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