llama_model_loader: loaded meta data with 35 key-value pairs and 363 tensors from Mistral-Nemo-Instruct-2407-IMat-GGUF/Mistral-Nemo-Instruct-2407.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 = llama llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = Mistral Nemo Instruct 2407 llama_model_loader: - kv 3: general.version str = 2407 llama_model_loader: - kv 4: general.finetune str = Instruct llama_model_loader: - kv 5: general.basename str = Mistral-Nemo llama_model_loader: - kv 6: general.size_label str = 12B llama_model_loader: - kv 7: general.license str = apache-2.0 llama_model_loader: - kv 8: general.languages arr[str,9] = ["en", "fr", "de", "es", "it", "pt", ... llama_model_loader: - kv 9: llama.block_count u32 = 40 llama_model_loader: - kv 10: llama.context_length u32 = 1024000 llama_model_loader: - kv 11: llama.embedding_length u32 = 5120 llama_model_loader: - kv 12: llama.feed_forward_length u32 = 14336 llama_model_loader: - kv 13: llama.attention.head_count u32 = 32 llama_model_loader: - kv 14: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 15: llama.rope.freq_base f32 = 1000000.000000 llama_model_loader: - kv 16: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 17: llama.attention.key_length u32 = 128 llama_model_loader: - kv 18: llama.attention.value_length u32 = 128 llama_model_loader: - kv 19: general.file_type u32 = 7 llama_model_loader: - kv 20: llama.vocab_size u32 = 131072 llama_model_loader: - kv 21: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 22: tokenizer.ggml.add_space_prefix bool = false llama_model_loader: - kv 23: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 24: tokenizer.ggml.pre str = tekken llama_model_loader: - kv 25: tokenizer.ggml.tokens arr[str,131072] = ["", "", "", "[INST]", "[... llama_model_loader: - kv 26: tokenizer.ggml.token_type arr[i32,131072] = [3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, ... llama_model_loader: - kv 27: tokenizer.ggml.merges arr[str,269443] = ["Ä  Ä ", "Ä  t", "e r", "i n", "Ä  Ä... llama_model_loader: - kv 28: tokenizer.ggml.bos_token_id u32 = 1 llama_model_loader: - kv 29: tokenizer.ggml.eos_token_id u32 = 2 llama_model_loader: - kv 30: tokenizer.ggml.unknown_token_id u32 = 0 llama_model_loader: - kv 31: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 32: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 33: tokenizer.chat_template str = {%- if messages[0]['role'] == 'system... llama_model_loader: - kv 34: general.quantization_version u32 = 2 llama_model_loader: - type f32: 81 tensors llama_model_loader: - type q8_0: 282 tensors llm_load_vocab: special tokens cache size = 1000 llm_load_vocab: token to piece cache size = 0.8498 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = llama llm_load_print_meta: vocab type = BPE llm_load_print_meta: n_vocab = 131072 llm_load_print_meta: n_merges = 269443 llm_load_print_meta: vocab_only = 0 llm_load_print_meta: n_ctx_train = 1024000 llm_load_print_meta: n_embd = 5120 llm_load_print_meta: n_layer = 40 llm_load_print_meta: n_head = 32 llm_load_print_meta: n_head_kv = 8 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 = 4 llm_load_print_meta: n_embd_k_gqa = 1024 llm_load_print_meta: n_embd_v_gqa = 1024 llm_load_print_meta: f_norm_eps = 0.0e+00 llm_load_print_meta: f_norm_rms_eps = 1.0e-05 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 = 14336 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 = 0 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 = 1024000 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 = 13B llm_load_print_meta: model ftype = Q8_0 llm_load_print_meta: model params = 12.25 B llm_load_print_meta: model size = 12.12 GiB (8.50 BPW) llm_load_print_meta: general.name = Mistral Nemo Instruct 2407 llm_load_print_meta: BOS token = 1 '' llm_load_print_meta: EOS token = 2 '' llm_load_print_meta: UNK token = 0 '' llm_load_print_meta: LF token = 1196 'Ä' llm_load_print_meta: max token length = 150 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 = 0.34 MiB llm_load_tensors: offloading 40 repeating layers to GPU llm_load_tensors: offloading non-repeating layers to GPU llm_load_tensors: offloaded 41/41 layers to GPU llm_load_tensors: CPU buffer size = 680.00 MiB llm_load_tensors: CUDA0 buffer size = 11731.58 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 = 80.00 MiB llama_new_context_with_model: KV self size = 80.00 MiB, K (f16): 40.00 MiB, V (f16): 40.00 MiB llama_new_context_with_model: CUDA_Host output buffer size = 0.50 MiB llama_new_context_with_model: CUDA0 compute buffer size = 266.00 MiB llama_new_context_with_model: CUDA_Host compute buffer size = 11.01 MiB llama_new_context_with_model: graph nodes = 1286 llama_new_context_with_model: graph splits = 2 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 99.114 ms compute_imatrix: computing over 128 chunks with batch_size 512 compute_imatrix: 0.92 seconds per pass - ETA 1.95 minutes [1]5.2918,[2]3.7923,[3]3.4130,[4]4.1305,[5]4.0173,[6]3.4890,[7]3.8390,[8]4.1619,[9]4.4018, save_imatrix: stored collected data after 10 chunks in Mistral-Nemo-Instruct-2407-IMat-GGUF/imatrix.dat [10]4.0506,[11]4.3860,[12]4.6928,[13]5.0106,[14]5.2390,[15]5.5682,[16]5.7882,[17]5.9757,[18]6.2078,[19]5.9615, save_imatrix: stored collected data after 20 chunks in Mistral-Nemo-Instruct-2407-IMat-GGUF/imatrix.dat [20]6.0467,[21]6.1736,[22]6.1387,[23]6.3176,[24]6.3173,[25]6.5500,[26]6.3835,[27]6.1659,[28]6.1253,[29]6.0949, save_imatrix: stored collected data after 30 chunks in Mistral-Nemo-Instruct-2407-IMat-GGUF/imatrix.dat [30]6.0361,[31]5.7638,[32]5.5991,[33]5.5706,[34]5.5152,[35]5.4836,[36]5.6390,[37]5.6570,[38]5.7241,[39]5.8588, save_imatrix: stored collected data after 40 chunks in Mistral-Nemo-Instruct-2407-IMat-GGUF/imatrix.dat [40]5.9745,[41]6.0201,[42]5.9388,[43]5.9528,[44]6.0180,[45]6.0375,[46]5.9824,[47]6.0451,[48]6.1780,[49]6.2906, save_imatrix: stored collected data after 50 chunks in Mistral-Nemo-Instruct-2407-IMat-GGUF/imatrix.dat [50]6.1854,[51]6.2280,[52]6.2645,[53]6.3241,[54]6.4478,[55]6.5426,[56]6.5950,[57]6.6163,[58]6.6213,[59]6.5759, save_imatrix: stored collected data after 60 chunks in Mistral-Nemo-Instruct-2407-IMat-GGUF/imatrix.dat [60]6.5416,[61]6.4588,[62]6.4180,[63]6.4422,[64]6.4844,[65]6.4035,[66]6.3765,[67]6.3733,[68]6.3543,[69]6.3294, save_imatrix: stored collected data after 70 chunks in Mistral-Nemo-Instruct-2407-IMat-GGUF/imatrix.dat [70]6.3320,[71]6.3605,[72]6.3260,[73]6.3491,[74]6.3383,[75]6.3215,[76]6.3317,[77]6.3033,[78]6.2680,[79]6.2206, save_imatrix: stored collected data after 80 chunks in Mistral-Nemo-Instruct-2407-IMat-GGUF/imatrix.dat [80]6.2476,[81]6.2664,[82]6.2552,[83]6.2480,[84]6.2366,[85]6.2680,[86]6.2172,[87]6.1927,[88]6.2088,[89]6.2263, save_imatrix: stored collected data after 90 chunks in Mistral-Nemo-Instruct-2407-IMat-GGUF/imatrix.dat [90]6.2319,[91]6.2014,[92]6.1644,[93]6.1216,[94]6.0799,[95]6.0400,[96]6.0043,[97]5.9634,[98]5.9249,[99]5.8866, save_imatrix: stored collected data after 100 chunks in Mistral-Nemo-Instruct-2407-IMat-GGUF/imatrix.dat [100]5.9012,[101]5.9680,[102]6.0227,[103]6.0767,[104]6.1288,[105]6.2229,[106]6.2293,[107]6.2602,[108]6.2032,[109]6.2032, save_imatrix: stored collected data after 110 chunks in Mistral-Nemo-Instruct-2407-IMat-GGUF/imatrix.dat [110]6.1724,[111]6.1121,[112]6.0538,[113]6.0541,[114]6.1129,[115]6.1164,[116]6.1133,[117]6.1276,[118]6.1574,[119]6.1555, save_imatrix: stored collected data after 120 chunks in Mistral-Nemo-Instruct-2407-IMat-GGUF/imatrix.dat [120]6.1496,[121]6.1651,[122]6.1554,[123]6.1832,[124]6.1819,[125]6.1751,[126]6.2086,[127]6.2030,[128]6.2041, save_imatrix: stored collected data after 128 chunks in Mistral-Nemo-Instruct-2407-IMat-GGUF/imatrix.dat llama_print_timings: load time = 5276.23 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 = 100983.08 ms / 65536 tokens ( 1.54 ms per token, 648.98 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 = 106203.71 ms / 65537 tokens Final estimate: PPL = 6.2041 +/- 0.08244