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 = 1717701641 llama_model_loader: loaded meta data with 21 key-value pairs and 339 tensors from Qwen2-7B-IMat-GGUF/Qwen2-7B.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 llama_model_loader: - kv 2: qwen2.block_count u32 = 28 llama_model_loader: - kv 3: qwen2.context_length u32 = 131072 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 = 151643 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 = 131072 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 = 131072 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 llm_load_print_meta: BOS token = 151643 '<|endoftext|>' llm_load_print_meta: EOS token = 151643 '<|endoftext|>' 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 219.84 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: 9.51 seconds per pass - ETA 20.28 minutes [1]4.9695,[2]3.4956,[3]3.3621,[4]3.8896,[5]3.7145,[6]3.4291,[7]3.7806,[8]3.8305,[9]4.3013, save_imatrix: stored collected data after 10 chunks in Qwen2-7B-IMat-GGUF/imatrix.dat [10]4.2099,[11]4.1511,[12]4.5306,[13]5.0314,[14]5.2554,[15]5.6803,[16]5.9606,[17]6.1168,[18]6.4450,[19]6.2415, save_imatrix: stored collected data after 20 chunks in Qwen2-7B-IMat-GGUF/imatrix.dat [20]6.3804,[21]6.4032,[22]6.4033,[23]6.2858,[24]6.4758,[25]6.5836,[26]6.4775,[27]6.6194,[28]6.7914,[29]6.9911, save_imatrix: stored collected data after 30 chunks in Qwen2-7B-IMat-GGUF/imatrix.dat [30]6.9298,[31]6.7189,[32]6.4771,[33]6.3337,[34]6.2158,[35]6.1245,[36]6.1354,[37]6.1898,[38]6.2409,[39]6.2013, save_imatrix: stored collected data after 40 chunks in Qwen2-7B-IMat-GGUF/imatrix.dat [40]6.3147,[41]6.3500,[42]6.5909,[43]6.8041,[44]6.9890,[45]7.1307,[46]7.2407,[47]7.1190,[48]7.1524,[49]7.2320, save_imatrix: stored collected data after 50 chunks in Qwen2-7B-IMat-GGUF/imatrix.dat [50]7.2824,[51]7.1739,[52]7.2446,[53]7.4010,[54]7.4913,[55]7.5556,[56]7.5991,[57]7.6379,[58]7.6734,[59]7.6771, save_imatrix: stored collected data after 60 chunks in Qwen2-7B-IMat-GGUF/imatrix.dat [60]7.7062,[61]7.6684,[62]7.6223,[63]7.6667,[64]7.7187,[65]7.6695,[66]7.6755,[67]7.6750,[68]7.6023,[69]7.5436, save_imatrix: stored collected data after 70 chunks in Qwen2-7B-IMat-GGUF/imatrix.dat [70]7.5346,[71]7.5090,[72]7.4932,[73]7.5051,[74]7.4376,[75]7.3725,[76]7.3107,[77]7.3027,[78]7.2859,[79]7.2677, save_imatrix: stored collected data after 80 chunks in Qwen2-7B-IMat-GGUF/imatrix.dat [80]7.1948,[81]7.2248,[82]7.2168,[83]7.1711,[84]7.1992,[85]7.2206,[86]7.1817,[87]7.1495,[88]7.1284,[89]7.1400, save_imatrix: stored collected data after 90 chunks in Qwen2-7B-IMat-GGUF/imatrix.dat [90]7.1519,[91]7.1352,[92]7.0875,[93]7.0347,[94]6.9792,[95]6.9292,[96]6.8871,[97]6.8372,[98]6.7926,[99]6.7673, save_imatrix: stored collected data after 100 chunks in Qwen2-7B-IMat-GGUF/imatrix.dat [100]6.7767,[101]6.8014,[102]6.8891,[103]6.9670,[104]7.0356,[105]7.1477,[106]7.2207,[107]7.2442,[108]7.2290,[109]7.2329, save_imatrix: stored collected data after 110 chunks in Qwen2-7B-IMat-GGUF/imatrix.dat [110]7.2256,[111]7.1904,[112]7.1256,[113]7.1172,[114]7.1617,[115]7.1613,[116]7.1671,[117]7.1805,[118]7.2152,[119]7.2127, save_imatrix: stored collected data after 120 chunks in Qwen2-7B-IMat-GGUF/imatrix.dat [120]7.2133,[121]7.2208,[122]7.1889,[123]7.2201,[124]7.2635,[125]7.2980,[126]7.3520,[127]7.3939,[128]7.4338, save_imatrix: stored collected data after 128 chunks in Qwen2-7B-IMat-GGUF/imatrix.dat llama_print_timings: load time = 10640.81 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 = 1001145.84 ms / 65536 tokens ( 15.28 ms per token, 65.46 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 = 1003431.71 ms / 65537 tokens Final estimate: PPL = 7.4338 +/- 0.10178