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 = 1717697740 llama_model_loader: loaded meta data with 21 key-value pairs and 339 tensors from Qwen2-7B-Instruct-IMat-GGUF/Qwen2-7B-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 = Qwen2-7B-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 = 3584 llama_model_loader: - kv 5: qwen2.feed_forward_length u32 = 18944 llama_model_loader: - kv 6: qwen2.attention.head_count u32 = 28 llama_model_loader: - kv 7: qwen2.attention.head_count_kv u32 = 4 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,152064] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 14: tokenizer.ggml.token_type arr[i32,152064] = [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: 339 tensors llm_load_vocab: special tokens cache size = 421 llm_load_vocab: token to piece cache size = 0.9352 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 = 152064 llm_load_print_meta: n_merges = 151387 llm_load_print_meta: n_ctx_train = 32768 llm_load_print_meta: n_embd = 3584 llm_load_print_meta: n_head = 28 llm_load_print_meta: n_head_kv = 4 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 = 7 llm_load_print_meta: n_embd_k_gqa = 512 llm_load_print_meta: n_embd_v_gqa = 512 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 = 18944 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 = 7.62 B llm_load_print_meta: model size = 28.37 GiB (32.00 BPW) llm_load_print_meta: general.name = Qwen2-7B-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 = 29051.27 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 28.00 MiB of pinned memory: no CUDA-capable device is detected llama_kv_cache_init: CPU KV buffer size = 28.00 MiB llama_new_context_with_model: KV self size = 28.00 MiB, K (f16): 14.00 MiB, V (f16): 14.00 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 304.00 MiB of pinned memory: no CUDA-capable device is detected llama_new_context_with_model: CUDA_Host compute buffer size = 304.00 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 134.862 ms compute_imatrix: computing over 128 chunks with batch_size 512 ggml_cuda_host_malloc: failed to allocate 297.00 MiB of pinned memory: no CUDA-capable device is detected compute_imatrix: 5.83 seconds per pass - ETA 12.43 minutes [1]5.2431,[2]3.6575,[3]3.5214,[4]4.0316,[5]3.8406,[6]3.5461,[7]3.9259,[8]3.9744,[9]4.4528, save_imatrix: stored collected data after 10 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat [10]4.3487,[11]4.2804,[12]4.6780,[13]5.1953,[14]5.4247,[15]5.8578,[16]6.1402,[17]6.3224,[18]6.6883,[19]6.4787, save_imatrix: stored collected data after 20 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat [20]6.6193,[21]6.6480,[22]6.6875,[23]6.5822,[24]6.7794,[25]6.9199,[26]6.8175,[27]6.9938,[28]7.1831,[29]7.3993, save_imatrix: stored collected data after 30 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat [30]7.3371,[31]7.1142,[32]6.8538,[33]6.6928,[34]6.5678,[35]6.4676,[36]6.4760,[37]6.5382,[38]6.6077,[39]6.5628, save_imatrix: stored collected data after 40 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat [40]6.6730,[41]6.7105,[42]6.9699,[43]7.1938,[44]7.3804,[45]7.5275,[46]7.6390,[47]7.5134,[48]7.5529,[49]7.6308, save_imatrix: stored collected data after 50 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat [50]7.6883,[51]7.5708,[52]7.6462,[53]7.8149,[54]7.9160,[55]7.9928,[56]8.0562,[57]8.0966,[58]8.1381,[59]8.1570, save_imatrix: stored collected data after 60 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat [60]8.1872,[61]8.1423,[62]8.0908,[63]8.1405,[64]8.1899,[65]8.1356,[66]8.1378,[67]8.1375,[68]8.0566,[69]7.9921, save_imatrix: stored collected data after 70 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat [70]7.9788,[71]7.9511,[72]7.9320,[73]7.9393,[74]7.8678,[75]7.7943,[76]7.7284,[77]7.7182,[78]7.6973,[79]7.6761, save_imatrix: stored collected data after 80 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat [80]7.5971,[81]7.6296,[82]7.6202,[83]7.5695,[84]7.5974,[85]7.6167,[86]7.5767,[87]7.5450,[88]7.5208,[89]7.5294, save_imatrix: stored collected data after 90 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat [90]7.5453,[91]7.5267,[92]7.4733,[93]7.4148,[94]7.3559,[95]7.2984,[96]7.2522,[97]7.1986,[98]7.1516,[99]7.1231, save_imatrix: stored collected data after 100 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat [100]7.1325,[101]7.1585,[102]7.2489,[103]7.3299,[104]7.4038,[105]7.5229,[106]7.6021,[107]7.6242,[108]7.6081,[109]7.6135, save_imatrix: stored collected data after 110 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat [110]7.6038,[111]7.5752,[112]7.5097,[113]7.5043,[114]7.5486,[115]7.5493,[116]7.5537,[117]7.5654,[118]7.5997,[119]7.5962, save_imatrix: stored collected data after 120 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat [120]7.5948,[121]7.6063,[122]7.5791,[123]7.6107,[124]7.6528,[125]7.6853,[126]7.7439,[127]7.7875,[128]7.8279, save_imatrix: stored collected data after 128 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat llama_print_timings: load time = 6575.63 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 = 728194.87 ms / 65536 tokens ( 11.11 ms per token, 90.00 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 = 729815.78 ms / 65537 tokens Final estimate: PPL = 7.8279 +/- 0.11030