|
llama_model_loader: loaded meta data with 25 key-value pairs and 464 tensors from gemma-2-9b-it-IMat-GGUF/gemma-2-9b-it.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 = gemma2 |
|
llama_model_loader: - kv 1: general.name str = gemma-2-9b-it |
|
llama_model_loader: - kv 2: gemma2.context_length u32 = 8192 |
|
llama_model_loader: - kv 3: gemma2.embedding_length u32 = 3584 |
|
llama_model_loader: - kv 4: gemma2.block_count u32 = 42 |
|
llama_model_loader: - kv 5: gemma2.feed_forward_length u32 = 14336 |
|
llama_model_loader: - kv 6: gemma2.attention.head_count u32 = 16 |
|
llama_model_loader: - kv 7: gemma2.attention.head_count_kv u32 = 8 |
|
llama_model_loader: - kv 8: gemma2.attention.layer_norm_rms_epsilon f32 = 0.000001 |
|
llama_model_loader: - kv 9: gemma2.attention.key_length u32 = 256 |
|
llama_model_loader: - kv 10: gemma2.attention.value_length u32 = 256 |
|
llama_model_loader: - kv 11: general.file_type u32 = 7 |
|
llama_model_loader: - kv 12: tokenizer.ggml.model str = llama |
|
llama_model_loader: - kv 13: tokenizer.ggml.pre str = default |
|
llama_model_loader: - kv 14: tokenizer.ggml.tokens arr[str,256000] = ["<pad>", "<eos>", "<bos>", "<unk>", ... |
|
llama_model_loader: - kv 15: tokenizer.ggml.scores arr[f32,256000] = [0.000000, 0.000000, 0.000000, 0.0000... |
|
llama_model_loader: - kv 16: tokenizer.ggml.token_type arr[i32,256000] = [3, 3, 3, 2, 1, 1, 1, 1, 1, 1, 1, 1, ... |
|
llama_model_loader: - kv 17: tokenizer.ggml.bos_token_id u32 = 2 |
|
llama_model_loader: - kv 18: tokenizer.ggml.eos_token_id u32 = 1 |
|
llama_model_loader: - kv 19: tokenizer.ggml.unknown_token_id u32 = 3 |
|
llama_model_loader: - kv 20: tokenizer.ggml.padding_token_id u32 = 0 |
|
llama_model_loader: - kv 21: tokenizer.ggml.add_bos_token bool = true |
|
llama_model_loader: - kv 22: tokenizer.ggml.add_eos_token bool = false |
|
llama_model_loader: - kv 23: tokenizer.chat_template str = {{ bos_token }}{% if messages[0]['rol... |
|
llama_model_loader: - kv 24: general.quantization_version u32 = 2 |
|
llama_model_loader: - type f32: 169 tensors |
|
llama_model_loader: - type q8_0: 295 tensors |
|
llm_load_vocab: special tokens cache size = 260 |
|
llm_load_vocab: token to piece cache size = 1.6014 MB |
|
llm_load_print_meta: format = GGUF V3 (latest) |
|
llm_load_print_meta: arch = gemma2 |
|
llm_load_print_meta: vocab type = SPM |
|
llm_load_print_meta: n_vocab = 256000 |
|
llm_load_print_meta: n_merges = 0 |
|
llm_load_print_meta: n_ctx_train = 8192 |
|
llm_load_print_meta: n_embd = 3584 |
|
llm_load_print_meta: n_head = 16 |
|
llm_load_print_meta: n_head_kv = 8 |
|
llm_load_print_meta: n_layer = 42 |
|
llm_load_print_meta: n_rot = 224 |
|
llm_load_print_meta: n_embd_head_k = 256 |
|
llm_load_print_meta: n_embd_head_v = 256 |
|
llm_load_print_meta: n_gqa = 2 |
|
llm_load_print_meta: n_embd_k_gqa = 2048 |
|
llm_load_print_meta: n_embd_v_gqa = 2048 |
|
llm_load_print_meta: f_norm_eps = 0.0e+00 |
|
llm_load_print_meta: f_norm_rms_eps = 1.0e-06 |
|
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 = 2 |
|
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 = 8192 |
|
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 = ?B |
|
llm_load_print_meta: model ftype = Q8_0 |
|
llm_load_print_meta: model params = 9.24 B |
|
llm_load_print_meta: model size = 9.15 GiB (8.50 BPW) |
|
llm_load_print_meta: general.name = gemma-2-9b-it |
|
llm_load_print_meta: BOS token = 2 '<bos>' |
|
llm_load_print_meta: EOS token = 1 '<eos>' |
|
llm_load_print_meta: UNK token = 3 '<unk>' |
|
llm_load_print_meta: PAD token = 0 '<pad>' |
|
llm_load_print_meta: LF token = 227 '<0x0A>' |
|
llm_load_print_meta: EOT token = 107 '<end_of_turn>' |
|
llm_load_print_meta: max token length = 93 |
|
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 = 0.41 MiB |
|
llm_load_tensors: offloading 42 repeating layers to GPU |
|
llm_load_tensors: offloading non-repeating layers to GPU |
|
llm_load_tensors: offloaded 43/43 layers to GPU |
|
llm_load_tensors: CPU buffer size = 929.69 MiB |
|
llm_load_tensors: CUDA0 buffer size = 9366.12 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 = 168.00 MiB |
|
llama_new_context_with_model: KV self size = 168.00 MiB, K (f16): 84.00 MiB, V (f16): 84.00 MiB |
|
llama_new_context_with_model: CUDA_Host output buffer size = 0.98 MiB |
|
llama_new_context_with_model: CUDA0 compute buffer size = 507.00 MiB |
|
llama_new_context_with_model: CUDA_Host compute buffer size = 8.01 MiB |
|
llama_new_context_with_model: graph nodes = 1561 |
|
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 124.683 ms |
|
compute_imatrix: computing over 128 chunks with batch_size 512 |
|
compute_imatrix: 0.83 seconds per pass - ETA 1.75 minutes |
|
[1]11.6771,[2]7.4833,[3]6.4754,[4]8.4522,[5]8.6895,[6]7.0038,[7]7.8546,[8]8.4646,[9]8.8183, |
|
save_imatrix: stored collected data after 10 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat |
|
[10]7.6272,[11]7.8174,[12]8.7305,[13]9.5990,[14]9.9023,[15]10.8211,[16]11.2734,[17]11.4621,[18]12.0211,[19]11.4085, |
|
save_imatrix: stored collected data after 20 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat |
|
[20]11.7441,[21]12.0377,[22]12.0034,[23]12.2039,[24]12.3667,[25]12.6682,[26]12.2060,[27]12.5602,[28]12.8297,[29]12.6891, |
|
save_imatrix: stored collected data after 30 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat |
|
[30]12.5921,[31]11.7099,[32]11.3067,[33]11.1819,[34]10.9639,[35]10.8633,[36]10.8581,[37]10.8758,[38]11.0319,[39]11.3075, |
|
save_imatrix: stored collected data after 40 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat |
|
[40]11.5737,[41]11.7938,[42]12.2299,[43]12.6891,[44]13.0918,[45]13.3168,[46]13.0891,[47]13.1461,[48]13.4924,[49]13.7363, |
|
save_imatrix: stored collected data after 50 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat |
|
[50]13.3847,[51]13.4436,[52]13.5379,[53]13.7711,[54]14.1253,[55]14.3239,[56]14.4230,[57]14.4063,[58]14.4329,[59]14.1763, |
|
save_imatrix: stored collected data after 60 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat |
|
[60]13.9614,[61]13.7580,[62]13.6845,[63]13.7762,[64]13.7836,[65]13.7635,[66]13.8324,[67]13.7439,[68]13.6359,[69]13.6722, |
|
save_imatrix: stored collected data after 70 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat |
|
[70]13.6115,[71]13.5899,[72]13.6093,[73]13.5783,[74]13.4840,[75]13.4323,[76]13.4368,[77]13.4732,[78]13.4611,[79]13.3709, |
|
save_imatrix: stored collected data after 80 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat |
|
[80]13.4802,[81]13.5753,[82]13.5417,[83]13.5532,[84]13.6483,[85]13.4302,[86]13.3705,[87]13.2581,[88]13.2679,[89]13.3038, |
|
save_imatrix: stored collected data after 90 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat |
|
[90]13.3596,[91]13.2432,[92]13.1122,[93]12.9672,[94]12.8206,[95]12.7243,[96]12.5957,[97]12.4788,[98]12.3693,[99]12.4411, |
|
save_imatrix: stored collected data after 100 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat |
|
[100]12.4826,[101]12.6258,[102]12.7398,[103]12.8584,[104]13.1219,[105]13.3135,[106]13.3536,[107]13.4055,[108]13.4438,[109]13.3964, |
|
save_imatrix: stored collected data after 110 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat |
|
[110]13.3558,[111]13.2382,[112]13.1135,[113]13.1991,[114]13.2304,[115]13.2366,[116]13.2327,[117]13.3196,[118]13.3490,[119]13.3551, |
|
save_imatrix: stored collected data after 120 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat |
|
[120]13.3762,[121]13.4465,[122]13.3793,[123]13.4577,[124]13.5307,[125]13.5815,[126]13.6899,[127]13.7724,[128]13.8487, |
|
save_imatrix: stored collected data after 128 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat |
|
|
|
llama_print_timings: load time = 2452.80 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 = 91799.71 ms / 65536 tokens ( 1.40 ms per token, 713.90 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 = 94944.80 ms / 65537 tokens |
|
|
|
Final estimate: PPL = 13.8487 +/- 0.28454 |
|
|
