build: 3787 (6026da52) 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 338 tensors from Qwen2.5-Math-1.5B-Instruct-IMat-GGUF/Qwen2.5-Math-1.5B-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 Math 1.5B Instruct llama_model_loader: - kv 3: general.finetune str = Instruct llama_model_loader: - kv 4: general.basename str = Qwen2.5-Math llama_model_loader: - kv 5: general.size_label str = 1.5B 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-M... llama_model_loader: - kv 8: general.base_model.count u32 = 1 llama_model_loader: - kv 9: general.base_model.0.name str = Qwen2.5 Math 1.5B 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-M... 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 = 28 llama_model_loader: - kv 15: qwen2.context_length u32 = 4096 llama_model_loader: - kv 16: qwen2.embedding_length u32 = 1536 llama_model_loader: - kv 17: qwen2.feed_forward_length u32 = 8960 llama_model_loader: - kv 18: qwen2.attention.head_count u32 = 12 llama_model_loader: - kv 19: qwen2.attention.head_count_kv u32 = 2 llama_model_loader: - kv 20: qwen2.rope.freq_base f32 = 10000.000000 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: 141 tensors llama_model_loader: - type q8_0: 197 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 = 4096 llm_load_print_meta: n_embd = 1536 llm_load_print_meta: n_layer = 28 llm_load_print_meta: n_head = 12 llm_load_print_meta: n_head_kv = 2 llm_load_print_meta: n_rot = 128 llm_load_print_meta: n_swa = 0 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 = 10000.0 llm_load_print_meta: freq_scale_train = 1 llm_load_print_meta: n_ctx_orig_yarn = 4096 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 = ?B llm_load_print_meta: model ftype = Q8_0 llm_load_print_meta: model params = 1.54 B llm_load_print_meta: model size = 1.53 GiB (8.50 BPW) llm_load_print_meta: general.name = Qwen2.5 Math 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|>' 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 = 0.30 MiB llm_load_tensors: offloading 28 repeating layers to GPU llm_load_tensors: offloading non-repeating layers to GPU llm_load_tensors: offloaded 29/29 layers to GPU llm_load_tensors: CPU buffer size = 236.47 MiB llm_load_tensors: CUDA0 buffer size = 1564.63 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 = 10000.0 llama_new_context_with_model: freq_scale = 1 llama_kv_cache_init: CUDA0 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 llama_new_context_with_model: CUDA_Host output buffer size = 0.58 MiB llama_new_context_with_model: CUDA0 compute buffer size = 299.75 MiB llama_new_context_with_model: CUDA_Host compute buffer size = 4.01 MiB llama_new_context_with_model: graph nodes = 986 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 135.209 ms compute_imatrix: computing over 128 chunks with batch_size 512 compute_imatrix: 0.39 seconds per pass - ETA 0.82 minutes [1]76.3534,[2]44.0303,[3]31.6350,[4]37.0097,[5]36.9772,[6]40.0268,[7]38.6530,[8]39.8474,[9]41.0920,[10]39.7125,[11]35.6288,[12]37.8969,[13]41.1135,[14]41.3761,[15]45.6199,[16]46.1514,[17]47.9945,[18]51.2402,[19]50.3270,[20]49.3483,[21]58.2344,[22]62.7025,[23]62.9567,[24]64.2388,[25]63.9855,[26]65.5560,[27]68.5196,[28]71.2349,[29]73.9642,[30]78.4475,[31]83.2389,[32]83.4088,[33]79.8979,[34]76.4622,[35]72.9805,[36]82.5251,[37]94.8080,[38]101.6563,[39]101.6932,[40]102.5662,[41]102.5259,[42]105.8845,[43]107.2122,[44]108.9494,[45]110.5805,[46]111.8862,[47]109.9830,[48]107.9592,[49]106.6537,[50]105.1476,[51]104.0614,[52]103.1540,[53]106.6089,[54]106.5142,[55]108.6973,[56]108.7682,[57]107.6624,[58]106.6510,[59]105.5954,[60]105.6071,[61]104.0959,[62]103.6760,[63]104.2393,[64]105.8032,[65]105.3703,[66]103.8000,[67]102.4559,[68]100.5003,[69]100.1043,[70]98.5139,[71]96.2124,[72]94.4408,[73]93.1674,[74]90.8032,[75]88.3730,[76]86.1229,[77]84.7100,[78]83.7798,[79]83.0234,[80]81.6884,[81]81.0501,[82]80.2872,[83]79.1985,[84]79.5808,[85]79.0158,[86]80.0719,[87]79.2331,[88]78.5611,[89]78.4093,[90]78.2067,[91]77.6363,[92]75.3036,[93]73.1595,[94]70.9507,[95]68.8827,[96]66.9942,[97]65.1730,[98]63.3927,[99]64.1802,[100]64.3003,[101]64.0369,[102]64.5606,[103]64.9922,[104]65.3317,[105]66.1201,[106]66.9926,[107]67.1652,[108]66.6607,[109]66.7239,[110]66.8040,[111]65.5796,[112]64.5900,[113]64.3368,[114]64.3996,[115]64.6678,[116]64.7223,[117]65.0348,[118]65.3331,[119]65.3733,[120]65.2025,[121]65.0798,[122]64.4611,[123]64.6898,[124]65.0316,[125]65.5398,[126]66.2413,[127]66.7434,[128]67.0922, Final estimate: PPL = 67.0922 +/- 1.51836 llama_perf_context_print: load time = 1153.45 ms llama_perf_context_print: prompt eval time = 30925.78 ms / 65536 tokens ( 0.47 ms per token, 2119.14 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 = 32688.54 ms / 65537 tokens