main: build = 3086 (554c247c) main: built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu main: seed = 1717699094 llama_model_loader: loaded meta data with 21 key-value pairs and 338 tensors from Qwen2-1.5B-Instruct-IMat-GGUF/Qwen2-1.5B-Instruct.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 = qwen2 llama_model_loader: - kv 1: general.name str = Qwen2-1.5B-Instruct llama_model_loader: - kv 2: qwen2.block_count u32 = 28 llama_model_loader: - kv 3: qwen2.context_length u32 = 32768 llama_model_loader: - kv 4: qwen2.embedding_length u32 = 1536 llama_model_loader: - kv 5: qwen2.feed_forward_length u32 = 8960 llama_model_loader: - kv 6: qwen2.attention.head_count u32 = 12 llama_model_loader: - kv 7: qwen2.attention.head_count_kv u32 = 2 llama_model_loader: - kv 8: qwen2.rope.freq_base f32 = 1000000.000000 llama_model_loader: - kv 9: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 10: general.file_type u32 = 0 llama_model_loader: - kv 11: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 12: tokenizer.ggml.pre str = qwen2 llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 14: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 15: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... llama_model_loader: - kv 16: tokenizer.ggml.eos_token_id u32 = 151645 llama_model_loader: - kv 17: tokenizer.ggml.padding_token_id u32 = 151643 llama_model_loader: - kv 18: tokenizer.ggml.bos_token_id u32 = 151643 llama_model_loader: - kv 19: tokenizer.chat_template str = {% for message in messages %}{% if lo... llama_model_loader: - kv 20: general.quantization_version u32 = 2 llama_model_loader: - type f32: 338 tensors llm_load_vocab: special tokens cache size = 293 llm_load_vocab: token to piece cache size = 0.9338 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = qwen2 llm_load_print_meta: vocab type = BPE llm_load_print_meta: n_vocab = 151936 llm_load_print_meta: n_merges = 151387 llm_load_print_meta: n_ctx_train = 32768 llm_load_print_meta: n_embd = 1536 llm_load_print_meta: n_head = 12 llm_load_print_meta: n_head_kv = 2 llm_load_print_meta: n_layer = 28 llm_load_print_meta: n_rot = 128 llm_load_print_meta: n_embd_head_k = 128 llm_load_print_meta: n_embd_head_v = 128 llm_load_print_meta: n_gqa = 6 llm_load_print_meta: n_embd_k_gqa = 256 llm_load_print_meta: n_embd_v_gqa = 256 llm_load_print_meta: f_norm_eps = 0.0e+00 llm_load_print_meta: f_norm_rms_eps = 1.0e-06 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 = 8960 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 = 2 llm_load_print_meta: rope scaling = linear llm_load_print_meta: freq_base_train = 1000000.0 llm_load_print_meta: freq_scale_train = 1 llm_load_print_meta: n_yarn_orig_ctx = 32768 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: model type = ?B llm_load_print_meta: model ftype = all F32 llm_load_print_meta: model params = 1.54 B llm_load_print_meta: model size = 5.75 GiB (32.00 BPW) llm_load_print_meta: general.name = Qwen2-1.5B-Instruct llm_load_print_meta: BOS token = 151643 '<|endoftext|>' llm_load_print_meta: EOS token = 151645 '<|im_end|>' llm_load_print_meta: PAD token = 151643 '<|endoftext|>' llm_load_print_meta: LF token = 148848 'ÄĬ' llm_load_print_meta: EOT token = 151645 '<|im_end|>' ggml_cuda_init: failed to initialize CUDA: no CUDA-capable device is detected llm_load_tensors: ggml ctx size = 0.16 MiB llm_load_tensors: offloading 0 repeating layers to GPU llm_load_tensors: offloaded 0/29 layers to GPU llm_load_tensors: CPU buffer size = 5888.80 MiB ............................................................................ llama_new_context_with_model: n_ctx = 512 llama_new_context_with_model: n_batch = 512 llama_new_context_with_model: n_ubatch = 512 llama_new_context_with_model: flash_attn = 0 llama_new_context_with_model: freq_base = 1000000.0 llama_new_context_with_model: freq_scale = 1 ggml_cuda_host_malloc: failed to allocate 14.00 MiB of pinned memory: no CUDA-capable device is detected llama_kv_cache_init: CPU KV buffer size = 14.00 MiB llama_new_context_with_model: KV self size = 14.00 MiB, K (f16): 7.00 MiB, V (f16): 7.00 MiB ggml_cuda_host_malloc: failed to allocate 0.58 MiB of pinned memory: no CUDA-capable device is detected llama_new_context_with_model: CPU output buffer size = 0.58 MiB ggml_cuda_host_malloc: failed to allocate 299.75 MiB of pinned memory: no CUDA-capable device is detected llama_new_context_with_model: CUDA_Host compute buffer size = 299.75 MiB llama_new_context_with_model: graph nodes = 986 llama_new_context_with_model: graph splits = 1 system_info: n_threads = 25 / 32 | AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 1 | AVX512_VBMI = 1 | AVX512_VNNI = 1 | AVX512_BF16 = 1 | FMA = 1 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | compute_imatrix: tokenizing the input .. compute_imatrix: tokenization took 186.265 ms compute_imatrix: computing over 128 chunks with batch_size 512 ggml_cuda_host_malloc: failed to allocate 296.75 MiB of pinned memory: no CUDA-capable device is detected compute_imatrix: 2.29 seconds per pass - ETA 4.87 minutes [1]7.1794,[2]5.3199,[3]5.0981,[4]5.9752,[5]5.7835,[6]5.2552,[7]5.7864,[8]6.0622,[9]6.6684, save_imatrix: stored collected data after 10 chunks in Qwen2-1.5B-Instruct-IMat-GGUF/imatrix.dat [10]6.3131,[11]6.1593,[12]6.6159,[13]7.3010,[14]7.5457,[15]8.1246,[16]8.5172,[17]8.6254,[18]9.1089,[19]8.7735, save_imatrix: stored collected data after 20 chunks in Qwen2-1.5B-Instruct-IMat-GGUF/imatrix.dat [20]8.8735,[21]8.9815,[22]8.9399,[23]8.8281,[24]9.1095,[25]9.2579,[26]9.1932,[27]9.4461,[28]9.6855,[29]9.9663, save_imatrix: stored collected data after 30 chunks in Qwen2-1.5B-Instruct-IMat-GGUF/imatrix.dat [30]9.8592,[31]9.4931,[32]9.0860,[33]8.8363,[34]8.6863,[35]8.5233,[36]8.5521,[37]8.6577,[38]8.7731,[39]8.8116, save_imatrix: stored collected data after 40 chunks in Qwen2-1.5B-Instruct-IMat-GGUF/imatrix.dat [40]8.9578,[41]9.0102,[42]9.3965,[43]9.7582,[44]10.0824,[45]10.3412,[46]10.4822,[47]10.2945,[48]10.3357,[49]10.4302, save_imatrix: stored collected data after 50 chunks in Qwen2-1.5B-Instruct-IMat-GGUF/imatrix.dat [50]10.4853,[51]10.3433,[52]10.4344,[53]10.6284,[54]10.7379,[55]10.8603,[56]10.8917,[57]10.9144,[58]10.9545,[59]10.9503, save_imatrix: stored collected data after 60 chunks in Qwen2-1.5B-Instruct-IMat-GGUF/imatrix.dat [60]10.9594,[61]10.8658,[62]10.8120,[63]10.8641,[64]10.9371,[65]10.8705,[66]10.8679,[67]10.8664,[68]10.7898,[69]10.7536, save_imatrix: stored collected data after 70 chunks in Qwen2-1.5B-Instruct-IMat-GGUF/imatrix.dat [70]10.7331,[71]10.6848,[72]10.6564,[73]10.6672,[74]10.5752,[75]10.4921,[76]10.4074,[77]10.3769,[78]10.3653,[79]10.3378, save_imatrix: stored collected data after 80 chunks in Qwen2-1.5B-Instruct-IMat-GGUF/imatrix.dat [80]10.2752,[81]10.2969,[82]10.2784,[83]10.2086,[84]10.2478,[85]10.2686,[86]10.2003,[87]10.1497,[88]10.1223,[89]10.1420, save_imatrix: stored collected data after 90 chunks in Qwen2-1.5B-Instruct-IMat-GGUF/imatrix.dat [90]10.1469,[91]10.1228,[92]10.0276,[93]9.9300,[94]9.8304,[95]9.7334,[96]9.6549,[97]9.5611,[98]9.4757,[99]9.4329, save_imatrix: stored collected data after 100 chunks in Qwen2-1.5B-Instruct-IMat-GGUF/imatrix.dat [100]9.4376,[101]9.4618,[102]9.5825,[103]9.6851,[104]9.7748,[105]9.9226,[106]10.0201,[107]10.0571,[108]10.0244,[109]10.0150, save_imatrix: stored collected data after 110 chunks in Qwen2-1.5B-Instruct-IMat-GGUF/imatrix.dat [110]10.0121,[111]9.9965,[112]9.9513,[113]9.9758,[114]10.0245,[115]10.0159,[116]10.0171,[117]10.0315,[118]10.0678,[119]10.0564, save_imatrix: stored collected data after 120 chunks in Qwen2-1.5B-Instruct-IMat-GGUF/imatrix.dat [120]10.0484,[121]10.0499,[122]10.0063,[123]10.0592,[124]10.1353,[125]10.1928,[126]10.2749,[127]10.3396,[128]10.4061, save_imatrix: stored collected data after 128 chunks in Qwen2-1.5B-Instruct-IMat-GGUF/imatrix.dat llama_print_timings: load time = 2730.80 ms llama_print_timings: sample time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second) llama_print_timings: prompt eval time = 1324946.47 ms / 65536 tokens ( 20.22 ms per token, 49.46 tokens per second) llama_print_timings: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second) llama_print_timings: total time = 1327865.09 ms / 65537 tokens Final estimate: PPL = 10.4061 +/- 0.15435