|
llama_model_loader: loaded meta data with 31 key-value pairs and 292 tensors from Meta-Llama-3.1-8B-Instruct-abliterated-IMat-GGUF/Meta-Llama-3.1-8B-Instruct-abliterated.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 = Meta Llama 3.1 8B Instruct Abliterated |
|
llama_model_loader: - kv 3: general.finetune str = Instruct-abliterated |
|
llama_model_loader: - kv 4: general.basename str = Meta-Llama-3.1 |
|
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.base_model.count u32 = 1 |
|
llama_model_loader: - kv 8: general.base_model.0.name str = Meta Llama 3.1 8B Instruct |
|
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,2] = ["abliterated", "uncensored"] |
|
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.attention.layer_norm_rms_epsilon f32 = 0.000010 |
|
llama_model_loader: - kv 19: general.file_type u32 = 7 |
|
llama_model_loader: - kv 20: llama.vocab_size u32 = 128256 |
|
llama_model_loader: - kv 21: llama.rope.dimension_count u32 = 128 |
|
llama_model_loader: - kv 22: tokenizer.ggml.model str = gpt2 |
|
llama_model_loader: - kv 23: tokenizer.ggml.pre str = llama-bpe |
|
llama_model_loader: - kv 24: tokenizer.ggml.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ... |
|
llama_model_loader: - kv 25: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... |
|
llama_model_loader: - kv 26: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "... |
|
llama_model_loader: - kv 27: tokenizer.ggml.bos_token_id u32 = 128000 |
|
llama_model_loader: - kv 28: tokenizer.ggml.eos_token_id u32 = 128009 |
|
llama_model_loader: - kv 29: tokenizer.chat_template str = {% set loop_messages = messages %}{% ... |
|
llama_model_loader: - kv 30: 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 = 10000.0 |
|
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 = Meta Llama 3.1 8B Instruct Abliterated |
|
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 = 10000.0 |
|
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 39.509 ms |
|
compute_imatrix: computing over 125 chunks with batch_size 512 |
|
compute_imatrix: 0.68 seconds per pass - ETA 1.40 minutes |
|
[1]7.0879,[2]5.6746,[3]5.1642,[4]6.3097,[5]6.6435,[6]5.4778,[7]5.9064,[8]6.5247,[9]6.7963, |
|
save_imatrix: stored collected data after 10 chunks in Meta-Llama-3.1-8B-Instruct-abliterated-IMat-GGUF/imatrix.dat |
|
[10]6.1381,[11]6.6961,[12]7.3893,[13]7.8834,[14]8.3969,[15]8.7444,[16]9.0568,[17]9.2784,[18]8.8756,[19]8.3935, |
|
save_imatrix: stored collected data after 20 chunks in Meta-Llama-3.1-8B-Instruct-abliterated-IMat-GGUF/imatrix.dat |
|
[20]8.3887,[21]8.5765,[22]8.5103,[23]8.8419,[24]8.7664,[25]9.1740,[26]9.1658,[27]9.3214,[28]9.6092,[29]9.6259, |
|
save_imatrix: stored collected data after 30 chunks in Meta-Llama-3.1-8B-Instruct-abliterated-IMat-GGUF/imatrix.dat |
|
[30]9.6208,[31]9.0791,[32]8.5899,[33]8.3527,[34]8.1595,[35]8.2341,[36]8.3076,[37]8.2326,[38]8.3380,[39]8.5501, |
|
save_imatrix: stored collected data after 40 chunks in Meta-Llama-3.1-8B-Instruct-abliterated-IMat-GGUF/imatrix.dat |
|
[40]8.6737,[41]8.8574,[42]9.0736,[43]9.3619,[44]9.5417,[45]9.7630,[46]9.5971,[47]9.7666,[48]9.8564,[49]9.9567, |
|
save_imatrix: stored collected data after 50 chunks in Meta-Llama-3.1-8B-Instruct-abliterated-IMat-GGUF/imatrix.dat |
|
[50]9.8372,[51]9.9395,[52]10.0823,[53]10.1798,[54]10.2499,[55]10.3437,[56]10.3959,[57]10.4569,[58]10.4559,[59]10.4698, |
|
save_imatrix: stored collected data after 60 chunks in Meta-Llama-3.1-8B-Instruct-abliterated-IMat-GGUF/imatrix.dat |
|
[60]10.4089,[61]10.3711,[62]10.4057,[63]10.4433,[64]10.3233,[65]10.2776,[66]10.2865,[67]10.2494,[68]10.2191,[69]10.1952, |
|
save_imatrix: stored collected data after 70 chunks in Meta-Llama-3.1-8B-Instruct-abliterated-IMat-GGUF/imatrix.dat |
|
[70]10.1794,[71]10.1597,[72]10.1452,[73]10.1104,[74]10.0241,[75]10.0245,[76]10.0268,[77]9.9790,[78]9.9726,[79]10.0272, |
|
save_imatrix: stored collected data after 80 chunks in Meta-Llama-3.1-8B-Instruct-abliterated-IMat-GGUF/imatrix.dat |
|
[80]10.0628,[81]10.0478,[82]10.0432,[83]10.0969,[84]9.9513,[85]9.9352,[86]9.9365,[87]9.9505,[88]9.9717,[89]9.9539, |
|
save_imatrix: stored collected data after 90 chunks in Meta-Llama-3.1-8B-Instruct-abliterated-IMat-GGUF/imatrix.dat |
|
[90]9.8700,[91]9.7703,[92]9.6800,[93]9.5952,[94]9.5091,[95]9.4239,[96]9.3628,[97]9.3764,[98]9.4357,[99]9.5426, |
|
save_imatrix: stored collected data after 100 chunks in Meta-Llama-3.1-8B-Instruct-abliterated-IMat-GGUF/imatrix.dat |
|
[100]9.6401,[101]9.6957,[102]9.8550,[103]9.8822,[104]9.9342,[105]9.8331,[106]9.8347,[107]9.7782,[108]9.6888,[109]9.5983, |
|
save_imatrix: stored collected data after 110 chunks in Meta-Llama-3.1-8B-Instruct-abliterated-IMat-GGUF/imatrix.dat |
|
[110]9.6488,[111]9.7143,[112]9.7335,[113]9.7393,[114]9.7898,[115]9.8457,[116]9.8633,[117]9.9023,[118]9.9265,[119]9.8498, |
|
save_imatrix: stored collected data after 120 chunks in Meta-Llama-3.1-8B-Instruct-abliterated-IMat-GGUF/imatrix.dat |
|
[120]9.8838,[121]9.9413,[122]9.9906,[123]10.0559,[124]10.1170,[125]10.1703, |
|
save_imatrix: stored collected data after 125 chunks in Meta-Llama-3.1-8B-Instruct-abliterated-IMat-GGUF/imatrix.dat |
|
|
|
llama_print_timings: load time = 2092.86 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 = 69696.00 ms / 64000 tokens ( 1.09 ms per token, 918.27 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 = 71971.70 ms / 64001 tokens |
|
|
|
Final estimate: PPL = 10.1703 +/- 0.16718 |
|
|
