|
llama_model_loader: loaded meta data with 29 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: gemma2.attention.sliding_window u32 = 4096 |
|
llama_model_loader: - kv 15: tokenizer.ggml.model str = llama |
|
llama_model_loader: - kv 16: tokenizer.ggml.pre str = default |
|
llama_model_loader: - kv 17: tokenizer.ggml.tokens arr[str,256000] = ["<pad>", "<eos>", "<bos>", "<unk>", ... |
|
llama_model_loader: - kv 18: tokenizer.ggml.scores arr[f32,256000] = [0.000000, 0.000000, 0.000000, 0.0000... |
|
llama_model_loader: - kv 19: tokenizer.ggml.token_type arr[i32,256000] = [3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, ... |
|
llama_model_loader: - kv 20: tokenizer.ggml.bos_token_id u32 = 2 |
|
llama_model_loader: - kv 21: tokenizer.ggml.eos_token_id u32 = 1 |
|
llama_model_loader: - kv 22: tokenizer.ggml.unknown_token_id u32 = 3 |
|
llama_model_loader: - kv 23: tokenizer.ggml.padding_token_id u32 = 0 |
|
llama_model_loader: - kv 24: tokenizer.ggml.add_bos_token bool = true |
|
llama_model_loader: - kv 25: tokenizer.ggml.add_eos_token bool = false |
|
llama_model_loader: - kv 26: tokenizer.chat_template str = {{ bos_token }}{% if messages[0]['rol... |
|
llama_model_loader: - kv 27: tokenizer.ggml.add_space_prefix bool = false |
|
llama_model_loader: - kv 28: 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 = 364 |
|
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: vocab_only = 0 |
|
llm_load_print_meta: n_ctx_train = 8192 |
|
llm_load_print_meta: n_embd = 3584 |
|
llm_load_print_meta: n_layer = 42 |
|
llm_load_print_meta: n_head = 16 |
|
llm_load_print_meta: n_head_kv = 8 |
|
llm_load_print_meta: n_rot = 224 |
|
llm_load_print_meta: n_swa = 4096 |
|
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 = 9.01 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 119.102 ms |
|
compute_imatrix: computing over 128 chunks with batch_size 512 |
|
compute_imatrix: 0.85 seconds per pass - ETA 1.82 minutes |
|
[1]8.2870,[2]5.5692,[3]4.8574,[4]6.1032,[5]6.2583,[6]5.2453,[7]5.7902,[8]6.1617,[9]6.4089, |
|
save_imatrix: stored collected data after 10 chunks in Gemma-2-9B-It-SPPO-Iter3-IMat-GGUF/imatrix.dat |
|
[10]5.6400,[11]5.7908,[12]6.3911,[13]6.9578,[14]7.1997,[15]7.8125,[16]8.1619,[17]8.3215,[18]8.6900,[19]8.3100, |
|
save_imatrix: stored collected data after 20 chunks in Gemma-2-9B-It-SPPO-Iter3-IMat-GGUF/imatrix.dat |
|
[20]8.5375,[21]8.6913,[22]8.6501,[23]8.8311,[24]8.9421,[25]9.1331,[26]8.8236,[27]9.0735,[28]9.2551,[29]9.1570, |
|
save_imatrix: stored collected data after 30 chunks in Gemma-2-9B-It-SPPO-Iter3-IMat-GGUF/imatrix.dat |
|
[30]9.0664,[31]8.5109,[32]8.2338,[33]8.1731,[34]8.0490,[35]8.0060,[36]8.0236,[37]8.0200,[38]8.1009,[39]8.2803, |
|
save_imatrix: stored collected data after 40 chunks in Gemma-2-9B-It-SPPO-Iter3-IMat-GGUF/imatrix.dat |
|
[40]8.4557,[41]8.6042,[42]8.8991,[43]9.2142,[44]9.4949,[45]9.6524,[46]9.4993,[47]9.5265,[48]9.7377,[49]9.8946, |
|
save_imatrix: stored collected data after 50 chunks in Gemma-2-9B-It-SPPO-Iter3-IMat-GGUF/imatrix.dat |
|
[50]9.6778,[51]9.7231,[52]9.7711,[53]9.9173,[54]10.1400,[55]10.2482,[56]10.3176,[57]10.3220,[58]10.3506,[59]10.1951, |
|
save_imatrix: stored collected data after 60 chunks in Gemma-2-9B-It-SPPO-Iter3-IMat-GGUF/imatrix.dat |
|
[60]10.0656,[61]9.9265,[62]9.8784,[63]9.9241,[64]9.9184,[65]9.8962,[66]9.9283,[67]9.8701,[68]9.7891,[69]9.8077, |
|
save_imatrix: stored collected data after 70 chunks in Gemma-2-9B-It-SPPO-Iter3-IMat-GGUF/imatrix.dat |
|
[70]9.7677,[71]9.7514,[72]9.7605,[73]9.7345,[74]9.6684,[75]9.6283,[76]9.6233,[77]9.6320,[78]9.6199,[79]9.5661, |
|
save_imatrix: stored collected data after 80 chunks in Gemma-2-9B-It-SPPO-Iter3-IMat-GGUF/imatrix.dat |
|
[80]9.6315,[81]9.6843,[82]9.6604,[83]9.6603,[84]9.7184,[85]9.5761,[86]9.5323,[87]9.4649,[88]9.4783,[89]9.5114, |
|
save_imatrix: stored collected data after 90 chunks in Gemma-2-9B-It-SPPO-Iter3-IMat-GGUF/imatrix.dat |
|
[90]9.5357,[91]9.4612,[92]9.3816,[93]9.2879,[94]9.1958,[95]9.1295,[96]9.0453,[97]8.9720,[98]8.9035,[99]8.9543, |
|
save_imatrix: stored collected data after 100 chunks in Gemma-2-9B-It-SPPO-Iter3-IMat-GGUF/imatrix.dat |
|
[100]8.9876,[101]9.0807,[102]9.1655,[103]9.2443,[104]9.4136,[105]9.5366,[106]9.5596,[107]9.5914,[108]9.6093,[109]9.5883, |
|
save_imatrix: stored collected data after 110 chunks in Gemma-2-9B-It-SPPO-Iter3-IMat-GGUF/imatrix.dat |
|
[110]9.5676,[111]9.4936,[112]9.4150,[113]9.4655,[114]9.4851,[115]9.4909,[116]9.4830,[117]9.5297,[118]9.5509,[119]9.5557, |
|
save_imatrix: stored collected data after 120 chunks in Gemma-2-9B-It-SPPO-Iter3-IMat-GGUF/imatrix.dat |
|
[120]9.5669,[121]9.6127,[122]9.5730,[123]9.6293,[124]9.6857,[125]9.7251,[126]9.7980,[127]9.8556,[128]9.9097, |
|
save_imatrix: stored collected data after 128 chunks in Gemma-2-9B-It-SPPO-Iter3-IMat-GGUF/imatrix.dat |
|
|
|
llama_print_timings: load time = 14925.71 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 = 96055.84 ms / 65536 tokens ( 1.47 ms per token, 682.27 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 = 111564.87 ms / 65537 tokens |
|
|
|
Final estimate: PPL = 9.9097 +/- 0.16369 |
|
|
