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