|
llama_model_loader: loaded meta data with 28 key-value pairs and 464 tensors from Gemma-2-9B-It-SPPO-Iter3-IMat-GGUF/Gemma-2-9B-It-SPPO-Iter3.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-SPPO-Iter3 |
|
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: gemma2.attn_logit_softcapping f32 = 50.000000 |
|
llama_model_loader: - kv 13: gemma2.final_logit_softcapping f32 = 30.000000 |
|
llama_model_loader: - kv 14: tokenizer.ggml.model str = llama |
|
llama_model_loader: - kv 15: tokenizer.ggml.pre str = default |
|
llama_model_loader: - kv 16: tokenizer.ggml.tokens arr[str,256000] = ["<pad>", "<eos>", "<bos>", "<unk>", ... |
|
llama_model_loader: - kv 17: tokenizer.ggml.scores arr[f32,256000] = [-1000.000000, -1000.000000, -1000.00... |
|
llama_model_loader: - kv 18: tokenizer.ggml.token_type arr[i32,256000] = [3, 3, 3, 3, 1, 1, 1, 1, 1, 1, 1, 1, ... |
|
llama_model_loader: - kv 19: tokenizer.ggml.bos_token_id u32 = 2 |
|
llama_model_loader: - kv 20: tokenizer.ggml.eos_token_id u32 = 1 |
|
llama_model_loader: - kv 21: tokenizer.ggml.unknown_token_id u32 = 3 |
|
llama_model_loader: - kv 22: tokenizer.ggml.padding_token_id u32 = 0 |
|
llama_model_loader: - kv 23: tokenizer.ggml.add_bos_token bool = true |
|
llama_model_loader: - kv 24: tokenizer.ggml.add_eos_token bool = false |
|
llama_model_loader: - kv 25: tokenizer.chat_template str = {{ bos_token }}{% if messages[0]['rol... |
|
llama_model_loader: - kv 26: tokenizer.ggml.add_space_prefix bool = false |
|
llama_model_loader: - kv 27: 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 = 261 |
|
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 = 9B |
|
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-SPPO-Iter3 |
|
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 = 1690 |
|
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 93.278 ms |
|
compute_imatrix: computing over 128 chunks with batch_size 512 |
|
compute_imatrix: 0.84 seconds per pass - ETA 1.78 minutes |
|
[1]16.6552,[2]8.0903,[3]6.9962,[4]8.3971,[5]9.2464,[6]9.7300,[7]10.7022,[8]11.6187,[9]11.9992, |
|
save_imatrix: stored collected data after 10 chunks in Gemma-2-9B-It-SPPO-Iter3-IMat-GGUF/imatrix.dat |
|
[10]10.4973,[11]10.2809,[12]11.3377,[13]11.9631,[14]12.0849,[15]12.9207,[16]13.0206,[17]13.0855,[18]13.5418,[19]13.4242, |
|
save_imatrix: stored collected data after 20 chunks in Gemma-2-9B-It-SPPO-Iter3-IMat-GGUF/imatrix.dat |
|
[20]13.7130,[21]14.8192,[22]14.8997,[23]14.7292,[24]14.9818,[25]14.8718,[26]14.5962,[27]14.8364,[28]15.0628,[29]15.0534, |
|
save_imatrix: stored collected data after 30 chunks in Gemma-2-9B-It-SPPO-Iter3-IMat-GGUF/imatrix.dat |
|
[30]15.2443,[31]14.0970,[32]13.4552,[33]13.0165,[34]12.6321,[35]12.3731,[36]12.5212,[37]12.8425,[38]13.0140,[39]13.1960, |
|
save_imatrix: stored collected data after 40 chunks in Gemma-2-9B-It-SPPO-Iter3-IMat-GGUF/imatrix.dat |
|
[40]13.3016,[41]13.3337,[42]13.9154,[43]14.2830,[44]14.6994,[45]14.9396,[46]14.6625,[47]14.4206,[48]14.6417,[49]14.8669, |
|
save_imatrix: stored collected data after 50 chunks in Gemma-2-9B-It-SPPO-Iter3-IMat-GGUF/imatrix.dat |
|
[50]14.6774,[51]14.5402,[52]14.6070,[53]14.8337,[54]15.1521,[55]15.4017,[56]15.5381,[57]15.5412,[58]15.5433,[59]15.3203, |
|
save_imatrix: stored collected data after 60 chunks in Gemma-2-9B-It-SPPO-Iter3-IMat-GGUF/imatrix.dat |
|
[60]15.1412,[61]14.9436,[62]14.7716,[63]14.8956,[64]15.0538,[65]14.9025,[66]14.9251,[67]14.8897,[68]14.8316,[69]14.7527, |
|
save_imatrix: stored collected data after 70 chunks in Gemma-2-9B-It-SPPO-Iter3-IMat-GGUF/imatrix.dat |
|
[70]14.6922,[71]14.6700,[72]14.6271,[73]14.6927,[74]14.6179,[75]14.4837,[76]14.4578,[77]14.4619,[78]14.4124,[79]14.3156, |
|
save_imatrix: stored collected data after 80 chunks in Gemma-2-9B-It-SPPO-Iter3-IMat-GGUF/imatrix.dat |
|
[80]14.3808,[81]14.4619,[82]14.4841,[83]14.5843,[84]14.6263,[85]14.3919,[86]14.3208,[87]14.1543,[88]14.1997,[89]14.1722, |
|
save_imatrix: stored collected data after 90 chunks in Gemma-2-9B-It-SPPO-Iter3-IMat-GGUF/imatrix.dat |
|
[90]14.2455,[91]14.1862,[92]14.0935,[93]14.0125,[94]13.8942,[95]13.8216,[96]13.7275,[97]13.6539,[98]13.5585,[99]13.6079, |
|
save_imatrix: stored collected data after 100 chunks in Gemma-2-9B-It-SPPO-Iter3-IMat-GGUF/imatrix.dat |
|
[100]13.6242,[101]13.7690,[102]13.8623,[103]13.9214,[104]14.1043,[105]14.2414,[106]14.2558,[107]14.2652,[108]14.1996,[109]14.2351, |
|
save_imatrix: stored collected data after 110 chunks in Gemma-2-9B-It-SPPO-Iter3-IMat-GGUF/imatrix.dat |
|
[110]14.1081,[111]13.9695,[112]13.7990,[113]13.8842,[114]13.9366,[115]13.9254,[116]13.8930,[117]13.9520,[118]13.9874,[119]14.0052, |
|
save_imatrix: stored collected data after 120 chunks in Gemma-2-9B-It-SPPO-Iter3-IMat-GGUF/imatrix.dat |
|
[120]13.9951,[121]14.0036,[122]13.9634,[123]13.9903,[124]14.0884,[125]14.1808,[126]14.2925,[127]14.3374,[128]14.3945, |
|
save_imatrix: stored collected data after 128 chunks in Gemma-2-9B-It-SPPO-Iter3-IMat-GGUF/imatrix.dat |
|
|
|
llama_print_timings: load time = 6383.63 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 = 91484.26 ms / 65536 tokens ( 1.40 ms per token, 716.36 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 = 98451.28 ms / 65537 tokens |
|
|
|
Final estimate: PPL = 14.3945 +/- 0.28244 |
|
|
