Upload imatrix.log with huggingface_hub

imatrix.log

@@ -0,0 +1,144 @@
+llama_model_loader: loaded meta data with 24 key-value pairs and 291 tensors from internlm2_5-7b-chat-1m-IMat-GGUF/internlm2_5-7b-chat-1m.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              = internlm2
+llama_model_loader: - kv   1:                               general.name str              = InternLM2
+llama_model_loader: - kv   2:                   internlm2.context_length u32              = 262144
+llama_model_loader: - kv   3:                      internlm2.block_count u32              = 32
+llama_model_loader: - kv   4:                 internlm2.embedding_length u32              = 4096
+llama_model_loader: - kv   5:              internlm2.feed_forward_length u32              = 14336
+llama_model_loader: - kv   6:                   internlm2.rope.freq_base f32              = 50000000.000000
+llama_model_loader: - kv   7:             internlm2.attention.head_count u32              = 32
+llama_model_loader: - kv   8: internlm2.attention.layer_norm_rms_epsilon f32              = 0.000010
+llama_model_loader: - kv   9:          internlm2.attention.head_count_kv u32              = 8
+llama_model_loader: - kv  10:                          general.file_type u32              = 7
+llama_model_loader: - kv  11:                       tokenizer.ggml.model str              = llama
+llama_model_loader: - kv  12:                         tokenizer.ggml.pre str              = default
+llama_model_loader: - kv  13:                      tokenizer.ggml.tokens arr[str,92544]   = ["<unk>", "<s>", "</s>", "<0x00>", "<...
+llama_model_loader: - kv  14:                      tokenizer.ggml.scores arr[f32,92544]   = [0.000000, 0.000000, 0.000000, 0.0000...
+llama_model_loader: - kv  15:                  tokenizer.ggml.token_type arr[i32,92544]   = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
+llama_model_loader: - kv  16:            tokenizer.ggml.add_space_prefix bool             = false
+llama_model_loader: - kv  17:                tokenizer.ggml.bos_token_id u32              = 1
+llama_model_loader: - kv  18:                tokenizer.ggml.eos_token_id u32              = 92542
+llama_model_loader: - kv  19:            tokenizer.ggml.padding_token_id u32              = 2
+llama_model_loader: - kv  20:               tokenizer.ggml.add_bos_token bool             = true
+llama_model_loader: - kv  21:               tokenizer.ggml.add_eos_token bool             = false
+llama_model_loader: - kv  22:                    tokenizer.chat_template str              = {{ bos_token }}{% for message in mess...
+llama_model_loader: - kv  23:               general.quantization_version u32              = 2
+llama_model_loader: - type  f32:   65 tensors
+llama_model_loader: - type q8_0:  226 tensors
+llm_load_vocab: special tokens cache size = 259
+llm_load_vocab: token to piece cache size = 0.5531 MB
+llm_load_print_meta: format           = GGUF V3 (latest)
+llm_load_print_meta: arch             = internlm2
+llm_load_print_meta: vocab type       = SPM
+llm_load_print_meta: n_vocab          = 92544
+llm_load_print_meta: n_merges         = 0
+llm_load_print_meta: n_ctx_train      = 262144
+llm_load_print_meta: n_embd           = 4096
+llm_load_print_meta: n_head           = 32
+llm_load_print_meta: n_head_kv        = 8
+llm_load_print_meta: n_layer          = 32
+llm_load_print_meta: n_rot            = 128
+llm_load_print_meta: n_swa            = 0
+llm_load_print_meta: n_embd_head_k    = 128
+llm_load_print_meta: n_embd_head_v    = 128
+llm_load_print_meta: n_gqa            = 4
+llm_load_print_meta: n_embd_k_gqa     = 1024
+llm_load_print_meta: n_embd_v_gqa     = 1024
+llm_load_print_meta: f_norm_eps       = 0.0e+00
+llm_load_print_meta: f_norm_rms_eps   = 1.0e-05
+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        = 0
+llm_load_print_meta: rope scaling     = linear
+llm_load_print_meta: freq_base_train  = 50000000.0
+llm_load_print_meta: freq_scale_train = 1
+llm_load_print_meta: n_ctx_orig_yarn  = 262144
+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       = 7B
+llm_load_print_meta: model ftype      = Q8_0
+llm_load_print_meta: model params     = 7.74 B
+llm_load_print_meta: model size       = 7.66 GiB (8.50 BPW) 
+llm_load_print_meta: general.name     = InternLM2
+llm_load_print_meta: BOS token        = 1 '<s>'
+llm_load_print_meta: EOS token        = 92542 '[UNUSED_TOKEN_145]'
+llm_load_print_meta: UNK token        = 0 '<unk>'
+llm_load_print_meta: PAD token        = 2 '</s>'
+llm_load_print_meta: LF token         = 13 '<0x0A>'
+llm_load_print_meta: max token length = 384
+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 =    0.27 MiB
+llm_load_tensors: offloading 32 repeating layers to GPU
+llm_load_tensors: offloading non-repeating layers to GPU
+llm_load_tensors: offloaded 33/33 layers to GPU
+llm_load_tensors:        CPU buffer size =   384.09 MiB
+llm_load_tensors:      CUDA0 buffer size =  7457.11 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  = 50000000.0
+llama_new_context_with_model: freq_scale = 1
+llama_kv_cache_init:      CUDA0 KV buffer size =    64.00 MiB
+llama_new_context_with_model: KV self size  =   64.00 MiB, K (f16):   32.00 MiB, V (f16):   32.00 MiB
+llama_new_context_with_model:  CUDA_Host  output buffer size =     0.35 MiB
+llama_new_context_with_model:      CUDA0 compute buffer size =   188.75 MiB
+llama_new_context_with_model:  CUDA_Host compute buffer size =     9.01 MiB
+llama_new_context_with_model: graph nodes  = 1030
+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 103.571 ms
+compute_imatrix: computing over 136 chunks with batch_size 512
+compute_imatrix: 0.57 seconds per pass - ETA 1.28 minutes
+[1]5.0346,[2]3.6723,[3]3.5707,[4]4.0879,[5]4.0274,[6]3.6532,[7]4.3100,[8]4.3760,[9]4.8143,
+save_imatrix: stored collected data after 10 chunks in internlm2_5-7b-chat-1m-IMat-GGUF/imatrix.dat
+[10]4.9549,[11]4.5921,[12]4.9100,[13]5.5257,[14]5.8588,[15]6.3237,[16]6.5349,[17]6.2162,[18]6.4203,[19]6.7455,
+save_imatrix: stored collected data after 20 chunks in internlm2_5-7b-chat-1m-IMat-GGUF/imatrix.dat
+[20]6.4964,[21]6.5862,[22]6.6543,[23]6.6712,[24]6.5913,[25]6.7950,[26]7.0111,[27]7.1811,[28]7.2316,[29]7.3379,
+save_imatrix: stored collected data after 30 chunks in internlm2_5-7b-chat-1m-IMat-GGUF/imatrix.dat
+[30]7.5555,[31]7.6303,[32]7.3712,[33]7.0776,[34]6.7896,[35]6.5375,[36]6.3935,[37]6.2858,[38]6.2133,[39]6.1529,
+save_imatrix: stored collected data after 40 chunks in internlm2_5-7b-chat-1m-IMat-GGUF/imatrix.dat
+[40]6.0788,[41]6.0151,[42]5.9126,[43]5.8695,[44]5.9202,[45]5.9750,[46]6.1160,[47]6.1016,[48]6.3090,[49]6.4878,
+save_imatrix: stored collected data after 50 chunks in internlm2_5-7b-chat-1m-IMat-GGUF/imatrix.dat
+[50]6.6539,[51]6.7808,[52]6.9489,[53]6.8259,[54]6.9078,[55]6.9920,[56]7.1027,[57]6.9751,[58]6.9850,[59]7.0143,
+save_imatrix: stored collected data after 60 chunks in internlm2_5-7b-chat-1m-IMat-GGUF/imatrix.dat
+[60]7.1009,[61]7.2276,[62]7.3030,[63]7.3550,[64]7.3615,[65]7.3773,[66]7.3610,[67]7.3245,[68]7.2521,[69]7.2307,
+save_imatrix: stored collected data after 70 chunks in internlm2_5-7b-chat-1m-IMat-GGUF/imatrix.dat
+[70]7.2776,[71]7.2967,[72]7.2223,[73]7.1809,[74]7.1856,[75]7.1442,[76]7.1218,[77]7.1049,[78]7.1137,[79]7.0665,
+save_imatrix: stored collected data after 80 chunks in internlm2_5-7b-chat-1m-IMat-GGUF/imatrix.dat
+[80]7.0704,[81]7.0205,[82]6.9936,[83]6.9500,[84]6.9328,[85]6.8774,[86]6.8457,[87]6.8165,[88]6.8428,[89]6.8503,
+save_imatrix: stored collected data after 90 chunks in internlm2_5-7b-chat-1m-IMat-GGUF/imatrix.dat
+[90]6.8185,[91]6.8376,[92]6.8526,[93]6.8059,[94]6.7976,[95]6.7873,[96]6.8087,[97]6.8044,[98]6.8017,[99]6.7634,
+save_imatrix: stored collected data after 100 chunks in internlm2_5-7b-chat-1m-IMat-GGUF/imatrix.dat
+[100]6.7333,[101]6.6953,[102]6.6538,[103]6.6212,[104]6.5844,[105]6.5521,[106]6.5216,[107]6.5282,[108]6.5647,[109]6.6344,
+save_imatrix: stored collected data after 110 chunks in internlm2_5-7b-chat-1m-IMat-GGUF/imatrix.dat
+[110]6.6972,[111]6.7546,[112]6.8547,[113]6.9219,[114]6.9492,[115]6.9457,[116]6.9581,[117]6.9503,[118]6.9399,[119]6.8934,
+save_imatrix: stored collected data after 120 chunks in internlm2_5-7b-chat-1m-IMat-GGUF/imatrix.dat
+[120]6.8699,[121]6.9023,[122]6.9007,[123]6.9027,[124]6.9205,[125]6.9609,[126]6.9884,[127]6.9980,[128]7.0215,[129]7.0489,
+save_imatrix: stored collected data after 130 chunks in internlm2_5-7b-chat-1m-IMat-GGUF/imatrix.dat
+[130]7.0098,[131]7.0461,[132]7.1022,[133]7.1359,[134]7.1953,[135]7.2389,[136]7.2832,
+save_imatrix: stored collected data after 136 chunks in internlm2_5-7b-chat-1m-IMat-GGUF/imatrix.dat
+
+llama_print_timings:        load time =    1840.88 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 =   71070.73 ms / 69632 tokens (    1.02 ms per token,   979.76 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 =   73099.32 ms / 69633 tokens
+
+Final estimate: PPL = 7.2832 +/- 0.09853