 1 |
|
[1721889628] llm_load_print_meta: n_ctx_orig_yarn = 32768 |
|
[1721889628] llm_load_print_meta: rope_finetuned = unknown |
|
[1721889628] llm_load_print_meta: ssm_d_conv = 0 |
|
[1721889628] llm_load_print_meta: ssm_d_inner = 0 |
|
[1721889628] llm_load_print_meta: ssm_d_state = 0 |
|
[1721889628] llm_load_print_meta: ssm_dt_rank = 0 |
|
[1721889628] llm_load_print_meta: model type = ?B |
|
[1721889628] llm_load_print_meta: model ftype = IQ1_M - 1.75 bpw |
|
[1721889628] llm_load_print_meta: model params = 122.61 B |
|
[1721889628] llm_load_print_meta: model size = 26.44 GiB (1.85 BPW) |
|
[1721889628] llm_load_print_meta: general.name = Models Mistralai Mistral Large Instruct 2407 |
|
[1721889628] llm_load_print_meta: BOS token = 1 '<s>' |
|
[1721889628] llm_load_print_meta: EOS token = 2 '</s>' |
|
[1721889628] llm_load_print_meta: UNK token = 0 '<unk>' |
|
[1721889628] llm_load_print_meta: LF token = 781 '<0x0A>' |
|
[1721889628] llm_load_print_meta: max token length = 48 |
|
[1721889628] llm_load_tensors: ggml ctx size = 0.37 MiB |
|
[1721889630] llm_load_tensors: CPU buffer size = 27070.55 MiB |
|
[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] |
|
[1721889630] llama_new_context_with_model: n_ctx = 32768 |
|
[1721889630] llama_new_context_with_model: n_batch = 2048 |
|
[1721889630] llama_new_context_with_model: n_ubatch = 512 |
|
[1721889630] llama_new_context_with_model: flash_attn = 0 |
|
[1721889630] llama_new_context_with_model: freq_base = 1000000.0 |
|
[1721889630] llama_new_context_with_model: freq_scale = 1 |
|
[1721889637] llama_kv_cache_init: CPU KV buffer size = 11264.00 MiB |
|
[1721889637] llama_new_context_with_model: KV self size = 11264.00 MiB, K (f16): 5632.00 MiB, V (f16): 5632.00 MiB |
|
[1721889637] llama_new_context_with_model: CPU output buffer size = 0.13 MiB |
|
[1721889637] llama_new_context_with_model: CPU compute buffer size = 6304.01 MiB |
|
[1721889637] llama_new_context_with_model: graph nodes = 2822 |
|
[1721889637] llama_new_context_with_model: graph splits = 1 |
|
[1721889637] warming up the model with an empty run |
|
[1721889643] n_ctx: 32768 |
|
[1721889643] |
|
[1721889643] system_info: n_threads = 40 / 80 | AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 1 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | |
|
[1721889643] add_bos: 1 |
|
[1721889643] tokenize the prompt |
|
[1721889643] prompt: "I have 10 apples." |
|
[1721889643] tokens: [ '<s>':1, 'I':29505, ' have':1274, ' ':29473, '1':29508, '0':29502, ' ap':1747, 'ples':3583, '.':29491 ] |
|
[1721889643] recalculate the cached logits (check): embd_inp.empty() false, n_matching_session_tokens 0, embd_inp.size() 9, session_tokens.size() 0, embd_inp.size() 9 |
|
[1721889643] sampling: |
|
repeat_last_n = 64, repeat_penalty = 1.000, frequency_penalty = 0.000, presence_penalty = 0.000 |
|
top_k = 40, tfs_z = 1.000, top_p = 0.950, min_p = 0.050, typical_p = 1.000, temp = 0.800 |
|
mirostat = 0, mirostat_lr = 0.100, mirostat_ent = 5.000 |
|
[1721889643] sampling order: |
|
CFG -> Penalties -> top_k -> tfs_z -> typical_p -> top_p -> min_p -> temperature |
|
[1721889643] generate: n_ctx = 32768, n_batch = 2048, n_predict = 1024, n_keep = 1 |
|
[1721889643] |
|
|
|
[1721889643] embd_inp.size(): 9, n_consumed: 0 |
|
[1721889643] eval: [ '<s>':1, 'I':29505, ' have':1274, ' ':29473, '1':29508, '0':29502, ' ap':1747, 'ples':3583, '.':29491 ] |
|
[1721889651] n_past = 9 |
|
[1721889651] last: [ '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<s>':1, 'I':29505, ' have':1274, ' ':29473, '1':29508, '0':29502, ' ap':1747, 'ples':3583, '.':29491, '':781 ] |
|
[1721889651] n_remain: 1023 |
|
[1721889651] eval: [ '':781 ] |
|
[1721889652] n_past = 10 |
|
[1721889652] last: [ '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<s>':1, 'I':29505, ' have':1274, ' ':29473, '1':29508, '0':29502, ' ap':1747, 'ples':3583, '.':29491, '':781, '':781 ] |
|
[1721889652] n_remain: 1022 |
|
[1721889652] eval: [ '':781 ] |
|
[1721889653] n_past = 11 |
|
[1721889653] last: [ '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<s>':1, 'I':29505, ' have':1274, ' ':29473, '1':29508, '0':29502, ' ap':1747, 'ples':3583, '.':29491, '':781, '':781, '1':29508 ] |
|
[1721889653] n_remain: 1021 |
|
[1721889653] eval: [ '1':29508 ] |
|
[1721889654] n_past = 12 |
|
[1721889654] last: [ '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<s>':1, 'I':29505, ' have':1274, ' ':29473, '1':29508, '0':29502, ' ap':1747, 'ples':3583, '.':29491, '':781, '':781, '1':29508, '0':29502 ] |
|
[1721889654] n_remain: 1020 |
|
[1721889654] eval: [ '0':29502 ] |
|
[1721889655] n_past = 13 |
|
[1721889655] last: [ '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<s>':1, 'I':29505, ' have':1274, ' ':29473, '1':29508, '0':29502, ' ap':1747, 'ples':3583, '.':29491, '':781, '':781, '1':29508, '0':29502, ' ap':1747 ] |
|
[1721889655] n_remain: 1019 |
|
[1721889655] eval: [ ' ap':1747 ] |
|
[1721889656] n_past = 14 |
|
[1721889656] last: [ '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<s>':1, 'I':29505, ' have':1274, ' ':29473, '1':29508, '0':29502, ' ap':1747, 'ples':3583, '.':29491, '':781, '':781, '1':29508, '0':29502, ' ap':1747, 'ples':3583 ] |
|
[1721889656] n_remain: 1018 |
|
[1721889656] eval: [ 'ples':3583 ] |
|
[1721889657] n_past = 15 |
|
[1721889657] last: [ '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<s>':1, 'I':29505, ' have':1274, ' ':29473, '1':29508, '0':29502, ' ap':1747, 'ples':3583, '.':29491, '':781, '':781, '1':29508, '0':29502, ' ap':1747, 'ples':3583, ' are':1228 ] |
|
[1721889657] n_remain: 1017 |
|
[1721889657] eval: [ ' are':1228 ] |
|
[1721889658] n_past = 16 |
|
[1721889658] last: [ '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<s>':1, 'I':29505, ' have':1274, ' ':29473, '1':29508, '0':29502, ' ap':1747, 'ples':3583, '.':29491, '':781, '':781, '1':29508, '0':29502, ' ap':1747, 'ples':3583, ' are':1228, ' ':29473 ] |
|
[1721889658] n_remain: 1016 |
|
[1721889658] eval: [ ' ':29473 ] |
|
[1721889659] n_past = 17 |
|
[1721889659] last: [ '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<s>':1, 'I':29505, ' have':1274, ' ':29473, '1':29508, '0':29502, ' ap':1747, 'ples':3583, '.':29491, '':781, '':781, '1':29508, '0':29502, ' ap':1747, 'ples':3583, ' are':1228, ' ':29473, '5':29550 ] |
|
[1721889659] n_remain: 1015 |
|
[1721889659] eval: [ '5':29550 ] |
|
[1721889660] n_past = 18 |
|
[1721889660] last: [ '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<s>':1, 'I':29505, ' have':1274, ' ':29473, '1':29508, '0':29502, ' ap':1747, 'ples':3583, '.':29491, '':781, '':781, '1':29508, '0':29502, ' ap':1747, 'ples':3583, ' are':1228, ' ':29473, '5':29550, '0':29502 ] |
|
[1721889660] n_remain: 1014 |
|
[1721889660] eval: [ '0':29502 ] |
|
[1721889662] n_past = 19 |
|
[1721889662] last: [ '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<s>':1, 'I':29505, ' have':1274, ' ':29473, '1':29508, '0':29502, ' ap':1747, 'ples':3583, '.':29491, '':781, '':781, '1':29508, '0':29502, ' ap':1747, 'ples':3583, ' are':1228, ' ':29473, '5':29550, '0':29502, '%':29591 ] |
|
[1721889662] n_remain: 1013 |
|
[1721889662] eval: [ '%':29591 ] |
|
[1721889663] n_past = 20 |
|
[1721889663] last: [ '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<s>':1, 'I':29505, ' have':1274, ' ':29473, '1':29508, '0':29502, ' ap':1747, 'ples':3583, '.':29491, '':781, '':781, '1':29508, '0':29502, ' ap':1747, 'ples':3583, ' are':1228, ' ':29473, '5':29550, '0':29502, '%':29591, ' of':1070 ] |
|
[1721889663] n_remain: 1012 |
|
[1721889663] eval: [ ' of':1070 ] |
|
[1721889663] |
|
[1721889663] llama_print_timings: load time = 15039.00 ms |
|
[1721889663] llama_print_timings: sample time = 0.60 ms / 12 runs ( 0.05 ms per token, 19867.55 tokens per second) |
|
[1721889663] llama_print_timings: prompt eval time = 8032.80 ms / 9 tokens ( 892.53 ms per token, 1.12 tokens per second) |
|
[1721889663] llama_print_timings: eval time = 11690.98 ms / 11 runs ( 1062.82 ms per token, 0.94 tokens per second) |
|
[1721889663] llama_print_timings: total time = 20028.03 ms / 20 tokens |
|
|
