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 = 1717697289 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: 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 = 0.32 MiB llm_load_tensors: offloading 23 repeating layers to GPU llm_load_tensors: offloaded 23/29 layers to GPU llm_load_tensors: CPU buffer size = 29051.27 MiB llm_load_tensors: CUDA0 buffer size = 20448.03 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: CUDA_Host KV buffer size = 5.00 MiB llama_kv_cache_init: CUDA0 KV buffer size = 23.00 MiB llama_new_context_with_model: KV self size = 28.00 MiB, K (f16): 14.00 MiB, V (f16): 14.00 MiB llama_new_context_with_model: CUDA_Host output buffer size = 0.58 MiB llama_new_context_with_model: CUDA0 compute buffer size = 2383.00 MiB llama_new_context_with_model: CUDA_Host compute buffer size = 8.01 MiB llama_new_context_with_model: graph nodes = 986 llama_new_context_with_model: graph splits = 74 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 133.474 ms compute_imatrix: computing over 128 chunks with batch_size 512 compute_imatrix: 0.88 seconds per pass - ETA 1.87 minutes [1]nan,[2]nan,[3]nan,[4]nan,[5]nan,[6]nan,[7]nan,[8]nan,[9]nan, save_imatrix: stored collected data after 10 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat [10]nan,[11]nan,[12]nan,[13]nan,[14]nan,[15]nan,[16]nan,[17]nan,[18]nan,[19]nan, save_imatrix: stored collected data after 20 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat [20]nan,[21]nan,[22]nan,[23]nan,[24]nan,[25]nan,[26]nan,[27]nan,[28]nan,[29]nan, save_imatrix: stored collected data after 30 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat [30]nan,[31]nan,[32]nan,[33]nan,[34]nan,[35]nan,[36]nan,[37]nan,[38]nan,[39]nan, save_imatrix: stored collected data after 40 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat [40]nan,[41]nan,[42]nan,[43]nan,[44]nan,[45]nan,[46]nan,[47]nan,[48]nan,[49]nan, save_imatrix: stored collected data after 50 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat [50]nan,[51]nan,[52]nan,[53]nan,[54]nan,[55]nan,[56]nan,[57]nan,[58]nan,[59]nan, save_imatrix: stored collected data after 60 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat [60]nan,[61]nan,[62]nan,[63]nan,[64]nan,[65]nan,[66]nan,[67]nan,[68]nan,[69]nan, save_imatrix: stored collected data after 70 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat [70]nan,[71]nan,[72]nan,[73]nan,[74]nan,[75]nan,[76]nan,[77]nan,[78]nan,[79]nan, save_imatrix: stored collected data after 80 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat [80]nan,[81]nan,[82]nan,[83]nan,[84]nan,[85]nan,[86]nan,[87]nan,[88]nan,[89]nan, save_imatrix: stored collected data after 90 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat [90]nan,[91]nan,[92]nan,[93]nan,[94]nan,[95]nan,[96]nan,[97]nan,[98]nan,[99]nan, save_imatrix: stored collected data after 100 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat [100]nan,[101]nan,[102]nan,[103]nan,[104]nan,[105]nan,[106]nan,[107]nan,[108]nan,[109]nan, save_imatrix: stored collected data after 110 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat [110]nan,[111]nan,[112]nan,[113]nan,[114]nan,[115]nan,[116]nan,[117]nan,[118]nan,[119]nan, save_imatrix: stored collected data after 120 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat [120]nan,[121]nan,[122]nan,[123]nan,[124]nan,[125]nan,[126]nan,[127]nan,[128]nan, save_imatrix: stored collected data after 128 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat llama_print_timings: load time = 2910.65 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 = 95408.80 ms / 65536 tokens ( 1.46 ms per token, 686.90 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 = 98358.01 ms / 65537 tokens Unexpected negative standard deviation of log(prob)