llama_model_loader: loaded meta data with 32 key-value pairs and 292 tensors from Llama-3.1-SuperNova-Lite-IMat-GGUF/Llama-3.1-SuperNova-Lite.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 SuperNova Lite
llama_model_loader: - kv 3: general.organization str = Arcee Ai
llama_model_loader: - kv 4: general.size_label str = 8.0B
llama_model_loader: - kv 5: general.license str = llama3
llama_model_loader: - kv 6: general.base_model.count u32 = 1
llama_model_loader: - kv 7: general.base_model.0.name str = Meta Llama 3.1 8B Instruct
llama_model_loader: - kv 8: general.base_model.0.organization str = Meta Llama
llama_model_loader: - kv 9: general.base_model.0.repo_url str = https://huggingface.co/meta-llama/Met...
llama_model_loader: - kv 10: general.languages arr[str,1] = ["en"]
llama_model_loader: - kv 11: general.datasets arr[str,1] = ["arcee-ai/EvolKit-20k"]
llama_model_loader: - kv 12: llama.block_count u32 = 32
llama_model_loader: - kv 13: llama.context_length u32 = 131072
llama_model_loader: - kv 14: llama.embedding_length u32 = 4096
llama_model_loader: - kv 15: llama.feed_forward_length u32 = 14336
llama_model_loader: - kv 16: llama.attention.head_count u32 = 32
llama_model_loader: - kv 17: llama.attention.head_count_kv u32 = 8
llama_model_loader: - kv 18: llama.rope.freq_base f32 = 500000.000000
llama_model_loader: - kv 19: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 20: general.file_type u32 = 7
llama_model_loader: - kv 21: llama.vocab_size u32 = 128256
llama_model_loader: - kv 22: llama.rope.dimension_count u32 = 128
llama_model_loader: - kv 23: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 24: tokenizer.ggml.pre str = smaug-bpe
llama_model_loader: - kv 25: tokenizer.ggml.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 26: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 27: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
llama_model_loader: - kv 28: tokenizer.ggml.bos_token_id u32 = 128000
llama_model_loader: - kv 29: tokenizer.ggml.eos_token_id u32 = 128009
llama_model_loader: - kv 30: tokenizer.chat_template str = {% set loop_messages = messages %}{% ...
llama_model_loader: - kv 31: 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: ssm_dt_b_c_rms = 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 SuperNova Lite
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|>'
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 (n_threads_batch = 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 131.258 ms
compute_imatrix: computing over 125 chunks with batch_size 512
compute_imatrix: 0.73 seconds per pass - ETA 1.52 minutes
[1]5.9054,[2]4.5288,[3]4.1229,[4]5.1188,[5]5.2694,[6]4.4648,[7]4.7487,[8]5.2632,[9]5.4645,
save_imatrix: stored collected data after 10 chunks in Llama-3.1-SuperNova-Lite-IMat-GGUF/imatrix.dat
[10]4.9764,[11]5.4254,[12]5.9339,[13]6.4061,[14]6.8196,[15]7.1133,[16]7.3655,[17]7.5513,[18]7.3084,[19]6.9742,
save_imatrix: stored collected data after 20 chunks in Llama-3.1-SuperNova-Lite-IMat-GGUF/imatrix.dat
[20]6.9703,[21]7.0845,[22]7.0159,[23]7.3318,[24]7.3170,[25]7.6580,[26]7.6621,[27]7.6912,[28]7.9148,[29]7.9204,
save_imatrix: stored collected data after 30 chunks in Llama-3.1-SuperNova-Lite-IMat-GGUF/imatrix.dat
[30]7.8816,[31]7.4623,[32]7.0817,[33]6.9040,[34]6.7512,[35]6.8090,[36]6.8563,[37]6.7930,[38]6.8720,[39]7.0476,
save_imatrix: stored collected data after 40 chunks in Llama-3.1-SuperNova-Lite-IMat-GGUF/imatrix.dat
[40]7.1342,[41]7.1737,[42]7.2620,[43]7.4605,[44]7.5596,[45]7.7648,[46]7.6456,[47]7.7715,[48]7.8573,[49]7.9611,
save_imatrix: stored collected data after 50 chunks in Llama-3.1-SuperNova-Lite-IMat-GGUF/imatrix.dat
[50]7.8411,[51]7.9472,[52]8.0760,[53]8.1585,[54]8.2176,[55]8.2971,[56]8.3406,[57]8.3919,[58]8.4165,[59]8.4164,
save_imatrix: stored collected data after 60 chunks in Llama-3.1-SuperNova-Lite-IMat-GGUF/imatrix.dat
[60]8.3626,[61]8.3449,[62]8.3876,[63]8.4264,[64]8.3430,[65]8.2895,[66]8.2917,[67]8.2546,[68]8.2382,[69]8.2134,
save_imatrix: stored collected data after 70 chunks in Llama-3.1-SuperNova-Lite-IMat-GGUF/imatrix.dat
[70]8.2049,[71]8.1895,[72]8.1833,[73]8.1404,[74]8.0796,[75]8.0678,[76]8.0688,[77]8.0258,[78]8.0131,[79]8.0468,
save_imatrix: stored collected data after 80 chunks in Llama-3.1-SuperNova-Lite-IMat-GGUF/imatrix.dat
[80]8.0683,[81]8.0483,[82]8.0420,[83]8.0620,[84]7.9553,[85]7.9559,[86]7.9619,[87]7.9743,[88]8.0047,[89]8.0065,
save_imatrix: stored collected data after 90 chunks in Llama-3.1-SuperNova-Lite-IMat-GGUF/imatrix.dat
[90]7.9404,[91]7.8574,[92]7.7855,[93]7.7171,[94]7.6493,[95]7.5867,[96]7.5429,[97]7.5490,[98]7.5928,[99]7.6823,
save_imatrix: stored collected data after 100 chunks in Llama-3.1-SuperNova-Lite-IMat-GGUF/imatrix.dat
[100]7.7560,[101]7.8142,[102]7.9387,[103]7.9712,[104]8.0099,[105]7.9307,[106]7.9264,[107]7.8750,[108]7.8282,[109]7.7569,
save_imatrix: stored collected data after 110 chunks in Llama-3.1-SuperNova-Lite-IMat-GGUF/imatrix.dat
[110]7.8064,[111]7.8672,[112]7.8771,[113]7.8745,[114]7.9108,[115]7.9486,[116]7.9609,[117]7.9808,[118]8.0168,[119]7.9594,
save_imatrix: stored collected data after 120 chunks in Llama-3.1-SuperNova-Lite-IMat-GGUF/imatrix.dat
[120]7.9724,[121]7.9857,[122]8.0078,[123]8.0521,[124]8.0841,[125]8.1073,
save_imatrix: stored collected data after 125 chunks in Llama-3.1-SuperNova-Lite-IMat-GGUF/imatrix.dat
llama_perf_print: load time = 4333.98 ms
llama_perf_print: prompt eval time = 71217.65 ms / 64000 tokens ( 1.11 ms per token, 898.65 tokens per second)
llama_perf_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_print: total time = 75666.02 ms / 64001 tokens
Final estimate: PPL = 8.1073 +/- 0.11958