Upload imatrix.log with huggingface_hub

Browse files

Files changed (1) hide show

imatrix.log +147 -0

imatrix.log ADDED Viewed

	@@ -0,0 +1,147 @@

+llama_model_loader: loaded meta data with 28 key-value pairs and 338 tensors from Qwen2-Math-1.5B-Instruct-IMat-GGUF/Qwen2-Math-1.5B-Instruct.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              = qwen2
+llama_model_loader: - kv   1:                               general.type str              = model
+llama_model_loader: - kv   2:                               general.name str              = Qwen2 Math 1.5B Instruct
+llama_model_loader: - kv   3:                           general.finetune str              = Instruct
+llama_model_loader: - kv   4:                           general.basename str              = Qwen2-Math
+llama_model_loader: - kv   5:                         general.size_label str              = 1.5B
+llama_model_loader: - kv   6:                            general.license str              = apache-2.0
+llama_model_loader: - kv   7:                               general.tags arr[str,2]       = ["chat", "text-generation"]
+llama_model_loader: - kv   8:                          general.languages arr[str,1]       = ["en"]
+llama_model_loader: - kv   9:                          qwen2.block_count u32              = 28
+llama_model_loader: - kv  10:                       qwen2.context_length u32              = 4096
+llama_model_loader: - kv  11:                     qwen2.embedding_length u32              = 1536
+llama_model_loader: - kv  12:                  qwen2.feed_forward_length u32              = 8960
+llama_model_loader: - kv  13:                 qwen2.attention.head_count u32              = 12
+llama_model_loader: - kv  14:              qwen2.attention.head_count_kv u32              = 2
+llama_model_loader: - kv  15:                       qwen2.rope.freq_base f32              = 10000.000000
+llama_model_loader: - kv  16:     qwen2.attention.layer_norm_rms_epsilon f32              = 0.000001
+llama_model_loader: - kv  17:                          general.file_type u32              = 7
+llama_model_loader: - kv  18:                       tokenizer.ggml.model str              = gpt2
+llama_model_loader: - kv  19:                         tokenizer.ggml.pre str              = qwen2
+llama_model_loader: - kv  20:                      tokenizer.ggml.tokens arr[str,151936]  = ["!", "\"", "#", "$", "%", "&", "'", ...
+llama_model_loader: - kv  21:                  tokenizer.ggml.token_type arr[i32,151936]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
+llama_model_loader: - kv  22:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
+llama_model_loader: - kv  23:                tokenizer.ggml.eos_token_id u32              = 151645
+llama_model_loader: - kv  24:            tokenizer.ggml.padding_token_id u32              = 151643
+llama_model_loader: - kv  25:                tokenizer.ggml.bos_token_id u32              = 151643
+llama_model_loader: - kv  26:                    tokenizer.chat_template str              = {% for message in messages %}{% if lo...
+llama_model_loader: - kv  27:               general.quantization_version u32              = 2
+llama_model_loader: - type  f32:  141 tensors
+llama_model_loader: - type q8_0:  197 tensors
+llm_load_vocab: special tokens cache size = 3
+llm_load_vocab: token to piece cache size = 0.9308 MB
+llm_load_print_meta: format           = GGUF V3 (latest)
+llm_load_print_meta: arch             = qwen2
+llm_load_print_meta: vocab type       = BPE
+llm_load_print_meta: n_vocab          = 151936
+llm_load_print_meta: n_merges         = 151387
+llm_load_print_meta: vocab_only       = 0
+llm_load_print_meta: n_ctx_train      = 4096
+llm_load_print_meta: n_embd           = 1536
+llm_load_print_meta: n_layer          = 28
+llm_load_print_meta: n_head           = 12
+llm_load_print_meta: n_head_kv        = 2
+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            = 6
+llm_load_print_meta: n_embd_k_gqa     = 256
+llm_load_print_meta: n_embd_v_gqa     = 256
+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             = 8960
+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        = 2
+llm_load_print_meta: rope scaling     = linear
+llm_load_print_meta: freq_base_train  = 10000.0
+llm_load_print_meta: freq_scale_train = 1
+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       = ?B
+llm_load_print_meta: model ftype      = Q8_0
+llm_load_print_meta: model params     = 1.54 B
+llm_load_print_meta: model size       = 1.53 GiB (8.50 BPW)
+llm_load_print_meta: general.name     = Qwen2 Math 1.5B Instruct
+llm_load_print_meta: BOS token        = 151643 '<|endoftext|>'
+llm_load_print_meta: EOS token        = 151645 '<|im_end|>'
+llm_load_print_meta: PAD token        = 151643 '<|endoftext|>'
+llm_load_print_meta: LF token         = 148848 'ÄĬ'
+llm_load_print_meta: EOT token        = 151645 '<|im_end|>'
+llm_load_print_meta: max token length = 256
+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 =    0.30 MiB
+llm_load_tensors: offloading 28 repeating layers to GPU
+llm_load_tensors: offloading non-repeating layers to GPU
+llm_load_tensors: offloaded 29/29 layers to GPU
+llm_load_tensors:        CPU buffer size =   236.47 MiB
+llm_load_tensors:      CUDA0 buffer size =  1564.63 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 = 1
+llama_kv_cache_init:      CUDA0 KV buffer size =    14.00 MiB
+llama_new_context_with_model: KV self size  =   14.00 MiB, K (f16):    7.00 MiB, V (f16):    7.00 MiB
+llama_new_context_with_model:  CUDA_Host  output buffer size =     0.58 MiB
+llama_new_context_with_model:      CUDA0 compute buffer size =   299.75 MiB
+llama_new_context_with_model:  CUDA_Host compute buffer size =     4.01 MiB
+llama_new_context_with_model: graph nodes  = 986
+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 129.312 ms
+compute_imatrix: computing over 128 chunks with batch_size 512
+compute_imatrix: 0.41 seconds per pass - ETA 0.87 minutes
+[1]21.5954,[2]16.3481,[3]13.5135,[4]15.6791,[5]15.3211,[6]14.5537,[7]15.0464,[8]14.4367,[9]15.6930,
+save_imatrix: stored collected data after 10 chunks in Qwen2-Math-1.5B-Instruct-IMat-GGUF/imatrix.dat
+[10]14.8501,[11]14.1743,[12]15.7505,[13]17.8924,[14]18.3293,[15]20.2933,[16]20.9890,[17]21.6694,[18]23.3586,[19]22.5698,
+save_imatrix: stored collected data after 20 chunks in Qwen2-Math-1.5B-Instruct-IMat-GGUF/imatrix.dat
+[20]22.5694,[21]24.8524,[22]25.7592,[23]25.6477,[24]26.0525,[25]26.5780,[26]27.1280,[27]28.3387,[28]29.2826,[29]30.8846,
+save_imatrix: stored collected data after 30 chunks in Qwen2-Math-1.5B-Instruct-IMat-GGUF/imatrix.dat
+[30]31.7509,[31]32.9879,[32]32.0955,[33]31.0417,[34]30.2879,[35]29.3795,[36]32.0682,[37]36.4868,[38]37.8778,[39]38.0367,
+save_imatrix: stored collected data after 40 chunks in Qwen2-Math-1.5B-Instruct-IMat-GGUF/imatrix.dat
+[40]38.6583,[41]38.5933,[42]40.2867,[43]41.3568,[44]42.4316,[45]43.3600,[46]43.9424,[47]43.4594,[48]43.0973,[49]42.9915,
+save_imatrix: stored collected data after 50 chunks in Qwen2-Math-1.5B-Instruct-IMat-GGUF/imatrix.dat
+[50]42.5710,[51]42.0195,[52]41.9720,[53]43.2653,[54]43.5679,[55]44.4592,[56]44.7204,[57]44.5410,[58]44.5908,[59]44.4207,
+save_imatrix: stored collected data after 60 chunks in Qwen2-Math-1.5B-Instruct-IMat-GGUF/imatrix.dat
+[60]44.4606,[61]43.8949,[62]43.5317,[63]43.8146,[64]44.3940,[65]43.9416,[66]43.4245,[67]42.9840,[68]42.1103,[69]41.7746,
+save_imatrix: stored collected data after 70 chunks in Qwen2-Math-1.5B-Instruct-IMat-GGUF/imatrix.dat
+[70]41.2368,[71]40.5090,[72]39.9531,[73]39.5549,[74]38.6676,[75]37.9093,[76]37.1520,[77]36.5948,[78]36.2084,[79]35.8016,
+save_imatrix: stored collected data after 80 chunks in Qwen2-Math-1.5B-Instruct-IMat-GGUF/imatrix.dat
+[80]35.2852,[81]35.1617,[82]34.8628,[83]34.3655,[84]34.3487,[85]34.1451,[86]34.3092,[87]34.0145,[88]33.9010,[89]33.9726,
+save_imatrix: stored collected data after 90 chunks in Qwen2-Math-1.5B-Instruct-IMat-GGUF/imatrix.dat
+[90]34.0018,[91]33.9192,[92]33.1946,[93]32.6052,[94]31.9016,[95]31.2409,[96]30.6513,[97]30.0298,[98]29.4772,[99]29.6608,
+save_imatrix: stored collected data after 100 chunks in Qwen2-Math-1.5B-Instruct-IMat-GGUF/imatrix.dat
+[100]29.6859,[101]29.6662,[102]30.0276,[103]30.3328,[104]30.5797,[105]31.0761,[106]31.5270,[107]31.6387,[108]31.3431,[109]31.2995,
+save_imatrix: stored collected data after 110 chunks in Qwen2-Math-1.5B-Instruct-IMat-GGUF/imatrix.dat
+[110]31.2990,[111]30.8986,[112]30.5160,[113]30.5057,[114]30.5968,[115]30.7201,[116]30.7513,[117]30.8649,[118]30.9462,[119]30.8916,
+save_imatrix: stored collected data after 120 chunks in Qwen2-Math-1.5B-Instruct-IMat-GGUF/imatrix.dat
+[120]30.8107,[121]30.7677,[122]30.4821,[123]30.6267,[124]30.9271,[125]31.2403,[126]31.5599,[127]31.8815,[128]32.1625,
+save_imatrix: stored collected data after 128 chunks in Qwen2-Math-1.5B-Instruct-IMat-GGUF/imatrix.dat
+llama_print_timings:        load time =     964.13 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 =   29971.58 ms / 65536 tokens (    0.46 ms per token,  2186.60 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 =   31510.10 ms / 65537 tokens
+Final estimate: PPL = 32.1625 +/- 0.64699