llama_model_loader: loaded meta data with 30 key-value pairs and 723 tensors from Athene-70B-IMat-GGUF/Athene-70B.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 = Athene 70B llama_model_loader: - kv 3: general.organization str = Nexusflow llama_model_loader: - kv 4: general.basename str = Athene llama_model_loader: - kv 5: general.size_label str = 70B llama_model_loader: - kv 6: general.license str = cc-by-nc-4.0 llama_model_loader: - kv 7: general.tags arr[str,4] = ["RLHF", "Nexusflow", "Athene", "Chat... llama_model_loader: - kv 8: general.languages arr[str,1] = ["en"] llama_model_loader: - kv 9: llama.block_count u32 = 80 llama_model_loader: - kv 10: llama.context_length u32 = 8192 llama_model_loader: - kv 11: llama.embedding_length u32 = 8192 llama_model_loader: - kv 12: llama.feed_forward_length u32 = 28672 llama_model_loader: - kv 13: llama.attention.head_count u32 = 64 llama_model_loader: - kv 14: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 15: llama.rope.freq_base f32 = 500000.000000 llama_model_loader: - kv 16: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 17: general.file_type u32 = 7 llama_model_loader: - kv 18: llama.vocab_size u32 = 128256 llama_model_loader: - kv 19: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 20: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 21: tokenizer.ggml.pre str = llama-bpe llama_model_loader: - kv 22: tokenizer.ggml.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 23: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 24: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "... llama_model_loader: - kv 25: tokenizer.ggml.bos_token_id u32 = 128000 llama_model_loader: - kv 26: tokenizer.ggml.eos_token_id u32 = 128009 llama_model_loader: - kv 27: tokenizer.ggml.padding_token_id u32 = 128002 llama_model_loader: - kv 28: tokenizer.chat_template str = {% set loop_messages = messages %}{% ... llama_model_loader: - kv 29: general.quantization_version u32 = 2 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 = 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: vocab_only = 0 llm_load_print_meta: n_ctx_train = 8192 llm_load_print_meta: n_embd = 8192 llm_load_print_meta: n_layer = 80 llm_load_print_meta: n_head = 64 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 = 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_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 = 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 = Athene 70B 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 = 128002 '<|reserved_special_token_0|>' 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: 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 = 0.68 MiB llm_load_tensors: offloading 25 repeating layers to GPU llm_load_tensors: offloaded 25/81 layers to GPU llm_load_tensors: CPU buffer size = 71494.28 MiB llm_load_tensors: CUDA0 buffer size = 21676.56 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 = 110.00 MiB llama_kv_cache_init: CUDA0 KV buffer size = 50.00 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 = 609 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 41.549 ms compute_imatrix: computing over 125 chunks with batch_size 512 compute_imatrix: 6.21 seconds per pass - ETA 12.93 minutes [1]6.6040,[2]4.9654,[3]4.2158,[4]5.3079,[5]5.2830,[6]4.3802,[7]4.4994,[8]4.9801,[9]5.2305, save_imatrix: stored collected data after 10 chunks in Athene-70B-IMat-GGUF/imatrix.dat [10]4.7802,[11]5.2935,[12]5.8063,[13]6.3303,[14]6.7388,[15]7.0367,[16]7.3833,[17]7.5615,[18]7.2905,[19]6.9202, save_imatrix: stored collected data after 20 chunks in Athene-70B-IMat-GGUF/imatrix.dat [20]6.9186,[21]7.0082,[22]7.0219,[23]7.3120,[24]7.3267,[25]7.7036,[26]7.6876,[27]7.2465,[28]6.9196,[29]6.9238, save_imatrix: stored collected data after 30 chunks in Athene-70B-IMat-GGUF/imatrix.dat [30]6.8880,[31]6.5472,[32]6.2482,[33]6.1213,[34]6.0183,[35]6.1065,[36]6.1466,[37]6.1005,[38]6.1802,[39]6.3539, save_imatrix: stored collected data after 40 chunks in Athene-70B-IMat-GGUF/imatrix.dat [40]6.4518,[41]6.2317,[42]6.0185,[43]5.8364,[44]5.6549,[45]5.6221,[46]5.5731,[47]5.7161,[48]5.8144,[49]5.9209, save_imatrix: stored collected data after 50 chunks in Athene-70B-IMat-GGUF/imatrix.dat [50]5.8572,[51]5.9829,[52]6.1082,[53]6.2041,[54]6.2706,[55]6.3803,[56]6.4462,[57]6.5214,[58]6.5590,[59]6.5982, save_imatrix: stored collected data after 60 chunks in Athene-70B-IMat-GGUF/imatrix.dat [60]6.5874,[61]6.5982,[62]6.6515,[63]6.7298,[64]6.6655,[65]6.6550,[66]6.6742,[67]6.6709,[68]6.6680,[69]6.6661, save_imatrix: stored collected data after 70 chunks in Athene-70B-IMat-GGUF/imatrix.dat [70]6.6896,[71]6.6932,[72]6.7114,[73]6.6993,[74]6.6703,[75]6.6811,[76]6.6850,[77]6.6742,[78]6.6739,[79]6.7207, save_imatrix: stored collected data after 80 chunks in Athene-70B-IMat-GGUF/imatrix.dat [80]6.7521,[81]6.7496,[82]6.7649,[83]6.8061,[84]6.7208,[85]6.7137,[86]6.7169,[87]6.7382,[88]6.7931,[89]6.8212, save_imatrix: stored collected data after 90 chunks in Athene-70B-IMat-GGUF/imatrix.dat [90]6.7899,[91]6.7493,[92]6.7108,[93]6.6857,[94]6.6498,[95]6.6187,[96]6.5850,[97]6.6142,[98]6.6590,[99]6.7482, save_imatrix: stored collected data after 100 chunks in Athene-70B-IMat-GGUF/imatrix.dat [100]6.8135,[101]6.8708,[102]6.9785,[103]7.0159,[104]7.0572,[105]7.0055,[106]7.0249,[107]6.9914,[108]6.9148,[109]6.8349, save_imatrix: stored collected data after 110 chunks in Athene-70B-IMat-GGUF/imatrix.dat [110]6.8814,[111]6.9228,[112]6.9417,[113]6.9482,[114]6.9912,[115]7.0329,[116]7.0516,[117]7.0875,[118]7.1372,[119]7.0931, save_imatrix: stored collected data after 120 chunks in Athene-70B-IMat-GGUF/imatrix.dat [120]7.0166,[121]6.9312,[122]6.8557,[123]6.7804,[124]6.7477,[125]6.6953, save_imatrix: stored collected data after 125 chunks in Athene-70B-IMat-GGUF/imatrix.dat llama_print_timings: load time = 28590.76 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 = 712512.01 ms / 64000 tokens ( 11.13 ms per token, 89.82 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 = 735966.69 ms / 64001 tokens Final estimate: PPL = 6.6953 +/- 0.10372