|
llama_model_loader: loaded meta data with 30 key-value pairs and 292 tensors from Llama-3.1-Storm-8B-IMat-GGUF/Llama-3.1-Storm-8B.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 = Llama 3.1 Storm 8B |
|
llama_model_loader: - kv 3: general.organization str = Akjindal53244 |
|
llama_model_loader: - kv 4: general.basename str = Llama-3.1-Storm |
|
llama_model_loader: - kv 5: general.size_label str = 8B |
|
llama_model_loader: - kv 6: general.license str = llama3.1 |
|
llama_model_loader: - kv 7: general.tags arr[str,9] = ["llama-3.1", "conversational", "inst... |
|
llama_model_loader: - kv 8: general.languages arr[str,8] = ["en", "de", "fr", "it", "pt", "hi", ... |
|
llama_model_loader: - kv 9: llama.block_count u32 = 32 |
|
llama_model_loader: - kv 10: llama.context_length u32 = 131072 |
|
llama_model_loader: - kv 11: llama.embedding_length u32 = 4096 |
|
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 = 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 = 128001 |
|
llama_model_loader: - kv 28: tokenizer.chat_template str = {% if not add_generation_prompt is de... |
|
llama_model_loader: - kv 29: general.quantization_version u32 = 2 |
|
llama_model_loader: - type f32: 66 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 = 0.7999 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 = 131072 |
|
llm_load_print_meta: n_embd = 4096 |
|
llm_load_print_meta: n_layer = 32 |
|
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 = 500000.0 |
|
llm_load_print_meta: freq_scale_train = 1 |
|
llm_load_print_meta: n_ctx_orig_yarn = 131072 |
|
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 = Llama 3.1 Storm 8B |
|
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 = 128001 '<|end_of_text|>' |
|
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 = 0.27 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 = 7605.34 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 42.015 ms |
|
compute_imatrix: computing over 125 chunks with batch_size 512 |
|
compute_imatrix: 0.73 seconds per pass - ETA 1.50 minutes |
|
[1]6.0124,[2]4.6572,[3]4.1911,[4]5.2156,[5]5.4155,[6]4.5837,[7]4.8698,[8]5.4021,[9]5.5789, |
|
save_imatrix: stored collected data after 10 chunks in Llama-3.1-Storm-8B-IMat-GGUF/imatrix.dat |
|
[10]5.0688,[11]5.5106,[12]6.0390,[13]6.5314,[14]6.9329,[15]7.2193,[16]7.4800,[17]7.6691,[18]7.3980,[19]7.0706, |
|
save_imatrix: stored collected data after 20 chunks in Llama-3.1-Storm-8B-IMat-GGUF/imatrix.dat |
|
[20]7.0733,[21]7.1945,[22]7.1445,[23]7.4636,[24]7.4749,[25]7.8272,[26]7.8457,[27]7.8559,[28]8.0767,[29]8.0749, |
|
save_imatrix: stored collected data after 30 chunks in Llama-3.1-Storm-8B-IMat-GGUF/imatrix.dat |
|
[30]8.0408,[31]7.6115,[32]7.2208,[33]7.0286,[34]6.8628,[35]6.9179,[36]6.9728,[37]6.9072,[38]6.9875,[39]7.1551, |
|
save_imatrix: stored collected data after 40 chunks in Llama-3.1-Storm-8B-IMat-GGUF/imatrix.dat |
|
[40]7.2409,[41]7.2735,[42]7.3354,[43]7.5347,[44]7.6209,[45]7.8162,[46]7.6910,[47]7.8154,[48]7.8981,[49]7.9928, |
|
save_imatrix: stored collected data after 50 chunks in Llama-3.1-Storm-8B-IMat-GGUF/imatrix.dat |
|
[50]7.8693,[51]7.9958,[52]8.1297,[53]8.2087,[54]8.2692,[55]8.3443,[56]8.3829,[57]8.4346,[58]8.4464,[59]8.4611, |
|
save_imatrix: stored collected data after 60 chunks in Llama-3.1-Storm-8B-IMat-GGUF/imatrix.dat |
|
[60]8.4101,[61]8.3922,[62]8.4383,[63]8.4764,[64]8.3935,[65]8.3585,[66]8.3590,[67]8.3361,[68]8.3253,[69]8.3123, |
|
save_imatrix: stored collected data after 70 chunks in Llama-3.1-Storm-8B-IMat-GGUF/imatrix.dat |
|
[70]8.3081,[71]8.2980,[72]8.2915,[73]8.2524,[74]8.1948,[75]8.1858,[76]8.1859,[77]8.1419,[78]8.1326,[79]8.1636, |
|
save_imatrix: stored collected data after 80 chunks in Llama-3.1-Storm-8B-IMat-GGUF/imatrix.dat |
|
[80]8.1888,[81]8.1743,[82]8.1627,[83]8.1903,[84]8.0800,[85]8.0787,[86]8.0850,[87]8.0957,[88]8.1212,[89]8.1230, |
|
save_imatrix: stored collected data after 90 chunks in Llama-3.1-Storm-8B-IMat-GGUF/imatrix.dat |
|
[90]8.0615,[91]7.9831,[92]7.9131,[93]7.8558,[94]7.7917,[95]7.7356,[96]7.6925,[97]7.7021,[98]7.7456,[99]7.8389, |
|
save_imatrix: stored collected data after 100 chunks in Llama-3.1-Storm-8B-IMat-GGUF/imatrix.dat |
|
[100]7.9166,[101]7.9744,[102]8.1057,[103]8.1368,[104]8.1736,[105]8.0973,[106]8.1032,[107]8.0522,[108]7.9998,[109]7.9328, |
|
save_imatrix: stored collected data after 110 chunks in Llama-3.1-Storm-8B-IMat-GGUF/imatrix.dat |
|
[110]7.9776,[111]8.0367,[112]8.0485,[113]8.0399,[114]8.0761,[115]8.1101,[116]8.1191,[117]8.1420,[118]8.1765,[119]8.1172, |
|
save_imatrix: stored collected data after 120 chunks in Llama-3.1-Storm-8B-IMat-GGUF/imatrix.dat |
|
[120]8.1317,[121]8.1403,[122]8.1682,[123]8.2098,[124]8.2470,[125]8.2647, |
|
save_imatrix: stored collected data after 125 chunks in Llama-3.1-Storm-8B-IMat-GGUF/imatrix.dat |
|
|
|
llama_print_timings: load time = 2202.93 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 = 71666.08 ms / 64000 tokens ( 1.12 ms per token, 893.03 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 = 73977.79 ms / 64001 tokens |
|
|
|
Final estimate: PPL = 8.2647 +/- 0.12491 |
|
|
