|
|
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 42.419 ms |
|
|
compute_imatrix: computing over 125 chunks with batch_size 512 |
|
|
compute_imatrix: 6.08 seconds per pass - ETA 12.67 minutes |
|
|
[1]5.6607,[2]4.3690,[3]3.7982,[4]4.7219,[5]4.7386,[6]3.9920,[7]4.0529,[8]4.4649,[9]4.6956, |
|
|
save_imatrix: stored collected data after 10 chunks in Athene-70B-IMat-GGUF/imatrix.dat |
|
|
[10]4.3121,[11]4.7598,[12]5.2267,[13]5.6945,[14]6.0797,[15]6.3689,[16]6.6771,[17]6.8512,[18]6.6230,[19]6.3086, |
|
|
save_imatrix: stored collected data after 20 chunks in Athene-70B-IMat-GGUF/imatrix.dat |
|
|
[20]6.3107,[21]6.3880,[22]6.3809,[23]6.6130,[24]6.6190,[25]6.9449,[26]6.9232,[27]6.5382,[28]6.2443,[29]6.2519, |
|
|
save_imatrix: stored collected data after 30 chunks in Athene-70B-IMat-GGUF/imatrix.dat |
|
|
[30]6.2276,[31]5.9329,[32]5.6729,[33]5.5590,[34]5.4676,[35]5.5469,[36]5.5922,[37]5.5570,[38]5.6292,[39]5.7870, |
|
|
save_imatrix: stored collected data after 40 chunks in Athene-70B-IMat-GGUF/imatrix.dat |
|
|
[40]5.8744,[41]5.6817,[42]5.4975,[43]5.3352,[44]5.1781,[45]5.1503,[46]5.1112,[47]5.2359,[48]5.3254,[49]5.4250, |
|
|
save_imatrix: stored collected data after 50 chunks in Athene-70B-IMat-GGUF/imatrix.dat |
|
|
[50]5.3756,[51]5.4817,[52]5.5847,[53]5.6688,[54]5.7287,[55]5.8171,[56]5.8762,[57]5.9448,[58]5.9811,[59]6.0067, |
|
|
save_imatrix: stored collected data after 60 chunks in Athene-70B-IMat-GGUF/imatrix.dat |
|
|
[60]5.9915,[61]5.9967,[62]6.0451,[63]6.1154,[64]6.0609,[65]6.0525,[66]6.0706,[67]6.0641,[68]6.0615,[69]6.0570, |
|
|
save_imatrix: stored collected data after 70 chunks in Athene-70B-IMat-GGUF/imatrix.dat |
|
|
[70]6.0743,[71]6.0788,[72]6.0915,[73]6.0795,[74]6.0542,[75]6.0624,[76]6.0654,[77]6.0518,[78]6.0436,[79]6.0849, |
|
|
save_imatrix: stored collected data after 80 chunks in Athene-70B-IMat-GGUF/imatrix.dat |
|
|
[80]6.1125,[81]6.1110,[82]6.1236,[83]6.1581,[84]6.0838,[85]6.0791,[86]6.0836,[87]6.1009,[88]6.1437,[89]6.1654, |
|
|
save_imatrix: stored collected data after 90 chunks in Athene-70B-IMat-GGUF/imatrix.dat |
|
|
[90]6.1387,[91]6.1030,[92]6.0702,[93]6.0462,[94]6.0139,[95]5.9859,[96]5.9572,[97]5.9806,[98]6.0224,[99]6.0990, |
|
|
save_imatrix: stored collected data after 100 chunks in Athene-70B-IMat-GGUF/imatrix.dat |
|
|
[100]6.1586,[101]6.2090,[102]6.3093,[103]6.3401,[104]6.3770,[105]6.3299,[106]6.3455,[107]6.3164,[108]6.2510,[109]6.1812, |
|
|
save_imatrix: stored collected data after 110 chunks in Athene-70B-IMat-GGUF/imatrix.dat |
|
|
[110]6.2216,[111]6.2588,[112]6.2743,[113]6.2800,[114]6.3150,[115]6.3538,[116]6.3714,[117]6.4002,[118]6.4411,[119]6.4024, |
|
|
save_imatrix: stored collected data after 120 chunks in Athene-70B-IMat-GGUF/imatrix.dat |
|
|
[120]6.3365,[121]6.2623,[122]6.1963,[123]6.1311,[124]6.0994,[125]6.0507, |
|
|
save_imatrix: stored collected data after 125 chunks in Athene-70B-IMat-GGUF/imatrix.dat |
|
|
|
|
|
llama_print_timings: load time = 34594.23 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 = 673117.85 ms / 64000 tokens ( 10.52 ms per token, 95.08 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 = 703206.64 ms / 64001 tokens |
|
|
|
|
|
Final estimate: PPL = 6.0507 +/- 0.08376 |
|
|
|
