|
llama_model_loader: loaded meta data with 26 key-value pairs and 195 tensors from Phi-3-mini-4k-instruct-IMat-GGUF/Phi-3-mini-4k-instruct.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 = phi3 |
|
llama_model_loader: - kv 1: general.name str = Phi3 |
|
llama_model_loader: - kv 2: phi3.context_length u32 = 4096 |
|
llama_model_loader: - kv 3: phi3.rope.scaling.original_context_length u32 = 4096 |
|
llama_model_loader: - kv 4: phi3.embedding_length u32 = 3072 |
|
llama_model_loader: - kv 5: phi3.feed_forward_length u32 = 8192 |
|
llama_model_loader: - kv 6: phi3.block_count u32 = 32 |
|
llama_model_loader: - kv 7: phi3.attention.head_count u32 = 32 |
|
llama_model_loader: - kv 8: phi3.attention.head_count_kv u32 = 32 |
|
llama_model_loader: - kv 9: phi3.attention.layer_norm_rms_epsilon f32 = 0.000010 |
|
llama_model_loader: - kv 10: phi3.rope.dimension_count u32 = 96 |
|
llama_model_loader: - kv 11: phi3.rope.freq_base f32 = 10000.000000 |
|
llama_model_loader: - kv 12: general.file_type u32 = 7 |
|
llama_model_loader: - kv 13: tokenizer.ggml.model str = llama |
|
llama_model_loader: - kv 14: tokenizer.ggml.pre str = default |
|
llama_model_loader: - kv 15: tokenizer.ggml.tokens arr[str,32064] = ["<unk>", "<s>", "</s>", "<0x00>", "<... |
|
llama_model_loader: - kv 16: tokenizer.ggml.scores arr[f32,32064] = [-1000.000000, -1000.000000, -1000.00... |
|
llama_model_loader: - kv 17: tokenizer.ggml.token_type arr[i32,32064] = [3, 3, 4, 6, 6, 6, 6, 6, 6, 6, 6, 6, ... |
|
llama_model_loader: - kv 18: tokenizer.ggml.bos_token_id u32 = 1 |
|
llama_model_loader: - kv 19: tokenizer.ggml.eos_token_id u32 = 32000 |
|
llama_model_loader: - kv 20: tokenizer.ggml.unknown_token_id u32 = 0 |
|
llama_model_loader: - kv 21: tokenizer.ggml.padding_token_id u32 = 32000 |
|
llama_model_loader: - kv 22: tokenizer.ggml.add_bos_token bool = false |
|
llama_model_loader: - kv 23: tokenizer.ggml.add_eos_token bool = false |
|
llama_model_loader: - kv 24: tokenizer.chat_template str = {% for message in messages %}{% if me... |
|
llama_model_loader: - kv 25: general.quantization_version u32 = 2 |
|
llama_model_loader: - type f32: 65 tensors |
|
llama_model_loader: - type q8_0: 130 tensors |
|
llm_load_vocab: special tokens cache size = 323 |
|
llm_load_vocab: token to piece cache size = 0.1687 MB |
|
llm_load_print_meta: format = GGUF V3 (latest) |
|
llm_load_print_meta: arch = phi3 |
|
llm_load_print_meta: vocab type = SPM |
|
llm_load_print_meta: n_vocab = 32064 |
|
llm_load_print_meta: n_merges = 0 |
|
llm_load_print_meta: n_ctx_train = 4096 |
|
llm_load_print_meta: n_embd = 3072 |
|
llm_load_print_meta: n_head = 32 |
|
llm_load_print_meta: n_head_kv = 32 |
|
llm_load_print_meta: n_layer = 32 |
|
llm_load_print_meta: n_rot = 96 |
|
llm_load_print_meta: n_swa = 0 |
|
llm_load_print_meta: n_embd_head_k = 96 |
|
llm_load_print_meta: n_embd_head_v = 96 |
|
llm_load_print_meta: n_gqa = 1 |
|
llm_load_print_meta: n_embd_k_gqa = 3072 |
|
llm_load_print_meta: n_embd_v_gqa = 3072 |
|
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 = 8192 |
|
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 = 4096 |
|
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 = 3B |
|
llm_load_print_meta: model ftype = Q8_0 |
|
llm_load_print_meta: model params = 3.82 B |
|
llm_load_print_meta: model size = 3.78 GiB (8.50 BPW) |
|
llm_load_print_meta: general.name = Phi3 |
|
llm_load_print_meta: BOS token = 1 '<s>' |
|
llm_load_print_meta: EOS token = 32000 '<|endoftext|>' |
|
llm_load_print_meta: UNK token = 0 '<unk>' |
|
llm_load_print_meta: PAD token = 32000 '<|endoftext|>' |
|
llm_load_print_meta: LF token = 13 '<0x0A>' |
|
llm_load_print_meta: EOT token = 32007 '<|end|>' |
|
llm_load_print_meta: max token length = 48 |
|
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 = 0.20 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 = 99.81 MiB |
|
llm_load_tensors: CUDA0 buffer size = 3772.57 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 = 192.00 MiB |
|
llama_new_context_with_model: KV self size = 192.00 MiB, K (f16): 96.00 MiB, V (f16): 96.00 MiB |
|
llama_new_context_with_model: CUDA_Host output buffer size = 0.12 MiB |
|
llama_new_context_with_model: CUDA0 compute buffer size = 83.00 MiB |
|
llama_new_context_with_model: CUDA_Host compute buffer size = 7.01 MiB |
|
llama_new_context_with_model: graph nodes = 1286 |
|
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 97.069 ms |
|
compute_imatrix: computing over 151 chunks with batch_size 512 |
|
compute_imatrix: 0.36 seconds per pass - ETA 0.88 minutes |
|
[1]5.4343,[2]3.8996,[3]3.8149,[4]4.2813,[5]4.7551,[6]4.8896,[7]4.3971,[8]4.8784,[9]5.0628, |
|
save_imatrix: stored collected data after 10 chunks in Phi-3-mini-4k-instruct-IMat-GGUF/imatrix.dat |
|
[10]5.3943,[11]5.4217,[12]5.0285,[13]4.9134,[14]5.1438,[15]5.5571,[16]5.6656,[17]5.9607,[18]6.1181,[19]6.2656, |
|
save_imatrix: stored collected data after 20 chunks in Phi-3-mini-4k-instruct-IMat-GGUF/imatrix.dat |
|
[20]6.3909,[21]6.6078,[22]6.3513,[23]6.0687,[24]6.1444,[25]6.2039,[26]6.0961,[27]5.9920,[28]6.0692,[29]6.2414, |
|
save_imatrix: stored collected data after 30 chunks in Phi-3-mini-4k-instruct-IMat-GGUF/imatrix.dat |
|
[30]6.3627,[31]6.3409,[32]6.4753,[33]6.5867,[34]6.7751,[35]6.7987,[36]6.8239,[37]6.5432,[38]6.3571,[39]6.2625, |
|
save_imatrix: stored collected data after 40 chunks in Phi-3-mini-4k-instruct-IMat-GGUF/imatrix.dat |
|
[40]6.1535,[41]6.0799,[42]6.0834,[43]6.0280,[44]6.0363,[45]5.9998,[46]5.9587,[47]5.9597,[48]6.0238,[49]6.1117, |
|
save_imatrix: stored collected data after 50 chunks in Phi-3-mini-4k-instruct-IMat-GGUF/imatrix.dat |
|
[50]6.1246,[51]6.3047,[52]6.4659,[53]6.6468,[54]6.8254,[55]6.9231,[56]6.8431,[57]6.7428,[58]6.7578,[59]6.8111, |
|
save_imatrix: stored collected data after 60 chunks in Phi-3-mini-4k-instruct-IMat-GGUF/imatrix.dat |
|
[60]6.9017,[61]6.7848,[62]6.7904,[63]6.8443,[64]6.9221,[65]6.9817,[66]7.0156,[67]7.0694,[68]7.1127,[69]7.0954, |
|
save_imatrix: stored collected data after 70 chunks in Phi-3-mini-4k-instruct-IMat-GGUF/imatrix.dat |
|
[70]7.1040,[71]7.0925,[72]7.1185,[73]7.0637,[74]6.9930,[75]6.9701,[76]7.0329,[77]7.0270,[78]6.9920,[79]6.9800, |
|
save_imatrix: stored collected data after 80 chunks in Phi-3-mini-4k-instruct-IMat-GGUF/imatrix.dat |
|
[80]6.9818,[81]6.9469,[82]6.9240,[83]6.8928,[84]6.8914,[85]6.8941,[86]6.8804,[87]6.8794,[88]6.8692,[89]6.8521, |
|
save_imatrix: stored collected data after 90 chunks in Phi-3-mini-4k-instruct-IMat-GGUF/imatrix.dat |
|
[90]6.8342,[91]6.8410,[92]6.8011,[93]6.7910,[94]6.7614,[95]6.7156,[96]6.7232,[97]6.7062,[98]6.7103,[99]6.6828, |
|
save_imatrix: stored collected data after 100 chunks in Phi-3-mini-4k-instruct-IMat-GGUF/imatrix.dat |
|
[100]6.6730,[101]6.6802,[102]6.6431,[103]6.6045,[104]6.5952,[105]6.6153,[106]6.6126,[107]6.6340,[108]6.6482,[109]6.6071, |
|
save_imatrix: stored collected data after 110 chunks in Phi-3-mini-4k-instruct-IMat-GGUF/imatrix.dat |
|
[110]6.5626,[111]6.5220,[112]6.4816,[113]6.4386,[114]6.3930,[115]6.3538,[116]6.3223,[117]6.2917,[118]6.3010,[119]6.3069, |
|
save_imatrix: stored collected data after 120 chunks in Phi-3-mini-4k-instruct-IMat-GGUF/imatrix.dat |
|
[120]6.3563,[121]6.4052,[122]6.4605,[123]6.5090,[124]6.5836,[125]6.6534,[126]6.6648,[127]6.6721,[128]6.6135,[129]6.6104, |
|
save_imatrix: stored collected data after 130 chunks in Phi-3-mini-4k-instruct-IMat-GGUF/imatrix.dat |
|
[130]6.5800,[131]6.5530,[132]6.5075,[133]6.4591,[134]6.4719,[135]6.4909,[136]6.4868,[137]6.4848,[138]6.4945,[139]6.5073, |
|
save_imatrix: stored collected data after 140 chunks in Phi-3-mini-4k-instruct-IMat-GGUF/imatrix.dat |
|
[140]6.5218,[141]6.5243,[142]6.5266,[143]6.5127,[144]6.4885,[145]6.5051,[146]6.5372,[147]6.5788,[148]6.6177,[149]6.6584, |
|
save_imatrix: stored collected data after 150 chunks in Phi-3-mini-4k-instruct-IMat-GGUF/imatrix.dat |
|
[150]6.6965,[151]6.7404, |
|
save_imatrix: stored collected data after 151 chunks in Phi-3-mini-4k-instruct-IMat-GGUF/imatrix.dat |
|
|
|
llama_print_timings: load time = 1141.39 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 = 41002.68 ms / 77312 tokens ( 0.53 ms per token, 1885.54 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 = 42175.96 ms / 77313 tokens |
|
|
|
Final estimate: PPL = 6.7404 +/- 0.08396 |
|
|
