build: 3785 (64c6af31) with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
llama_model_loader: loaded meta data with 34 key-value pairs and 290 tensors from Qwen2.5-0.5B-Instruct-IMat-GGUF/Qwen2.5-0.5B-Instruct.Q8_0.gguf.hardlink.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.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Qwen2.5 0.5B Instruct
llama_model_loader: - kv   3:                           general.finetune str              = Instruct
llama_model_loader: - kv   4:                           general.basename str              = Qwen2.5
llama_model_loader: - kv   5:                         general.size_label str              = 0.5B
llama_model_loader: - kv   6:                            general.license str              = apache-2.0
llama_model_loader: - kv   7:                       general.license.link str              = https://huggingface.co/Qwen/Qwen2.5-0...
llama_model_loader: - kv   8:                   general.base_model.count u32              = 1
llama_model_loader: - kv   9:                  general.base_model.0.name str              = Qwen2.5 0.5B
llama_model_loader: - kv  10:          general.base_model.0.organization str              = Qwen
llama_model_loader: - kv  11:              general.base_model.0.repo_url str              = https://huggingface.co/Qwen/Qwen2.5-0.5B
llama_model_loader: - kv  12:                               general.tags arr[str,2]       = ["chat", "text-generation"]
llama_model_loader: - kv  13:                          general.languages arr[str,1]       = ["en"]
llama_model_loader: - kv  14:                          qwen2.block_count u32              = 24
llama_model_loader: - kv  15:                       qwen2.context_length u32              = 32768
llama_model_loader: - kv  16:                     qwen2.embedding_length u32              = 896
llama_model_loader: - kv  17:                  qwen2.feed_forward_length u32              = 4864
llama_model_loader: - kv  18:                 qwen2.attention.head_count u32              = 14
llama_model_loader: - kv  19:              qwen2.attention.head_count_kv u32              = 2
llama_model_loader: - kv  20:                       qwen2.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv  21:     qwen2.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  22:                          general.file_type u32              = 7
llama_model_loader: - kv  23:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  24:                         tokenizer.ggml.pre str              = qwen2
llama_model_loader: - kv  25:                      tokenizer.ggml.tokens arr[str,151936]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  26:                  tokenizer.ggml.token_type arr[i32,151936]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  27:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  28:                tokenizer.ggml.eos_token_id u32              = 151645
llama_model_loader: - kv  29:            tokenizer.ggml.padding_token_id u32              = 151643
llama_model_loader: - kv  30:                tokenizer.ggml.bos_token_id u32              = 151643
llama_model_loader: - kv  31:               tokenizer.ggml.add_bos_token bool             = false
llama_model_loader: - kv  32:                    tokenizer.chat_template str              = {%- if tools %}\n    {{- '<|im_start|>...
llama_model_loader: - kv  33:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:  121 tensors
llama_model_loader: - type q8_0:  169 tensors
llm_load_vocab: special tokens cache size = 22
llm_load_vocab: token to piece cache size = 0.9310 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: vocab_only       = 0
llm_load_print_meta: n_ctx_train      = 32768
llm_load_print_meta: n_embd           = 896
llm_load_print_meta: n_layer          = 24
llm_load_print_meta: n_head           = 14
llm_load_print_meta: n_head_kv        = 2
llm_load_print_meta: n_rot            = 64
llm_load_print_meta: n_swa            = 0
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_ctx_orig_yarn  = 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: ssm_dt_b_c_rms   = 0
llm_load_print_meta: model type       = 1B
llm_load_print_meta: model ftype      = Q8_0
llm_load_print_meta: model params     = 494.03 M
llm_load_print_meta: model size       = 500.79 MiB (8.50 BPW) 
llm_load_print_meta: general.name     = Qwen2.5 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|>'
llm_load_print_meta: max token length = 256
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
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 =    0.25 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 =   137.94 MiB
llm_load_tensors:      CUDA0 buffer size =   500.84 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 (n_threads_batch = 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 | RISCV_VECT = 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 138.654 ms
compute_imatrix: computing over 128 chunks with batch_size 512
compute_imatrix: 0.36 seconds per pass - ETA 0.75 minutes
[1]7.9682,[2]5.9445,[3]5.8811,[4]7.0440,[5]6.8317,[6]6.3818,[7]7.1962,[8]7.1075,[9]7.7926,[10]7.3545,[11]7.1359,[12]7.8729,[13]8.8051,[14]9.0799,[15]9.8729,[16]10.4115,[17]10.6743,[18]11.3420,[19]10.8674,[20]10.9033,[21]11.1268,[22]11.1346,[23]10.9051,[24]11.2866,[25]11.5903,[26]11.4937,[27]11.8234,[28]12.1064,[29]12.5883,[30]12.5654,[31]12.0887,[32]11.5623,[33]11.2204,[34]11.0625,[35]10.8576,[36]10.8785,[37]10.9343,[38]11.1171,[39]11.1783,[40]11.4766,[41]11.5545,[42]12.0473,[43]12.5054,[44]12.9404,[45]13.2580,[46]13.4466,[47]13.2806,[48]13.3244,[49]13.4145,[50]13.4653,[51]13.3043,[52]13.3726,[53]13.6527,[54]13.8243,[55]14.0258,[56]14.1177,[57]14.1280,[58]14.1928,[59]14.2089,[60]14.2025,[61]14.1319,[62]14.0815,[63]14.1511,[64]14.2516,[65]14.1177,[66]14.0853,[67]14.0350,[68]13.8819,[69]13.7514,[70]13.7061,[71]13.5941,[72]13.5378,[73]13.5276,[74]13.3511,[75]13.2085,[76]13.0566,[77]12.9796,[78]12.9334,[79]12.8661,[80]12.7301,[81]12.7526,[82]12.7203,[83]12.6196,[84]12.6556,[85]12.6450,[86]12.5210,[87]12.4733,[88]12.4713,[89]12.5217,[90]12.5637,[91]12.5665,[92]12.4282,[93]12.3183,[94]12.1736,[95]12.0442,[96]11.9314,[97]11.8035,[98]11.6834,[99]11.6557,[100]11.6743,[101]11.7112,[102]11.8812,[103]12.0334,[104]12.1496,[105]12.3488,[106]12.4719,[107]12.5221,[108]12.4606,[109]12.4409,[110]12.4464,[111]12.4179,[112]12.3578,[113]12.3950,[114]12.4549,[115]12.4594,[116]12.4827,[117]12.4992,[118]12.5449,[119]12.5426,[120]12.5279,[121]12.5243,[122]12.4539,[123]12.5254,[124]12.6199,[125]12.7012,[126]12.8118,[127]12.8985,[128]12.9894,
Final estimate: PPL = 12.9894 +/- 0.20056

llama_perf_context_print:        load time =     961.75 ms
llama_perf_context_print: prompt eval time =   17565.37 ms / 65536 tokens (    0.27 ms per token,  3730.98 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 =   19120.52 ms / 65537 tokens