llama_model_loader: loaded meta data with 23 key-value pairs and 291 tensors from RoLlama3-8b-Instruct-IMat-GGUF/RoLlama3-8b-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 = llama llama_model_loader: - kv 1: general.name str = RoLlama3-8b-Instruct llama_model_loader: - kv 2: llama.block_count u32 = 32 llama_model_loader: - kv 3: llama.context_length u32 = 8192 llama_model_loader: - kv 4: llama.embedding_length u32 = 4096 llama_model_loader: - kv 5: llama.feed_forward_length u32 = 14336 llama_model_loader: - kv 6: llama.attention.head_count u32 = 32 llama_model_loader: - kv 7: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 8: llama.rope.freq_base f32 = 500000.000000 llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 10: general.file_type u32 = 7 llama_model_loader: - kv 11: llama.vocab_size u32 = 128256 llama_model_loader: - kv 12: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 13: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 14: tokenizer.ggml.pre str = llama-bpe llama_model_loader: - kv 15: tokenizer.ggml.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 16: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 17: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "... llama_model_loader: - kv 18: tokenizer.ggml.bos_token_id u32 = 128000 llama_model_loader: - kv 19: tokenizer.ggml.eos_token_id u32 = 128009 llama_model_loader: - kv 20: tokenizer.ggml.padding_token_id u32 = 128009 llama_model_loader: - kv 21: tokenizer.chat_template str = {% set system_message = 'Ești un asi... llama_model_loader: - kv 22: general.quantization_version u32 = 2 llama_model_loader: - type f32: 65 tensors llama_model_loader: - type q8_0: 226 tensors llm_load_vocab: special tokens cache size = 256 llm_load_vocab: token to piece cache size = 0.8000 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 = 128256 llm_load_print_meta: n_merges = 280147 llm_load_print_meta: n_ctx_train = 8192 llm_load_print_meta: n_embd = 4096 llm_load_print_meta: n_head = 32 llm_load_print_meta: n_head_kv = 8 llm_load_print_meta: n_layer = 32 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 = 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 = 500000.0 llm_load_print_meta: freq_scale_train = 1 llm_load_print_meta: n_ctx_orig_yarn = 8192 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 = 8B llm_load_print_meta: model ftype = Q8_0 llm_load_print_meta: model params = 8.03 B llm_load_print_meta: model size = 7.95 GiB (8.50 BPW) llm_load_print_meta: general.name = RoLlama3-8b-Instruct llm_load_print_meta: BOS token = 128000 '<|begin_of_text|>' llm_load_print_meta: EOS token = 128009 '<|eot_id|>' llm_load_print_meta: PAD token = 128009 '<|eot_id|>' llm_load_print_meta: LF token = 128 'Ä' llm_load_print_meta: EOT token = 128009 '<|eot_id|>' llm_load_print_meta: max token length = 256 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 = 0.30 MiB llm_load_tensors: offloading 32 repeating layers to GPU llm_load_tensors: offloading non-repeating layers to GPU llm_load_tensors: offloaded 33/33 layers to GPU llm_load_tensors: CPU buffer size = 532.31 MiB llm_load_tensors: CUDA0 buffer size = 7605.33 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 = 500000.0 llama_new_context_with_model: freq_scale = 1 llama_kv_cache_init: CUDA0 KV buffer size = 64.00 MiB llama_new_context_with_model: KV self size = 64.00 MiB, K (f16): 32.00 MiB, V (f16): 32.00 MiB llama_new_context_with_model: CUDA_Host output buffer size = 0.49 MiB llama_new_context_with_model: CUDA0 compute buffer size = 258.50 MiB llama_new_context_with_model: CUDA_Host compute buffer size = 9.01 MiB llama_new_context_with_model: graph nodes = 1030 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 41.879 ms compute_imatrix: computing over 125 chunks with batch_size 512 compute_imatrix: 0.73 seconds per pass - ETA 1.52 minutes [1]5.3197,[2]4.1203,[3]3.7466,[4]4.6688,[5]4.7522,[6]4.0511,[7]4.3325,[8]4.7194,[9]4.9221, save_imatrix: stored collected data after 10 chunks in RoLlama3-8b-Instruct-IMat-GGUF/imatrix.dat [10]4.5371,[11]4.9454,[12]5.3936,[13]5.7982,[14]6.1836,[15]6.4117,[16]6.6886,[17]6.8575,[18]6.6066,[19]6.3120, save_imatrix: stored collected data after 20 chunks in RoLlama3-8b-Instruct-IMat-GGUF/imatrix.dat [20]6.3036,[21]6.4335,[22]6.3724,[23]6.6187,[24]6.5874,[25]6.8862,[26]6.8678,[27]6.6280,[28]6.5552,[29]6.5581, save_imatrix: stored collected data after 30 chunks in RoLlama3-8b-Instruct-IMat-GGUF/imatrix.dat [30]6.5409,[31]6.2219,[32]5.9307,[33]5.8011,[34]5.7020,[35]5.7571,[36]5.8205,[37]5.7797,[38]5.8361,[39]5.9567, save_imatrix: stored collected data after 40 chunks in RoLlama3-8b-Instruct-IMat-GGUF/imatrix.dat [40]6.0255,[41]5.9107,[42]5.7491,[43]5.7262,[44]5.6353,[45]5.6632,[46]5.5978,[47]5.7036,[48]5.7899,[49]5.8828, save_imatrix: stored collected data after 50 chunks in RoLlama3-8b-Instruct-IMat-GGUF/imatrix.dat [50]5.8221,[51]5.9057,[52]6.0108,[53]6.0854,[54]6.1489,[55]6.2118,[56]6.2579,[57]6.3263,[58]6.3467,[59]6.3636, save_imatrix: stored collected data after 60 chunks in RoLlama3-8b-Instruct-IMat-GGUF/imatrix.dat [60]6.3386,[61]6.3349,[62]6.3772,[63]6.4250,[64]6.3709,[65]6.3589,[66]6.3773,[67]6.3664,[68]6.3711,[69]6.3702, save_imatrix: stored collected data after 70 chunks in RoLlama3-8b-Instruct-IMat-GGUF/imatrix.dat [70]6.3837,[71]6.3912,[72]6.4015,[73]6.3856,[74]6.3523,[75]6.3589,[76]6.3727,[77]6.3558,[78]6.3552,[79]6.3900, save_imatrix: stored collected data after 80 chunks in RoLlama3-8b-Instruct-IMat-GGUF/imatrix.dat [80]6.4211,[81]6.4179,[82]6.4221,[83]6.4511,[84]6.3773,[85]6.3770,[86]6.3915,[87]6.4025,[88]6.4275,[89]6.4389, save_imatrix: stored collected data after 90 chunks in RoLlama3-8b-Instruct-IMat-GGUF/imatrix.dat [90]6.3974,[91]6.3435,[92]6.2970,[93]6.2533,[94]6.2075,[95]6.1652,[96]6.1383,[97]6.1492,[98]6.1894,[99]6.2637, save_imatrix: stored collected data after 100 chunks in RoLlama3-8b-Instruct-IMat-GGUF/imatrix.dat [100]6.3332,[101]6.3741,[102]6.4802,[103]6.5092,[104]6.5449,[105]6.4910,[106]6.5028,[107]6.4773,[108]6.4371,[109]6.3888, save_imatrix: stored collected data after 110 chunks in RoLlama3-8b-Instruct-IMat-GGUF/imatrix.dat [110]6.4299,[111]6.4773,[112]6.4889,[113]6.4877,[114]6.5176,[115]6.5522,[116]6.5670,[117]6.5873,[118]6.6148,[119]6.5830, save_imatrix: stored collected data after 120 chunks in RoLlama3-8b-Instruct-IMat-GGUF/imatrix.dat [120]6.5531,[121]6.5227,[122]6.5207,[123]6.5083,[124]6.5082,[125]6.4824, save_imatrix: stored collected data after 125 chunks in RoLlama3-8b-Instruct-IMat-GGUF/imatrix.dat llama_print_timings: load time = 9645.06 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 = 78767.49 ms / 64000 tokens ( 1.23 ms per token, 812.52 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 = 88484.18 ms / 64001 tokens Final estimate: PPL = 6.4824 +/- 0.08632