[1708254748] Log start [1708254748] Cmd: /main -m 34b-beta_Q4_K_M.gguf -p "What is a Large Language Model?" -n 512 --temp 1 [1708254748] main: build = 0 (unknown) [1708254748] main: built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu [1708254748] main: seed = 1708254748 [1708254748] main: llama backend init [1708254748] main: load the model and apply lora adapter, if any [1708254748] llama_model_loader: loaded meta data with 24 key-value pairs and 543 tensors from 34b-beta_Q4_K_M.gguf (version GGUF V3 (latest)) [1708254748] llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. [1708254748] llama_model_loader: - kv 0: general.architecture str = llama [1708254748] llama_model_loader: - kv 1: general.name str = workspace [1708254748] llama_model_loader: - kv 2: llama.context_length u32 = 200000 [1708254748] llama_model_loader: - kv 3: llama.embedding_length u32 = 7168 [1708254748] llama_model_loader: - kv 4: llama.block_count u32 = 60 [1708254748] llama_model_loader: - kv 5: llama.feed_forward_length u32 = 20480 [1708254748] llama_model_loader: - kv 6: llama.rope.dimension_count u32 = 128 [1708254748] llama_model_loader: - kv 7: llama.attention.head_count u32 = 56 [1708254748] llama_model_loader: - kv 8: llama.attention.head_count_kv u32 = 8 [1708254748] llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 [1708254748] llama_model_loader: - kv 10: llama.rope.freq_base f32 = 5000000.000000 [1708254748] llama_model_loader: - kv 11: general.file_type u32 = 15 [1708254748] llama_model_loader: - kv 12: tokenizer.ggml.model str = llama [1708254748] llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,64000] = ["", "~~", "~~", "<|Human|>",... [1708254748] llama_model_loader: - kv 14: tokenizer.ggml.scores arr[f32,64000] = [-1000.000000, -1000.000000, -1000.00... [1708254748] llama_model_loader: - kv 15: tokenizer.ggml.token_type arr[i32,64000] = [3, 3, 3, 1, 1, 1, 3, 3, 3, 1, 1, 1, ... [1708254748] llama_model_loader: - kv 16: tokenizer.ggml.bos_token_id u32 = 1 [1708254748] llama_model_loader: - kv 17: tokenizer.ggml.eos_token_id u32 = 2 [1708254748] llama_model_loader: - kv 18: tokenizer.ggml.unknown_token_id u32 = 0 [1708254748] llama_model_loader: - kv 19: tokenizer.ggml.padding_token_id u32 = 0 [1708254748] llama_model_loader: - kv 20: tokenizer.ggml.add_bos_token bool = false [1708254748] llama_model_loader: - kv 21: tokenizer.ggml.add_eos_token bool = false [1708254748] llama_model_loader: - kv 22: tokenizer.chat_template str = {% for message in messages %}{{'<|im_... [1708254748] llama_model_loader: - kv 23: general.quantization_version u32 = 2 [1708254748] llama_model_loader: - type f32: 121 tensors [1708254748] llama_model_loader: - type q4_K: 361 tensors [1708254748] llama_model_loader: - type q6_K: 61 tensors [1708254748] llm_load_vocab: mismatch in special tokens definition ( 498/64000 vs 262/64000 ). [1708254748] llm_load_print_meta: format = GGUF V3 (latest) [1708254748] llm_load_print_meta: arch = llama [1708254748] llm_load_print_meta: vocab type = SPM [1708254748] llm_load_print_meta: n_vocab = 64000 [1708254748] llm_load_print_meta: n_merges = 0 [1708254748] llm_load_print_meta: n_ctx_train = 200000 [1708254748] llm_load_print_meta: n_embd = 7168 [1708254748] llm_load_print_meta: n_head = 56 [1708254748] llm_load_print_meta: n_head_kv = 8 [1708254748] llm_load_print_meta: n_layer = 60 [1708254748] llm_load_print_meta: n_rot = 128 [1708254748] llm_load_print_meta: n_embd_head_k = 128 [1708254748] llm_load_print_meta: n_embd_head_v = 128 [1708254748] llm_load_print_meta: n_gqa = 7 [1708254748] llm_load_print_meta: n_embd_k_gqa = 1024 [1708254748] llm_load_print_meta: n_embd_v_gqa = 1024 [1708254748] llm_load_print_meta: f_norm_eps = 0.0e+00 [1708254748] llm_load_print_meta: f_norm_rms_eps = 1.0e-05 [1708254748] llm_load_print_meta: f_clamp_kqv = 0.0e+00 [1708254748] llm_load_print_meta: f_max_alibi_bias = 0.0e+00 [1708254748] llm_load_print_meta: n_ff = 20480 [1708254748] llm_load_print_meta: n_expert = 0 [1708254748] llm_load_print_meta: n_expert_used = 0 [1708254748] llm_load_print_meta: rope scaling = linear [1708254748] llm_load_print_meta: freq_base_train = 5000000.0 [1708254748] llm_load_print_meta: freq_scale_train = 1 [1708254748] llm_load_print_meta: n_yarn_orig_ctx = 200000 [1708254748] llm_load_print_meta: rope_finetuned = unknown [1708254748] llm_load_print_meta: model type = 30B [1708254748] llm_load_print_meta: model ftype = Q4_K - Medium [1708254748] llm_load_print_meta: model params = 34.39 B [1708254748] llm_load_print_meta: model size = 19.24 GiB (4.81 BPW) [1708254748] llm_load_print_meta: general.name = workspace [1708254748] llm_load_print_meta: BOS token = 1 '~~' [1708254748] llm_load_print_meta: EOS token = 2 '~~' [1708254748] llm_load_print_meta: UNK token = 0 '' [1708254748] llm_load_print_meta: PAD token = 0 '' [1708254748] llm_load_print_meta: LF token = 315 '<0x0A>' [1708254748] llm_load_tensors: ggml ctx size = 0.21 MiB [1708254793] llm_load_tensors: CPU buffer size = 19700.24 MiB [1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] .[1708254793] [1708254793] llama_new_context_with_model: n_ctx = 512 [1708254793] llama_new_context_with_model: freq_base = 5000000.0 [1708254793] llama_new_context_with_model: freq_scale = 1 [1708254793] llama_kv_cache_init: CPU KV buffer size = 120.00 MiB [1708254793] llama_new_context_with_model: KV self size = 120.00 MiB, K (f16): 60.00 MiB, V (f16): 60.00 MiB [1708254793] llama_new_context_with_model: CPU input buffer size = 16.01 MiB [1708254793] llama_new_context_with_model: CPU compute buffer size = 139.00 MiB [1708254793] llama_new_context_with_model: graph splits (measure): 1 [1708254793] warming up the model with an empty run [1708254841] n_ctx: 512 [1708254841] [1708254841] system_info: n_threads = 16 / 32 | AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | [1708254841] add_bos: 0 [1708254841] tokenize the prompt [1708254841] prompt: "What is a Large Language Model?" [1708254841] tokens: [ ' What':2371, ' is':620, ' a':562, ' Large':21356, ' Lang':29527, 'ua':8949, 'ge':671, ' Model':9627, '?':100 ] [1708254841] 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 [1708254841] inp_pfx: [ ' ':59568, '':144, '':144, '###':8308, ' Inst':3335, 'ruction':3252, ':':59601, '':144, '':144 ] [1708254841] inp_sfx: [ ' ':59568, '':144, '':144, '###':8308, ' Response':21278, ':':59601, '':144, '':144 ] [1708254841] cml_pfx: [ ' ':59568, '':144, '':6, 'user':3903, '':144 ] [1708254841] cml_sfx: [ '':7, '':144, '':6, 'assis':33509, 'tan':11064, 't':59570, '':144 ] [1708254841] sampling: repeat_last_n = 64, repeat_penalty = 1.100, 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 = 1.000 mirostat = 0, mirostat_lr = 0.100, mirostat_ent = 5.000 [1708254841] sampling order: CFG -> Penalties -> top_k -> tfs_z -> typical_p -> top_p -> min_p -> temperature [1708254841] generate: n_ctx = 512, n_batch = 512, n_predict = 512, n_keep = 0 [1708254841] [1708254841] embd_inp.size(): 9, n_consumed: 0 [1708254841] eval: [ ' What':2371, ' is':620, ' a':562, ' Large':21356, ' Lang':29527, 'ua':8949, 'ge':671, ' Model':9627, '?':100 ] [1708254888] n_past = 9 [1708254888] sampled token: 2: '' [1708254888] last: [ '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, '':0, ' What':2371, ' is':620, ' a':562, ' Large':21356, ' Lang':29527, 'ua':8949, 'ge':671, ' Model':9627, '?':100, '':2 ] [1708254888] n_remain: 511 [1708254888] found EOS token [1708254888] [end of text] [1708254888] [1708254888] llama_print_timings: load time = 92761.63 ms [1708254888] llama_print_timings: sample time = 0.68 ms / 1 runs ( 0.68 ms per token, 1461.99 tokens per second) [1708254888] llama_print_timings: prompt eval time = 47314.99 ms / 9 tokens ( 5257.22 ms per token, 0.19 tokens per second) [1708254888] llama_print_timings: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second) [1708254888] llama_print_timings: total time = 47326.73 ms / 10 tokens [1708254889] Log end