llama_model_loader: loaded meta data with 34 key-value pairs and 292 tensors from Hermes-3-Llama-3.1-8B-IMat-GGUF/Hermes-3-Llama-3.1-8B.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 = Hermes 3 Llama 3.1 8B llama_model_loader: - kv 3: general.organization str = NousResearch llama_model_loader: - kv 4: general.basename str = Hermes-3-Llama-3.1 llama_model_loader: - kv 5: general.size_label str = 8B llama_model_loader: - kv 6: general.license str = llama3 llama_model_loader: - kv 7: general.base_model.count u32 = 1 llama_model_loader: - kv 8: general.base_model.0.name str = Meta Llama 3.1 8B llama_model_loader: - kv 9: general.base_model.0.organization str = Meta Llama llama_model_loader: - kv 10: general.base_model.0.repo_url str = https://huggingface.co/meta-llama/Met... llama_model_loader: - kv 11: general.tags arr[str,12] = ["Llama-3", "instruct", "finetune", "... llama_model_loader: - kv 12: general.languages arr[str,1] = ["en"] llama_model_loader: - kv 13: llama.block_count u32 = 32 llama_model_loader: - kv 14: llama.context_length u32 = 131072 llama_model_loader: - kv 15: llama.embedding_length u32 = 4096 llama_model_loader: - kv 16: llama.feed_forward_length u32 = 14336 llama_model_loader: - kv 17: llama.attention.head_count u32 = 32 llama_model_loader: - kv 18: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 19: llama.rope.freq_base f32 = 500000.000000 llama_model_loader: - kv 20: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 21: general.file_type u32 = 7 llama_model_loader: - kv 22: llama.vocab_size u32 = 128256 llama_model_loader: - kv 23: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 24: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 25: tokenizer.ggml.pre str = llama-bpe llama_model_loader: - kv 26: tokenizer.ggml.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 27: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 28: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "... llama_model_loader: - kv 29: tokenizer.ggml.bos_token_id u32 = 128000 llama_model_loader: - kv 30: tokenizer.ggml.eos_token_id u32 = 128040 llama_model_loader: - kv 31: tokenizer.ggml.padding_token_id u32 = 128040 llama_model_loader: - kv 32: tokenizer.chat_template str = {{bos_token}}{% for message in messag... llama_model_loader: - kv 33: 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 = 0.7994 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 = Hermes 3 Llama 3.1 8B llm_load_print_meta: BOS token = 128000 '<|begin_of_text|>' llm_load_print_meta: EOS token = 128040 '<|im_end|>' llm_load_print_meta: PAD token = 128040 '<|im_end|>' llm_load_print_meta: LF token = 128 'Ä' llm_load_print_meta: EOT token = 128040 '<|im_end|>' 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 42.013 ms compute_imatrix: computing over 125 chunks with batch_size 512 compute_imatrix: 0.75 seconds per pass - ETA 1.55 minutes [1]6.5294,[2]5.2572,[3]4.6884,[4]5.8580,[5]5.9745,[6]4.9979,[7]5.2920,[8]5.8251,[9]5.9930, save_imatrix: stored collected data after 10 chunks in Hermes-3-Llama-3.1-8B-IMat-GGUF/imatrix.dat [10]5.3755,[11]5.8342,[12]6.3525,[13]6.8022,[14]7.2438,[15]7.5480,[16]7.8856,[17]8.0749,[18]7.7882,[19]7.4444, save_imatrix: stored collected data after 20 chunks in Hermes-3-Llama-3.1-8B-IMat-GGUF/imatrix.dat [20]7.4155,[21]7.6047,[22]7.5125,[23]7.8480,[24]7.8675,[25]8.2301,[26]8.2276,[27]8.0914,[28]8.0742,[29]8.0705, save_imatrix: stored collected data after 30 chunks in Hermes-3-Llama-3.1-8B-IMat-GGUF/imatrix.dat [30]8.0540,[31]7.6576,[32]7.2706,[33]7.0903,[34]6.9371,[35]7.0092,[36]7.0515,[37]7.0219,[38]7.1002,[39]7.2472, save_imatrix: stored collected data after 40 chunks in Hermes-3-Llama-3.1-8B-IMat-GGUF/imatrix.dat [40]7.3291,[41]7.2846,[42]7.1899,[43]7.2619,[44]7.2908,[45]7.4095,[46]7.3172,[47]7.4408,[48]7.5346,[49]7.6345, save_imatrix: stored collected data after 50 chunks in Hermes-3-Llama-3.1-8B-IMat-GGUF/imatrix.dat [50]7.5249,[51]7.6517,[52]7.7858,[53]7.8870,[54]7.9717,[55]7.9944,[56]7.9542,[57]7.9644,[58]7.9124,[59]7.9322, save_imatrix: stored collected data after 60 chunks in Hermes-3-Llama-3.1-8B-IMat-GGUF/imatrix.dat [60]7.9002,[61]7.8969,[62]7.9549,[63]8.0105,[64]7.9395,[65]7.9150,[66]7.9417,[67]7.9349,[68]7.9387,[69]7.9429, save_imatrix: stored collected data after 70 chunks in Hermes-3-Llama-3.1-8B-IMat-GGUF/imatrix.dat [70]7.9583,[71]7.9599,[72]7.9700,[73]7.9487,[74]7.9034,[75]7.9109,[76]7.9282,[77]7.8986,[78]7.9046,[79]7.9482, save_imatrix: stored collected data after 80 chunks in Hermes-3-Llama-3.1-8B-IMat-GGUF/imatrix.dat [80]7.9852,[81]7.9814,[82]7.9836,[83]8.0226,[84]7.9148,[85]7.9197,[86]7.9340,[87]7.9525,[88]7.9872,[89]8.0079, save_imatrix: stored collected data after 90 chunks in Hermes-3-Llama-3.1-8B-IMat-GGUF/imatrix.dat [90]7.9379,[91]7.8548,[92]7.7770,[93]7.7098,[94]7.6401,[95]7.5784,[96]7.5469,[97]7.5560,[98]7.6133,[99]7.6978, save_imatrix: stored collected data after 100 chunks in Hermes-3-Llama-3.1-8B-IMat-GGUF/imatrix.dat [100]7.7826,[101]7.8411,[102]7.9709,[103]7.9998,[104]8.0367,[105]7.9608,[106]7.9741,[107]7.9274,[108]7.8736,[109]7.8201, save_imatrix: stored collected data after 110 chunks in Hermes-3-Llama-3.1-8B-IMat-GGUF/imatrix.dat [110]7.8671,[111]7.9228,[112]7.9391,[113]7.9329,[114]7.9656,[115]8.0049,[116]8.0187,[117]8.0360,[118]8.0694,[119]8.0208, save_imatrix: stored collected data after 120 chunks in Hermes-3-Llama-3.1-8B-IMat-GGUF/imatrix.dat [120]8.0207,[121]8.0026,[122]8.0207,[123]8.0415,[124]8.0669,[125]8.0627, save_imatrix: stored collected data after 125 chunks in Hermes-3-Llama-3.1-8B-IMat-GGUF/imatrix.dat llama_print_timings: load time = 3984.97 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 = 74660.71 ms / 64000 tokens ( 1.17 ms per token, 857.21 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 = 78713.95 ms / 64001 tokens Final estimate: PPL = 8.0627 +/- 0.12730