legraphista's picture
Upload imatrix.log with huggingface_hub
d1a772a verified
raw
history blame
13.3 kB
warning: not compiled with GPU offload support, --n-gpu-layers option will be ignored
warning: see main README.md for information on enabling GPU BLAS support
main: build = 3004 (bb9c3618)
main: built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
main: seed = 1716723554
llama_model_loader: loaded meta data with 38 key-value pairs and 377 tensors from DeepSeek-V2-Lite-Chat-IMat-GGUF/DeepSeek-V2-Lite-Chat.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 = deepseek2
llama_model_loader: - kv 1: general.name str = DeepSeek-V2-Lite-Chat
llama_model_loader: - kv 2: deepseek2.block_count u32 = 27
llama_model_loader: - kv 3: deepseek2.context_length u32 = 163840
llama_model_loader: - kv 4: deepseek2.embedding_length u32 = 2048
llama_model_loader: - kv 5: deepseek2.feed_forward_length u32 = 10944
llama_model_loader: - kv 6: deepseek2.attention.head_count u32 = 16
llama_model_loader: - kv 7: deepseek2.attention.head_count_kv u32 = 16
llama_model_loader: - kv 8: deepseek2.rope.freq_base f32 = 10000.000000
llama_model_loader: - kv 9: deepseek2.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 10: deepseek2.expert_used_count u32 = 6
llama_model_loader: - kv 11: general.file_type u32 = 0
llama_model_loader: - kv 12: deepseek2.leading_dense_block_count u32 = 1
llama_model_loader: - kv 13: deepseek2.vocab_size u32 = 102400
llama_model_loader: - kv 14: deepseek2.attention.kv_lora_rank u32 = 512
llama_model_loader: - kv 15: deepseek2.attention.key_length u32 = 192
llama_model_loader: - kv 16: deepseek2.attention.value_length u32 = 128
llama_model_loader: - kv 17: deepseek2.expert_feed_forward_length u32 = 1408
llama_model_loader: - kv 18: deepseek2.expert_count u32 = 64
llama_model_loader: - kv 19: deepseek2.expert_shared_count u32 = 2
llama_model_loader: - kv 20: deepseek2.expert_weights_scale f32 = 1.000000
llama_model_loader: - kv 21: deepseek2.rope.dimension_count u32 = 64
llama_model_loader: - kv 22: deepseek2.rope.scaling.type str = yarn
llama_model_loader: - kv 23: deepseek2.rope.scaling.factor f32 = 40.000000
llama_model_loader: - kv 24: deepseek2.rope.scaling.original_context_length u32 = 4096
llama_model_loader: - kv 25: deepseek2.rope.scaling.yarn_log_multiplier f32 = 0.070700
llama_model_loader: - kv 26: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 27: tokenizer.ggml.pre str = deepseek-llm
llama_model_loader: - kv 28: tokenizer.ggml.tokens arr[str,102400] = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 29: tokenizer.ggml.token_type arr[i32,102400] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 30: tokenizer.ggml.merges arr[str,99757] = ["Ġ Ġ", "Ġ t", "Ġ a", "i n", "h e...
llama_model_loader: - kv 31: tokenizer.ggml.bos_token_id u32 = 100000
llama_model_loader: - kv 32: tokenizer.ggml.eos_token_id u32 = 100001
llama_model_loader: - kv 33: tokenizer.ggml.padding_token_id u32 = 100001
llama_model_loader: - kv 34: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 35: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 36: tokenizer.chat_template str = {% if not add_generation_prompt is de...
llama_model_loader: - kv 37: general.quantization_version u32 = 2
llama_model_loader: - type f32: 377 tensors
llm_load_vocab: special tokens definition check successful ( 2400/102400 ).
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = deepseek2
llm_load_print_meta: vocab type = BPE
llm_load_print_meta: n_vocab = 102400
llm_load_print_meta: n_merges = 99757
llm_load_print_meta: n_ctx_train = 163840
llm_load_print_meta: n_embd = 2048
llm_load_print_meta: n_head = 16
llm_load_print_meta: n_head_kv = 16
llm_load_print_meta: n_layer = 27
llm_load_print_meta: n_rot = 64
llm_load_print_meta: n_embd_head_k = 192
llm_load_print_meta: n_embd_head_v = 128
llm_load_print_meta: n_gqa = 1
llm_load_print_meta: n_embd_k_gqa = 3072
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 = 10944
llm_load_print_meta: n_expert = 64
llm_load_print_meta: n_expert_used = 6
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 = yarn
llm_load_print_meta: freq_base_train = 10000.0
llm_load_print_meta: freq_scale_train = 0.025
llm_load_print_meta: n_yarn_orig_ctx = 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 = 16B
llm_load_print_meta: model ftype = all F32
llm_load_print_meta: model params = 15.71 B
llm_load_print_meta: model size = 58.51 GiB (32.00 BPW)
llm_load_print_meta: general.name = DeepSeek-V2-Lite-Chat
llm_load_print_meta: BOS token = 100000 '<|begin▁of▁sentence|>'
llm_load_print_meta: EOS token = 100001 '<|end▁of▁sentence|>'
llm_load_print_meta: PAD token = 100001 '<|end▁of▁sentence|>'
llm_load_print_meta: LF token = 126 'Ä'
llm_load_tensors: ggml ctx size = 0.18 MiB
llm_load_tensors: CPU buffer size = 59915.48 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 = 0.025
llama_kv_cache_init: CPU KV buffer size = 135.00 MiB
llama_new_context_with_model: KV self size = 135.00 MiB, K (f16): 81.00 MiB, V (f16): 54.00 MiB
llama_new_context_with_model: CPU output buffer size = 0.39 MiB
llama_new_context_with_model: CPU compute buffer size = 367.76 MiB
llama_new_context_with_model: graph nodes = 1924
llama_new_context_with_model: graph splits = 1
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 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 |
compute_imatrix: tokenizing the input ..
compute_imatrix: tokenization took 290.224 ms
compute_imatrix: computing over 214 chunks with batch_size 512
compute_imatrix: 3.74 seconds per pass - ETA 13.33 minutes
[1]8.2768,[2]5.4737,[3]5.4391,[4]6.2128,[5]5.9929,[6]5.7320,[7]6.1111,[8]6.2020,[9]6.9063,
save_imatrix: stored collected data after 10 chunks in DeepSeek-V2-Lite-Chat-IMat-GGUF/imatrix.dat
[10]7.1247,[11]7.2969,[12]7.6469,[13]7.1879,[14]7.5155,[15]7.6139,[16]7.9793,[17]8.1919,[18]8.4695,[19]8.5381,
save_imatrix: stored collected data after 20 chunks in DeepSeek-V2-Lite-Chat-IMat-GGUF/imatrix.dat
[20]8.9097,[21]8.5797,[22]8.6558,[23]8.0642,[24]7.6486,[25]7.3866,[26]7.1277,[27]7.4222,[28]7.3693,[29]7.5654,
save_imatrix: stored collected data after 30 chunks in DeepSeek-V2-Lite-Chat-IMat-GGUF/imatrix.dat
[30]7.4697,[31]7.5927,[32]7.2141,[33]7.0326,[34]6.9585,[35]6.9555,[36]6.9146,[37]6.8700,[38]6.9146,[39]7.0737,
save_imatrix: stored collected data after 40 chunks in DeepSeek-V2-Lite-Chat-IMat-GGUF/imatrix.dat
[40]7.1851,[41]7.3125,[42]7.3394,[43]7.5495,[44]7.7104,[45]7.8862,[46]7.9809,[47]8.0805,[48]8.0834,[49]8.1130,
save_imatrix: stored collected data after 50 chunks in DeepSeek-V2-Lite-Chat-IMat-GGUF/imatrix.dat
[50]7.9198,[51]8.0131,[52]8.0931,[53]8.1593,[54]8.2404,[55]8.2924,[56]8.3474,[57]8.4669,[58]8.4857,[59]8.4941,
save_imatrix: stored collected data after 60 chunks in DeepSeek-V2-Lite-Chat-IMat-GGUF/imatrix.dat
[60]8.5300,[61]8.5434,[62]8.6402,[63]8.6901,[64]8.7586,[65]8.8041,[66]8.7296,[67]8.6748,[68]8.6409,[69]8.6341,
save_imatrix: stored collected data after 70 chunks in DeepSeek-V2-Lite-Chat-IMat-GGUF/imatrix.dat
[70]8.6099,[71]8.5414,[72]8.4441,[73]8.4169,[74]8.3939,[75]8.3706,[76]8.4325,[77]8.4689,[78]8.4645,[79]8.3915,
save_imatrix: stored collected data after 80 chunks in DeepSeek-V2-Lite-Chat-IMat-GGUF/imatrix.dat
[80]8.3912,[81]8.2811,[82]8.2327,[83]8.1841,[84]8.1584,[85]8.1328,[86]8.1233,[87]8.1040,[88]8.0841,[89]8.0420,
save_imatrix: stored collected data after 90 chunks in DeepSeek-V2-Lite-Chat-IMat-GGUF/imatrix.dat
[90]8.0628,[91]8.0975,[92]8.1182,[93]8.1254,[94]8.0728,[95]8.0515,[96]8.0575,[97]8.0787,[98]8.0673,[99]8.0877,
save_imatrix: stored collected data after 100 chunks in DeepSeek-V2-Lite-Chat-IMat-GGUF/imatrix.dat
[100]8.1236,[101]8.0989,[102]8.1019,[103]8.1148,[104]8.1103,[105]8.0952,[106]8.0690,[107]8.0914,[108]8.0672,[109]8.0498,
save_imatrix: stored collected data after 110 chunks in DeepSeek-V2-Lite-Chat-IMat-GGUF/imatrix.dat
[110]8.0253,[111]8.0585,[112]8.0983,[113]8.0915,[114]8.0882,[115]8.0723,[116]8.1090,[117]8.0438,[118]8.0238,[119]7.9827,
save_imatrix: stored collected data after 120 chunks in DeepSeek-V2-Lite-Chat-IMat-GGUF/imatrix.dat
[120]7.9136,[121]7.9178,[122]7.8371,[123]7.7582,[124]7.6814,[125]7.6017,[126]7.5301,[127]7.4569,[128]7.3836,[129]7.3148,
save_imatrix: stored collected data after 130 chunks in DeepSeek-V2-Lite-Chat-IMat-GGUF/imatrix.dat
[130]7.3209,[131]7.3164,[132]7.2912,[133]7.2601,[134]7.2430,[135]7.2101,[136]7.1949,[137]7.1702,[138]7.1602,[139]7.1316,
save_imatrix: stored collected data after 140 chunks in DeepSeek-V2-Lite-Chat-IMat-GGUF/imatrix.dat
[140]7.1220,[141]7.0939,[142]7.0929,[143]7.0717,[144]7.0836,[145]7.1291,[146]7.2135,[147]7.2831,[148]7.3252,[149]7.3546,
save_imatrix: stored collected data after 150 chunks in DeepSeek-V2-Lite-Chat-IMat-GGUF/imatrix.dat
[150]7.3515,[151]7.3579,[152]7.3738,[153]7.3494,[154]7.3624,[155]7.3616,[156]7.3830,[157]7.3775,[158]7.3696,[159]7.3718,
save_imatrix: stored collected data after 160 chunks in DeepSeek-V2-Lite-Chat-IMat-GGUF/imatrix.dat
[160]7.3719,[161]7.3653,[162]7.3560,[163]7.3624,[164]7.3382,[165]7.3665,[166]7.3864,[167]7.4096,[168]7.4063,[169]7.4368,
save_imatrix: stored collected data after 170 chunks in DeepSeek-V2-Lite-Chat-IMat-GGUF/imatrix.dat
[170]7.4473,[171]7.4306,[172]7.4294,[173]7.4347,[174]7.4371,[175]7.4414,[176]7.4471,[177]7.4279,[178]7.4707,[179]7.5203,
save_imatrix: stored collected data after 180 chunks in DeepSeek-V2-Lite-Chat-IMat-GGUF/imatrix.dat
[180]7.5633,[181]7.6337,[182]7.6936,[183]7.7097,[184]7.7229,[185]7.6975,[186]7.7126,[187]7.7328,[188]7.7450,[189]7.7400,
save_imatrix: stored collected data after 190 chunks in DeepSeek-V2-Lite-Chat-IMat-GGUF/imatrix.dat
[190]7.7441,[191]7.7533,[192]7.7629,[193]7.7630,[194]7.7572,[195]7.7748,[196]7.7876,[197]7.8267,[198]7.8181,[199]7.8260,
save_imatrix: stored collected data after 200 chunks in DeepSeek-V2-Lite-Chat-IMat-GGUF/imatrix.dat
[200]7.8176,[201]7.8249,[202]7.8238,[203]7.8531,[204]7.8300,[205]7.8388,[206]7.8234,[207]7.8745,[208]7.9260,[209]7.9768,
save_imatrix: stored collected data after 210 chunks in DeepSeek-V2-Lite-Chat-IMat-GGUF/imatrix.dat
[210]8.0105,[211]8.0434,[212]8.0049,[213]7.9776,[214]7.9422,
save_imatrix: stored collected data after 214 chunks in DeepSeek-V2-Lite-Chat-IMat-GGUF/imatrix.dat
llama_print_timings: load time = 5606.62 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 = 792874.73 ms / 109568 tokens ( 7.24 ms per token, 138.19 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 = 796095.09 ms / 109569 tokens
Final estimate: PPL = 7.9422 +/- 0.09818