|
llama_model_loader: loaded meta data with 38 key-value pairs and 377 tensors from DeepSeek-Coder-V2-Lite-Base-IMat-GGUF/DeepSeek-Coder-V2-Lite-Base.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-Coder-V2-Lite-Base |
|
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 cache size = 2400 |
|
llm_load_vocab: token to piece cache size = 0.6661 MB |
|
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_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 = 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-Coder-V2-Lite-Base |
|
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_print_meta: n_layer_dense_lead = 1 |
|
llm_load_print_meta: n_lora_q = 0 |
|
llm_load_print_meta: n_lora_kv = 512 |
|
llm_load_print_meta: n_ff_exp = 1408 |
|
llm_load_print_meta: n_expert_shared = 2 |
|
llm_load_print_meta: expert_weights_scale = 1.0 |
|
llm_load_print_meta: rope_yarn_log_mul = 0.0707 |
|
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no |
|
ggml_cuda_init: CUDA_USE_TENSOR_CORES: yes |
|
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 = 0.35 MiB |
|
llm_load_tensors: offloading 9 repeating layers to GPU |
|
llm_load_tensors: offloaded 9/28 layers to GPU |
|
llm_load_tensors: CPU buffer size = 39836.32 MiB |
|
llm_load_tensors: CUDA0 buffer size = 20079.16 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: CUDA_Host KV buffer size = 90.00 MiB |
|
llama_kv_cache_init: CUDA0 KV buffer size = 45.00 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: CUDA_Host output buffer size = 0.39 MiB |
|
llama_new_context_with_model: CUDA0 compute buffer size = 1012.00 MiB |
|
llama_new_context_with_model: CUDA_Host compute buffer size = 11.01 MiB |
|
llama_new_context_with_model: graph nodes = 1924 |
|
llama_new_context_with_model: graph splits = 288 |
|
|
|
system_info: n_threads = 25 / 32 | AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | 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 190.191 ms |
|
compute_imatrix: computing over 139 chunks with batch_size 512 |
|
compute_imatrix: 34.56 seconds per pass - ETA 1 hours 20.05 minutes |
|
[1]6.2603,[2]4.2559,[3]4.2127,[4]4.7761,[5]4.5767,[6]4.3695,[7]4.6843,[8]4.7775,[9]5.3341, |
|
save_imatrix: stored collected data after 10 chunks in DeepSeek-Coder-V2-Lite-Base-IMat-GGUF/imatrix.dat |
|
[10]5.5364,[11]5.0894,[12]5.3454,[13]5.7265,[14]6.0547,[15]6.1866,[16]6.5001,[17]6.7199,[18]6.8140,[19]7.0880, |
|
save_imatrix: stored collected data after 20 chunks in DeepSeek-Coder-V2-Lite-Base-IMat-GGUF/imatrix.dat |
|
[20]6.7173,[21]6.6857,[22]6.6704,[23]6.7736,[24]6.5974,[25]6.7703,[26]6.6414,[27]6.7620,[28]6.6177,[29]6.8103, |
|
save_imatrix: stored collected data after 30 chunks in DeepSeek-Coder-V2-Lite-Base-IMat-GGUF/imatrix.dat |
|
[30]6.9909,[31]7.0526,[32]6.9375,[33]6.7018,[34]6.3698,[35]6.0946,[36]5.9819,[37]5.8802,[38]5.8355,[39]5.7438, |
|
save_imatrix: stored collected data after 40 chunks in DeepSeek-Coder-V2-Lite-Base-IMat-GGUF/imatrix.dat |
|
[40]5.6738,[41]5.5508,[42]5.4551,[43]5.5012,[44]5.5681,[45]5.6692,[46]5.6761,[47]5.8850,[48]6.0827,[49]6.2164, |
|
save_imatrix: stored collected data after 50 chunks in DeepSeek-Coder-V2-Lite-Base-IMat-GGUF/imatrix.dat |
|
[50]6.3397,[51]6.4074,[52]6.3073,[53]6.4070,[54]6.4883,[55]6.5826,[56]6.4898,[57]6.4658,[58]6.4771,[59]6.5720, |
|
save_imatrix: stored collected data after 60 chunks in DeepSeek-Coder-V2-Lite-Base-IMat-GGUF/imatrix.dat |
|
[60]6.6571,[61]6.7510,[62]6.7832,[63]6.7929,[64]6.8095,[65]6.8090,[66]6.7834,[67]6.7655,[68]6.7364,[69]6.7711, |
|
save_imatrix: stored collected data after 70 chunks in DeepSeek-Coder-V2-Lite-Base-IMat-GGUF/imatrix.dat |
|
[70]6.7805,[71]6.7797,[72]6.8014,[73]6.7961,[74]6.7804,[75]6.7637,[76]6.7513,[77]6.7458,[78]6.7567,[79]6.7167, |
|
save_imatrix: stored collected data after 80 chunks in DeepSeek-Coder-V2-Lite-Base-IMat-GGUF/imatrix.dat |
|
[80]6.7398,[81]6.7282,[82]6.7182,[83]6.6923,[84]6.6760,[85]6.6566,[86]6.6329,[87]6.6121,[88]6.6344,[89]6.6562, |
|
save_imatrix: stored collected data after 90 chunks in DeepSeek-Coder-V2-Lite-Base-IMat-GGUF/imatrix.dat |
|
[90]6.6532,[91]6.6857,[92]6.7165,[93]6.6615,[94]6.6489,[95]6.6257,[96]6.6471,[97]6.6566,[98]6.6490,[99]6.5802, |
|
save_imatrix: stored collected data after 100 chunks in DeepSeek-Coder-V2-Lite-Base-IMat-GGUF/imatrix.dat |
|
[100]6.5077,[101]6.4362,[102]6.3653,[103]6.2953,[104]6.2303,[105]6.1670,[106]6.1073,[107]6.0471,[108]6.0034,[109]6.0147, |
|
save_imatrix: stored collected data after 110 chunks in DeepSeek-Coder-V2-Lite-Base-IMat-GGUF/imatrix.dat |
|
[110]6.0502,[111]6.1111,[112]6.1705,[113]6.2131,[114]6.3040,[115]6.3445,[116]6.3729,[117]6.3757,[118]6.4049,[119]6.3903, |
|
save_imatrix: stored collected data after 120 chunks in DeepSeek-Coder-V2-Lite-Base-IMat-GGUF/imatrix.dat |
|
[120]6.3742,[121]6.3021,[122]6.2349,[123]6.2705,[124]6.3141,[125]6.3077,[126]6.3098,[127]6.3189,[128]6.3448,[129]6.3466, |
|
save_imatrix: stored collected data after 130 chunks in DeepSeek-Coder-V2-Lite-Base-IMat-GGUF/imatrix.dat |
|
[130]6.3555,[131]6.3755,[132]6.3570,[133]6.3367,[134]6.3710,[135]6.4155,[136]6.4502,[137]6.4921,[138]6.5475,[139]6.5773, |
|
save_imatrix: stored collected data after 139 chunks in DeepSeek-Coder-V2-Lite-Base-IMat-GGUF/imatrix.dat |
|
|
|
llama_print_timings: load time = 52295.72 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 = 549194.65 ms / 71168 tokens ( 7.72 ms per token, 129.59 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 = 571412.12 ms / 71169 tokens |
|
|
|
Final estimate: PPL = 6.5773 +/- 0.08523 |
|
|
