Upload imatrix.log with huggingface_hub

imatrix.log

@@ -1,43 +1,50 @@
-llama_model_loader: loaded meta data with 24 key-value pairs and 291 tensors from internlm2_5-7b-chat-IMat-GGUF/internlm2_5-7b-chat.Q8_0.gguf.hardlink.gguf (version GGUF V3 (latest))
+llama_model_loader: loaded meta data with 30 key-value pairs and 291 tensors from internlm2_5-7b-chat-IMat-GGUF/internlm2_5-7b-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.name str              = InternLM2
-llama_model_loader: - kv   2:                   internlm2.context_length u32              = 32768
-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              = 1000000.000000
-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: - kv   1:                               general.type str              = model
+llama_model_loader: - kv   2:                               general.name str              = Internlm2_5 7b 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              = 7B
+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              = 32
+llama_model_loader: - kv  10:                 internlm2.embedding_length u32              = 4096
+llama_model_loader: - kv  11:              internlm2.feed_forward_length u32              = 14336
+llama_model_loader: - kv  12:                   internlm2.rope.freq_base f32              = 1000000.000000
+llama_model_loader: - kv  13:             internlm2.attention.head_count u32              = 32
+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:   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_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           = 4096
+llm_load_print_meta: n_layer          = 32
 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
@@ -69,12 +76,13 @@ 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: general.name     = Internlm2_5 7b Chat
 llm_load_print_meta: BOS token        = 1 '<s>'
-llm_load_print_meta: EOS token        = 92542 '[UNUSED_TOKEN_145]'
+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
@@ -103,42 +111,42 @@ 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 125.116 ms
+compute_imatrix: tokenization took 101.295 ms
 compute_imatrix: computing over 136 chunks with batch_size 512
-compute_imatrix: 1.50 seconds per pass - ETA 3.38 minutes
-[1]5.3660,[2]3.9648,[3]3.7793,[4]4.3816,[5]4.2898,[6]3.9196,[7]4.5676,[8]4.6225,[9]5.0903,
+compute_imatrix: 0.59 seconds per pass - ETA 1.32 minutes
+[1]5.3769,[2]3.9691,[3]3.7820,[4]4.3833,[5]4.2913,[6]3.9200,[7]4.5687,[8]4.6228,[9]5.0904,
 save_imatrix: stored collected data after 10 chunks in internlm2_5-7b-chat-IMat-GGUF/imatrix.dat
-[10]5.2353,[11]4.8014,[12]5.1504,[13]5.7994,[14]6.1277,[15]6.6241,[16]6.8574,[17]6.5020,[18]6.7127,[19]7.0476,
+[10]5.2358,[11]4.8009,[12]5.1499,[13]5.7993,[14]6.1283,[15]6.6242,[16]6.8570,[17]6.5016,[18]6.7125,[19]7.0479,
 save_imatrix: stored collected data after 20 chunks in internlm2_5-7b-chat-IMat-GGUF/imatrix.dat
-[20]6.8084,[21]6.8750,[22]7.0183,[23]7.0552,[24]7.0645,[25]7.2564,[26]7.4545,[27]7.6265,[28]7.6720,[29]7.8119,
+[20]6.8082,[21]6.8744,[22]7.0183,[23]7.0556,[24]7.0649,[25]7.2574,[26]7.4557,[27]7.6284,[28]7.6740,[29]7.8141,
 save_imatrix: stored collected data after 30 chunks in internlm2_5-7b-chat-IMat-GGUF/imatrix.dat
-[30]8.0432,[31]8.0995,[32]7.8028,[33]7.4882,[34]7.1976,[35]6.9321,[36]6.7823,[37]6.6661,[38]6.5867,[39]6.5069,
+[30]8.0461,[31]8.1025,[32]7.8055,[33]7.4904,[34]7.1984,[35]6.9328,[36]6.7832,[37]6.6670,[38]6.5876,[39]6.5080,
 save_imatrix: stored collected data after 40 chunks in internlm2_5-7b-chat-IMat-GGUF/imatrix.dat
-[40]6.4153,[41]6.3593,[42]6.2493,[43]6.2304,[44]6.2903,[45]6.3623,[46]6.4987,[47]6.4758,[48]6.7113,[49]6.8952,
+[40]6.4166,[41]6.3603,[42]6.2501,[43]6.2315,[44]6.2919,[45]6.3633,[46]6.4997,[47]6.4768,[48]6.7117,[49]6.8956,
 save_imatrix: stored collected data after 50 chunks in internlm2_5-7b-chat-IMat-GGUF/imatrix.dat
-[50]7.0713,[51]7.1993,[52]7.3858,[53]7.2623,[54]7.3476,[55]7.4306,[56]7.5495,[57]7.4182,[58]7.4262,[59]7.4570,
+[50]7.0720,[51]7.2003,[52]7.3871,[53]7.2634,[54]7.3487,[55]7.4317,[56]7.5508,[57]7.4196,[58]7.4276,[59]7.4583,
 save_imatrix: stored collected data after 60 chunks in internlm2_5-7b-chat-IMat-GGUF/imatrix.dat
-[60]7.5600,[61]7.6967,[62]7.8142,[63]7.8778,[64]7.8814,[65]7.8901,[66]7.8617,[67]7.8262,[68]7.7442,[69]7.7165,
+[60]7.5612,[61]7.6982,[62]7.8157,[63]7.8791,[64]7.8829,[65]7.8916,[66]7.8631,[67]7.8273,[68]7.7453,[69]7.7176,
 save_imatrix: stored collected data after 70 chunks in internlm2_5-7b-chat-IMat-GGUF/imatrix.dat
-[70]7.7870,[71]7.8071,[72]7.7318,[73]7.6962,[74]7.6986,[75]7.6555,[76]7.6464,[77]7.6257,[78]7.6434,[79]7.5874,
+[70]7.7884,[71]7.8087,[72]7.7333,[73]7.6979,[74]7.7003,[75]7.6571,[76]7.6477,[77]7.6271,[78]7.6449,[79]7.5887,
 save_imatrix: stored collected data after 80 chunks in internlm2_5-7b-chat-IMat-GGUF/imatrix.dat
-[80]7.5887,[81]7.5350,[82]7.4994,[83]7.4532,[84]7.4326,[85]7.3718,[86]7.3389,[87]7.3023,[88]7.3406,[89]7.3531,
+[80]7.5901,[81]7.5365,[82]7.5011,[83]7.4550,[84]7.4343,[85]7.3733,[86]7.3403,[87]7.3036,[88]7.3420,[89]7.3542,
 save_imatrix: stored collected data after 90 chunks in internlm2_5-7b-chat-IMat-GGUF/imatrix.dat
-[90]7.3153,[91]7.3366,[92]7.3520,[93]7.3018,[94]7.2910,[95]7.2756,[96]7.3042,[97]7.3015,[98]7.3043,[99]7.2553,
+[90]7.3164,[91]7.3376,[92]7.3530,[93]7.3026,[94]7.2918,[95]7.2765,[96]7.3050,[97]7.3023,[98]7.3053,[99]7.2564,
 save_imatrix: stored collected data after 100 chunks in internlm2_5-7b-chat-IMat-GGUF/imatrix.dat
-[100]7.2220,[101]7.1726,[102]7.1216,[103]7.0830,[104]7.0406,[105]7.0004,[106]6.9762,[107]6.9796,[108]7.0178,[109]7.0906,
+[100]7.2231,[101]7.1735,[102]7.1225,[103]7.0841,[104]7.0417,[105]7.0015,[106]6.9774,[107]6.9807,[108]7.0191,[109]7.0920,
 save_imatrix: stored collected data after 110 chunks in internlm2_5-7b-chat-IMat-GGUF/imatrix.dat
-[110]7.1629,[111]7.2254,[112]7.3286,[113]7.3967,[114]7.4209,[115]7.4120,[116]7.4278,[117]7.4226,[118]7.4174,[119]7.3764,
+[110]7.1641,[111]7.2266,[112]7.3301,[113]7.3983,[114]7.4227,[115]7.4135,[116]7.4296,[117]7.4244,[118]7.4193,[119]7.3785,
 save_imatrix: stored collected data after 120 chunks in internlm2_5-7b-chat-IMat-GGUF/imatrix.dat
-[120]7.3639,[121]7.3932,[122]7.3968,[123]7.3999,[124]7.4179,[125]7.4566,[126]7.4840,[127]7.4967,[128]7.5167,[129]7.5438,
+[120]7.3659,[121]7.3952,[122]7.3990,[123]7.4023,[124]7.4202,[125]7.4587,[126]7.4862,[127]7.4988,[128]7.5187,[129]7.5457,
 save_imatrix: stored collected data after 130 chunks in internlm2_5-7b-chat-IMat-GGUF/imatrix.dat
-[130]7.4995,[131]7.5409,[132]7.6049,[133]7.6445,[134]7.7057,[135]7.7517,[136]7.8004,
+[130]7.5014,[131]7.5428,[132]7.6069,[133]7.6466,[134]7.7078,[135]7.7539,[136]7.8028,
 save_imatrix: stored collected data after 136 chunks in internlm2_5-7b-chat-IMat-GGUF/imatrix.dat
 
-llama_print_timings:        load time =    3258.43 ms
+llama_print_timings:        load time =    2096.79 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 =   78728.65 ms / 69632 tokens (    1.13 ms per token,   884.46 tokens per second)
+llama_print_timings: prompt eval time =   70631.81 ms / 69632 tokens (    1.01 ms per token,   985.84 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 =   81165.19 ms / 69633 tokens
+llama_print_timings:       total time =   72872.89 ms / 69633 tokens
 
-Final estimate: PPL = 7.8004 +/- 0.10722
+Final estimate: PPL = 7.8028 +/- 0.10727