Upload imatrix.log with huggingface_hub

imatrix.log

@@ -0,0 +1,152 @@
+llama_model_loader: loaded meta data with 30 key-value pairs and 219 tensors from internlm2_5-1_8b-chat-IMat-GGUF/internlm2_5-1_8b-chat.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.type str              = model
+llama_model_loader: - kv   2:                               general.name str              = Internlm2_5 1_8b Chat
+llama_model_loader: - kv   3:                           general.finetune str              = chat
+llama_model_loader: - kv   4:                           general.basename str              = internlm2_5
+llama_model_loader: - kv   5:                         general.size_label str              = 1.8B
+llama_model_loader: - kv   6:                            general.license str              = other
+llama_model_loader: - kv   7:                               general.tags arr[str,1]       = ["text-generation"]
+llama_model_loader: - kv   8:                   internlm2.context_length u32              = 32768
+llama_model_loader: - kv   9:                      internlm2.block_count u32              = 24
+llama_model_loader: - kv  10:                 internlm2.embedding_length u32              = 2048
+llama_model_loader: - kv  11:              internlm2.feed_forward_length u32              = 8192
+llama_model_loader: - kv  12:                   internlm2.rope.freq_base f32              = 1000000.000000
+llama_model_loader: - kv  13:             internlm2.attention.head_count u32              = 16
+llama_model_loader: - kv  14: internlm2.attention.layer_norm_rms_epsilon f32              = 0.000010
+llama_model_loader: - kv  15:          internlm2.attention.head_count_kv u32              = 8
+llama_model_loader: - kv  16:                          general.file_type u32              = 7
+llama_model_loader: - kv  17:                       tokenizer.ggml.model str              = llama
+llama_model_loader: - kv  18:                         tokenizer.ggml.pre str              = default
+llama_model_loader: - kv  19:                      tokenizer.ggml.tokens arr[str,92544]   = ["<unk>", "<s>", "</s>", "<0x00>", "<...
+llama_model_loader: - kv  20:                      tokenizer.ggml.scores arr[f32,92544]   = [-1000.000000, -1000.000000, -1000.00...
+llama_model_loader: - kv  21:                  tokenizer.ggml.token_type arr[i32,92544]   = [3, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
+llama_model_loader: - kv  22:            tokenizer.ggml.add_space_prefix bool             = false
+llama_model_loader: - kv  23:                tokenizer.ggml.bos_token_id u32              = 1
+llama_model_loader: - kv  24:                tokenizer.ggml.eos_token_id u32              = 92542
+llama_model_loader: - kv  25:            tokenizer.ggml.padding_token_id u32              = 2
+llama_model_loader: - kv  26:               tokenizer.ggml.add_bos_token bool             = true
+llama_model_loader: - kv  27:               tokenizer.ggml.add_eos_token bool             = false
+llama_model_loader: - kv  28:                    tokenizer.chat_template str              = {{ bos_token }}{% for message in mess...
+llama_model_loader: - kv  29:               general.quantization_version u32              = 2
+llama_model_loader: - type  f32:   49 tensors
+llama_model_loader: - type q8_0:  170 tensors
+llm_load_vocab: special tokens cache size = 9
+llm_load_vocab: token to piece cache size = 0.5508 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: vocab_only       = 0
+llm_load_print_meta: n_ctx_train      = 32768
+llm_load_print_meta: n_embd           = 2048
+llm_load_print_meta: n_layer          = 24
+llm_load_print_meta: n_head           = 16
+llm_load_print_meta: n_head_kv        = 8
+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            = 2
+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             = 8192
+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  = 1000000.0
+llm_load_print_meta: freq_scale_train = 1
+llm_load_print_meta: n_ctx_orig_yarn  = 32768
+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       = ?B
+llm_load_print_meta: model ftype      = Q8_0
+llm_load_print_meta: model params     = 1.89 B
+llm_load_print_meta: model size       = 1.87 GiB (8.50 BPW) 
+llm_load_print_meta: general.name     = Internlm2_5 1_8b Chat
+llm_load_print_meta: BOS token        = 1 '<s>'
+llm_load_print_meta: EOS token        = 92542 '<|im_end|>'
+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: EOT token        = 92542 '<|im_end|>'
+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 =    0.20 MiB
+llm_load_tensors: offloading 24 repeating layers to GPU
+llm_load_tensors: offloading non-repeating layers to GPU
+llm_load_tensors: offloaded 25/25 layers to GPU
+llm_load_tensors:        CPU buffer size =   192.05 MiB
+llm_load_tensors:      CUDA0 buffer size =  1722.43 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  = 1000000.0
+llama_new_context_with_model: freq_scale = 1
+llama_kv_cache_init:      CUDA0 KV buffer size =    48.00 MiB
+llama_new_context_with_model: KV self size  =   48.00 MiB, K (f16):   24.00 MiB, V (f16):   24.00 MiB
+llama_new_context_with_model:  CUDA_Host  output buffer size =     0.35 MiB
+llama_new_context_with_model:      CUDA0 compute buffer size =   184.75 MiB
+llama_new_context_with_model:  CUDA_Host compute buffer size =     5.01 MiB
+llama_new_context_with_model: graph nodes  = 774
+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 101.517 ms
+compute_imatrix: computing over 136 chunks with batch_size 512
+compute_imatrix: 0.33 seconds per pass - ETA 0.73 minutes
+[1]8.1171,[2]5.9799,[3]5.7618,[4]6.6971,[5]6.4950,[6]6.0289,[7]7.0354,[8]7.1483,[9]7.7376,
+save_imatrix: stored collected data after 10 chunks in internlm2_5-1_8b-chat-IMat-GGUF/imatrix.dat
+[10]7.9689,[11]7.2215,[12]7.7731,[13]8.7223,[14]9.0516,[15]9.7168,[16]10.0917,[17]9.5464,[18]9.7949,[19]10.3060,
+save_imatrix: stored collected data after 20 chunks in internlm2_5-1_8b-chat-IMat-GGUF/imatrix.dat
+[20]9.9339,[21]9.9455,[22]10.4933,[23]10.5496,[24]10.6832,[25]11.0028,[26]11.3810,[27]11.5816,[28]11.6345,[29]11.8410,
+save_imatrix: stored collected data after 30 chunks in internlm2_5-1_8b-chat-IMat-GGUF/imatrix.dat
+[30]12.2061,[31]12.3618,[32]11.9333,[33]11.3946,[34]11.0039,[35]10.5436,[36]10.2947,[37]10.1431,[38]9.9996,[39]9.8758,
+save_imatrix: stored collected data after 40 chunks in internlm2_5-1_8b-chat-IMat-GGUF/imatrix.dat
+[40]9.6970,[41]9.6002,[42]9.4100,[43]9.4145,[44]9.5582,[45]9.6642,[46]9.8442,[47]9.7956,[48]10.1698,[49]10.4816,
+save_imatrix: stored collected data after 50 chunks in internlm2_5-1_8b-chat-IMat-GGUF/imatrix.dat
+[50]10.7730,[51]10.9893,[52]11.2415,[53]11.0541,[54]11.1860,[55]11.2785,[56]11.4315,[57]11.2089,[58]11.1962,[59]11.2325,
+save_imatrix: stored collected data after 60 chunks in internlm2_5-1_8b-chat-IMat-GGUF/imatrix.dat
+[60]11.3766,[61]11.6076,[62]11.8270,[63]11.9009,[64]11.8892,[65]11.9089,[66]11.8533,[67]11.8062,[68]11.6699,[69]11.6049,
+save_imatrix: stored collected data after 70 chunks in internlm2_5-1_8b-chat-IMat-GGUF/imatrix.dat
+[70]11.8227,[71]11.8646,[72]11.7587,[73]11.6955,[74]11.6992,[75]11.6129,[76]11.5900,[77]11.5655,[78]11.5782,[79]11.4525,
+save_imatrix: stored collected data after 80 chunks in internlm2_5-1_8b-chat-IMat-GGUF/imatrix.dat
+[80]11.4559,[81]11.3677,[82]11.3043,[83]11.2185,[84]11.1752,[85]11.0769,[86]11.0208,[87]10.9759,[88]11.0296,[89]11.0480,
+save_imatrix: stored collected data after 90 chunks in internlm2_5-1_8b-chat-IMat-GGUF/imatrix.dat
+[90]10.9831,[91]11.0180,[92]11.0436,[93]10.9488,[94]10.9721,[95]10.9829,[96]11.0193,[97]11.0148,[98]11.0314,[99]10.9347,
+save_imatrix: stored collected data after 100 chunks in internlm2_5-1_8b-chat-IMat-GGUF/imatrix.dat
+[100]10.8573,[101]10.7583,[102]10.6529,[103]10.5755,[104]10.4815,[105]10.3995,[106]10.4044,[107]10.4093,[108]10.4513,[109]10.5537,
+save_imatrix: stored collected data after 110 chunks in internlm2_5-1_8b-chat-IMat-GGUF/imatrix.dat
+[110]10.6555,[111]10.7395,[112]10.8834,[113]10.9967,[114]11.0452,[115]11.0187,[116]11.0439,[117]11.0456,[118]11.0526,[119]11.0112,
+save_imatrix: stored collected data after 120 chunks in internlm2_5-1_8b-chat-IMat-GGUF/imatrix.dat
+[120]11.0089,[121]11.0437,[122]11.0437,[123]11.0685,[124]11.0935,[125]11.1375,[126]11.1771,[127]11.1773,[128]11.1958,[129]11.2284,
+save_imatrix: stored collected data after 130 chunks in internlm2_5-1_8b-chat-IMat-GGUF/imatrix.dat
+[130]11.1497,[131]11.2302,[132]11.3329,[133]11.4005,[134]11.4898,[135]11.5583,[136]11.6249,
+save_imatrix: stored collected data after 136 chunks in internlm2_5-1_8b-chat-IMat-GGUF/imatrix.dat
+
+llama_print_timings:        load time =     951.98 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 =   27440.24 ms / 69632 tokens (    0.39 ms per token,  2537.59 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 =   28774.74 ms / 69633 tokens
+
+Final estimate: PPL = 11.6249 +/- 0.17251