|
main: build = 3086 (554c247c) |
|
main: built with cc (Ubuntu 13.2.0-23ubuntu4) 13.2.0 for x86_64-linux-gnu |
|
main: seed = 1717697501 |
|
llama_model_loader: loaded meta data with 21 key-value pairs and 290 tensors from Qwen2-0.5B-Instruct-IMat-GGUF/Qwen2-0.5B-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 = Qwen2-0.5B-Instruct |
|
llama_model_loader: - kv 2: qwen2.block_count u32 = 24 |
|
llama_model_loader: - kv 3: qwen2.context_length u32 = 32768 |
|
llama_model_loader: - kv 4: qwen2.embedding_length u32 = 896 |
|
llama_model_loader: - kv 5: qwen2.feed_forward_length u32 = 4864 |
|
llama_model_loader: - kv 6: qwen2.attention.head_count u32 = 14 |
|
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: 290 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 = 896 |
|
llm_load_print_meta: n_head = 14 |
|
llm_load_print_meta: n_head_kv = 2 |
|
llm_load_print_meta: n_layer = 24 |
|
llm_load_print_meta: n_rot = 64 |
|
llm_load_print_meta: n_embd_head_k = 64 |
|
llm_load_print_meta: n_embd_head_v = 64 |
|
llm_load_print_meta: n_gqa = 7 |
|
llm_load_print_meta: n_embd_k_gqa = 128 |
|
llm_load_print_meta: n_embd_v_gqa = 128 |
|
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 = 4864 |
|
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 = 1B |
|
llm_load_print_meta: model ftype = all F32 |
|
llm_load_print_meta: model params = 494.03 M |
|
llm_load_print_meta: model size = 1.84 GiB (32.00 BPW) |
|
llm_load_print_meta: general.name = Qwen2-0.5B-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: GGML_CUDA_FORCE_MMQ: no |
|
ggml_cuda_init: CUDA_USE_TENSOR_CORES: yes |
|
ggml_cuda_init: found 1 CUDA devices: |
|
Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9, VMM: yes |
|
llm_load_tensors: ggml ctx size = 0.28 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: CPU buffer size = 519.31 MiB |
|
llm_load_tensors: CUDA0 buffer size = 1884.59 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 |
|
llama_kv_cache_init: CUDA0 KV buffer size = 6.00 MiB |
|
llama_new_context_with_model: KV self size = 6.00 MiB, K (f16): 3.00 MiB, V (f16): 3.00 MiB |
|
llama_new_context_with_model: CUDA_Host output buffer size = 0.58 MiB |
|
llama_new_context_with_model: CUDA0 compute buffer size = 298.50 MiB |
|
llama_new_context_with_model: CUDA_Host compute buffer size = 2.76 MiB |
|
llama_new_context_with_model: graph nodes = 846 |
|
llama_new_context_with_model: graph splits = 2 |
|
|
|
system_info: n_threads = 25 / 32 | 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 = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | |
|
compute_imatrix: tokenizing the input .. |
|
compute_imatrix: tokenization took 143.46 ms |
|
compute_imatrix: computing over 128 chunks with batch_size 512 |
|
compute_imatrix: 0.32 seconds per pass - ETA 0.68 minutes |
|
[1]11.0153,[2]8.7867,[3]7.8438,[4]9.5496,[5]9.3272,[6]8.4608,[7]9.2335,[8]9.6817,[9]10.4469, |
|
save_imatrix: stored collected data after 10 chunks in Qwen2-0.5B-Instruct-IMat-GGUF/imatrix.dat |
|
[10]9.6325,[11]9.1945,[12]9.9034,[13]10.8543,[14]11.0685,[15]11.8463,[16]12.3478,[17]12.4503,[18]13.0519,[19]12.5067, |
|
save_imatrix: stored collected data after 20 chunks in Qwen2-0.5B-Instruct-IMat-GGUF/imatrix.dat |
|
[20]12.5579,[21]12.6907,[22]12.7226,[23]12.5846,[24]13.0383,[25]13.2262,[26]13.2079,[27]13.6637,[28]14.0292,[29]14.4747, |
|
save_imatrix: stored collected data after 30 chunks in Qwen2-0.5B-Instruct-IMat-GGUF/imatrix.dat |
|
[30]14.3979,[31]13.7993,[32]13.1442,[33]12.7399,[34]12.4904,[35]12.2049,[36]12.3080,[37]12.6005,[38]12.8030,[39]12.8264, |
|
save_imatrix: stored collected data after 40 chunks in Qwen2-0.5B-Instruct-IMat-GGUF/imatrix.dat |
|
[40]13.0478,[41]13.0751,[42]13.6493,[43]14.1599,[44]14.6647,[45]15.0588,[46]15.2725,[47]15.0340,[48]15.0376,[49]15.1503, |
|
save_imatrix: stored collected data after 50 chunks in Qwen2-0.5B-Instruct-IMat-GGUF/imatrix.dat |
|
[50]15.1859,[51]15.0006,[52]15.0761,[53]15.3538,[54]15.5192,[55]15.7389,[56]15.8111,[57]15.8110,[58]15.8510,[59]15.8512, |
|
save_imatrix: stored collected data after 60 chunks in Qwen2-0.5B-Instruct-IMat-GGUF/imatrix.dat |
|
[60]15.8503,[61]15.7101,[62]15.6407,[63]15.7145,[64]15.8063,[65]15.7094,[66]15.6743,[67]15.6515,[68]15.5856,[69]15.5664, |
|
save_imatrix: stored collected data after 70 chunks in Qwen2-0.5B-Instruct-IMat-GGUF/imatrix.dat |
|
[70]15.5587,[71]15.4788,[72]15.4158,[73]15.4249,[74]15.2522,[75]15.1291,[76]15.0129,[77]14.9624,[78]14.9531,[79]14.9062, |
|
save_imatrix: stored collected data after 80 chunks in Qwen2-0.5B-Instruct-IMat-GGUF/imatrix.dat |
|
[80]14.8102,[81]14.8351,[82]14.8070,[83]14.6925,[84]14.7681,[85]14.8005,[86]14.6922,[87]14.6163,[88]14.5540,[89]14.5760, |
|
save_imatrix: stored collected data after 90 chunks in Qwen2-0.5B-Instruct-IMat-GGUF/imatrix.dat |
|
[90]14.5867,[91]14.5719,[92]14.3912,[93]14.2202,[94]14.0447,[95]13.8821,[96]13.7340,[97]13.5649,[98]13.4127,[99]13.3627, |
|
save_imatrix: stored collected data after 100 chunks in Qwen2-0.5B-Instruct-IMat-GGUF/imatrix.dat |
|
[100]13.3850,[101]13.4151,[102]13.5983,[103]13.7427,[104]13.8673,[105]14.0567,[106]14.1836,[107]14.2397,[108]14.1732,[109]14.1509, |
|
save_imatrix: stored collected data after 110 chunks in Qwen2-0.5B-Instruct-IMat-GGUF/imatrix.dat |
|
[110]14.1576,[111]14.1077,[112]14.0437,[113]14.0704,[114]14.1317,[115]14.1182,[116]14.1220,[117]14.1334,[118]14.1737,[119]14.1457, |
|
save_imatrix: stored collected data after 120 chunks in Qwen2-0.5B-Instruct-IMat-GGUF/imatrix.dat |
|
[120]14.1093,[121]14.0986,[122]14.0078,[123]14.0817,[124]14.1812,[125]14.2818,[126]14.3994,[127]14.4974,[128]14.5959, |
|
save_imatrix: stored collected data after 128 chunks in Qwen2-0.5B-Instruct-IMat-GGUF/imatrix.dat |
|
|
|
llama_print_timings: load time = 978.27 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 = 16847.44 ms / 65536 tokens ( 0.26 ms per token, 3889.97 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 = 18657.16 ms / 65537 tokens |
|
|
|
Final estimate: PPL = 14.5959 +/- 0.23103 |
|
|
