main: build = 3058 (30e238b2) main: built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu main: seed = 1717189635 llama_model_loader: loaded meta data with 25 key-value pairs and 723 tensors from Meta-Llama-3-70B-Instruct-abliterated-v3.5.Q8_0.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 = Meta-Llama-3-70B-Instruct-abliterated... llama_model_loader: - kv 2: llama.block_count u32 = 80 llama_model_loader: - kv 3: llama.context_length u32 = 8192 llama_model_loader: - kv 4: llama.embedding_length u32 = 8192 llama_model_loader: - kv 5: llama.feed_forward_length u32 = 28672 llama_model_loader: - kv 6: llama.attention.head_count u32 = 64 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.chat_template str = {% set loop_messages = messages %}{% ... llama_model_loader: - kv 21: general.quantization_version u32 = 2 llama_model_loader: - kv 22: split.no u16 = 0 llama_model_loader: - kv 23: split.count u16 = 0 llama_model_loader: - kv 24: split.tensors.count i32 = 723 llama_model_loader: - type f32: 161 tensors llama_model_loader: - type q8_0: 562 tensors llm_load_vocab: special tokens cache size = 256 llm_load_vocab: token to piece cache size = 1.5928 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 = 8192 llm_load_print_meta: n_head = 64 llm_load_print_meta: n_head_kv = 8 llm_load_print_meta: n_layer = 80 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 = 8 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 = 28672 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_yarn_orig_ctx = 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 = 70B llm_load_print_meta: model ftype = Q8_0 llm_load_print_meta: model params = 70.55 B llm_load_print_meta: model size = 69.82 GiB (8.50 BPW) llm_load_print_meta: general.name = Meta-Llama-3-70B-Instruct-abliterated-v3.5 llm_load_print_meta: BOS token = 128000 '<|begin_of_text|>' llm_load_print_meta: EOS token = 128009 '<|eot_id|>' llm_load_print_meta: LF token = 128 'Ä' llm_load_print_meta: EOT token = 128009 '<|eot_id|>' 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 = 0.74 MiB llm_load_tensors: offloading 23 repeating layers to GPU llm_load_tensors: offloaded 23/81 layers to GPU llm_load_tensors: CPU buffer size = 71494.28 MiB llm_load_tensors: CUDA0 buffer size = 19942.44 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: CUDA_Host KV buffer size = 114.00 MiB llama_kv_cache_init: CUDA0 KV buffer size = 46.00 MiB llama_new_context_with_model: KV self size = 160.00 MiB, K (f16): 80.00 MiB, V (f16): 80.00 MiB llama_new_context_with_model: CUDA_Host output buffer size = 0.49 MiB llama_new_context_with_model: CUDA0 compute buffer size = 1331.12 MiB llama_new_context_with_model: CUDA_Host compute buffer size = 17.01 MiB llama_new_context_with_model: graph nodes = 2566 llama_new_context_with_model: graph splits = 631 system_info: n_threads = 32 / 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 43.919 ms compute_imatrix: computing over 125 chunks with batch_size 512 compute_imatrix: 5.03 seconds per pass - ETA 10.48 minutes [1]6.0299,[2]4.9246,[3]4.3350,[4]5.2603,[5]5.3356,[6]4.4245,[7]4.5128,[8]4.9960,[9]5.2117, save_imatrix: stored collected data after 10 chunks in Meta-Llama-3-70B-Instruct-abliterated-v3.5-IMat-GGUF/imatrix.dat [10]4.7652,[11]5.2864,[12]5.7827,[13]6.2313,[14]6.6502,[15]6.8963,[16]7.2162,[17]7.4192,[18]7.1377,[19]6.7935, save_imatrix: stored collected data after 20 chunks in Meta-Llama-3-70B-Instruct-abliterated-v3.5-IMat-GGUF/imatrix.dat [20]6.7903,[21]6.9130,[22]6.8973,[23]7.1753,[24]7.1424,[25]7.4987,[26]7.5153,[27]7.1168,[28]6.8683,[29]6.8810, save_imatrix: stored collected data after 30 chunks in Meta-Llama-3-70B-Instruct-abliterated-v3.5-IMat-GGUF/imatrix.dat [30]6.8435,[31]6.5088,[32]6.1927,[33]6.0464,[34]5.9345,[35]6.0107,[36]6.0695,[37]6.0254,[38]6.1048,[39]6.2725, save_imatrix: stored collected data after 40 chunks in Meta-Llama-3-70B-Instruct-abliterated-v3.5-IMat-GGUF/imatrix.dat [40]6.3660,[41]6.1815,[42]5.9769,[43]5.9275,[44]5.8078,[45]5.7785,[46]5.7151,[47]5.8522,[48]5.9435,[49]6.0425, save_imatrix: stored collected data after 50 chunks in Meta-Llama-3-70B-Instruct-abliterated-v3.5-IMat-GGUF/imatrix.dat [50]5.9779,[51]6.0886,[52]6.2123,[53]6.3082,[54]6.3799,[55]6.4696,[56]6.5283,[57]6.5963,[58]6.6250,[59]6.6484, save_imatrix: stored collected data after 60 chunks in Meta-Llama-3-70B-Instruct-abliterated-v3.5-IMat-GGUF/imatrix.dat [60]6.6355,[61]6.6356,[62]6.6859,[63]6.7479,[64]6.6837,[65]6.6598,[66]6.6695,[67]6.6561,[68]6.6521,[69]6.6417, save_imatrix: stored collected data after 70 chunks in Meta-Llama-3-70B-Instruct-abliterated-v3.5-IMat-GGUF/imatrix.dat [70]6.6508,[71]6.6521,[72]6.6629,[73]6.6454,[74]6.6165,[75]6.6284,[76]6.6360,[77]6.6234,[78]6.6200,[79]6.6617, save_imatrix: stored collected data after 80 chunks in Meta-Llama-3-70B-Instruct-abliterated-v3.5-IMat-GGUF/imatrix.dat [80]6.6900,[81]6.6857,[82]6.7030,[83]6.7294,[84]6.6462,[85]6.6509,[86]6.6529,[87]6.6708,[88]6.7142,[89]6.7299, save_imatrix: stored collected data after 90 chunks in Meta-Llama-3-70B-Instruct-abliterated-v3.5-IMat-GGUF/imatrix.dat [90]6.6917,[91]6.6476,[92]6.6037,[93]6.5698,[94]6.5286,[95]6.4881,[96]6.4893,[97]6.5106,[98]6.5497,[99]6.6270, save_imatrix: stored collected data after 100 chunks in Meta-Llama-3-70B-Instruct-abliterated-v3.5-IMat-GGUF/imatrix.dat [100]6.6900,[101]6.7389,[102]6.8478,[103]6.8841,[104]6.9202,[105]6.8548,[106]6.8672,[107]6.8289,[108]6.7632,[109]6.6914, save_imatrix: stored collected data after 110 chunks in Meta-Llama-3-70B-Instruct-abliterated-v3.5-IMat-GGUF/imatrix.dat [110]6.7287,[111]6.7779,[112]6.7930,[113]6.8060,[114]6.8440,[115]6.8934,[116]6.9108,[117]6.9391,[118]6.9750,[119]6.9357, save_imatrix: stored collected data after 120 chunks in Meta-Llama-3-70B-Instruct-abliterated-v3.5-IMat-GGUF/imatrix.dat [120]6.8696,[121]6.7890,[122]6.7378,[123]6.6867,[124]6.6589,[125]6.6244, save_imatrix: stored collected data after 125 chunks in Meta-Llama-3-70B-Instruct-abliterated-v3.5-IMat-GGUF/imatrix.dat llama_print_timings: load time = 8534.89 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 = 797658.74 ms / 64000 tokens ( 12.46 ms per token, 80.23 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 = 802631.68 ms / 64001 tokens Final estimate: PPL = 6.6244 +/- 0.10022