Upload imatrix.log with huggingface_hub

imatrix.log

@@ -0,0 +1,128 @@
+build: 3787 (6026da52) with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
+llama_model_loader: loaded meta data with 34 key-value pairs and 338 tensors from Qwen2.5-Coder-1.5B-Instruct-IMat-GGUF/Qwen2.5-Coder-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              = Qwen2.5 Coder 1.5B Instruct
+llama_model_loader: - kv   3:                           general.finetune str              = Instruct
+llama_model_loader: - kv   4:                           general.basename str              = Qwen2.5-Coder
+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.license.link str              = https://huggingface.co/Qwen/Qwen2.5-C...
+llama_model_loader: - kv   8:                   general.base_model.count u32              = 1
+llama_model_loader: - kv   9:                  general.base_model.0.name str              = Qwen2.5 Coder 1.5B
+llama_model_loader: - kv  10:          general.base_model.0.organization str              = Qwen
+llama_model_loader: - kv  11:              general.base_model.0.repo_url str              = https://huggingface.co/Qwen/Qwen2.5-C...
+llama_model_loader: - kv  12:                               general.tags arr[str,6]       = ["code", "codeqwen", "chat", "qwen", ...
+llama_model_loader: - kv  13:                          general.languages arr[str,1]       = ["en"]
+llama_model_loader: - kv  14:                          qwen2.block_count u32              = 28
+llama_model_loader: - kv  15:                       qwen2.context_length u32              = 32768
+llama_model_loader: - kv  16:                     qwen2.embedding_length u32              = 1536
+llama_model_loader: - kv  17:                  qwen2.feed_forward_length u32              = 8960
+llama_model_loader: - kv  18:                 qwen2.attention.head_count u32              = 12
+llama_model_loader: - kv  19:              qwen2.attention.head_count_kv u32              = 2
+llama_model_loader: - kv  20:                       qwen2.rope.freq_base f32              = 1000000.000000
+llama_model_loader: - kv  21:     qwen2.attention.layer_norm_rms_epsilon f32              = 0.000001
+llama_model_loader: - kv  22:                          general.file_type u32              = 7
+llama_model_loader: - kv  23:                       tokenizer.ggml.model str              = gpt2
+llama_model_loader: - kv  24:                         tokenizer.ggml.pre str              = qwen2
+llama_model_loader: - kv  25:                      tokenizer.ggml.tokens arr[str,151936]  = ["!", "\"", "#", "$", "%", "&", "'", ...
+llama_model_loader: - kv  26:                  tokenizer.ggml.token_type arr[i32,151936]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
+llama_model_loader: - kv  27:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
+llama_model_loader: - kv  28:                tokenizer.ggml.eos_token_id u32              = 151645
+llama_model_loader: - kv  29:            tokenizer.ggml.padding_token_id u32              = 151643
+llama_model_loader: - kv  30:                tokenizer.ggml.bos_token_id u32              = 151643
+llama_model_loader: - kv  31:               tokenizer.ggml.add_bos_token bool             = false
+llama_model_loader: - kv  32:                    tokenizer.chat_template str              = {%- if tools %}\n    {{- '<|im_start|>...
+llama_model_loader: - kv  33:               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 = 22
+llm_load_vocab: token to piece cache size = 0.9310 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      = 32768
+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  = 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: ssm_dt_b_c_rms   = 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     = Qwen2.5 Coder 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  = 1000000.0
+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 (n_threads_batch = 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 | RISCV_VECT = 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 135.945 ms
+compute_imatrix: computing over 128 chunks with batch_size 512
+compute_imatrix: 0.48 seconds per pass - ETA 1.02 minutes
+[1]8.0255,[2]5.6679,[3]5.5442,[4]6.5665,[5]6.3226,[6]5.7603,[7]6.4922,[8]6.4873,[9]7.1176,[10]6.6665,[11]6.4402,[12]7.1183,[13]8.0053,[14]8.2996,[15]9.0116,[16]9.4675,[17]9.6610,[18]10.2516,[19]9.8646,[20]9.9243,[21]10.1661,[22]10.1604,[23]9.8229,[24]10.1659,[25]10.3703,[26]10.4160,[27]10.7070,[28]10.9852,[29]11.4889,[30]11.4633,[31]11.0550,[32]10.4831,[33]10.1651,[34]10.0286,[35]9.8516,[36]9.9758,[37]10.2115,[38]10.3686,[39]10.4037,[40]10.6708,[41]10.7474,[42]11.2357,[43]11.6636,[44]12.0635,[45]12.3884,[46]12.5386,[47]12.3797,[48]12.4337,[49]12.5329,[50]12.5961,[51]12.4679,[52]12.5306,[53]12.7710,[54]12.8884,[55]13.0886,[56]13.1719,[57]13.2244,[58]13.2873,[59]13.3084,[60]13.2498,[61]13.1785,[62]13.1140,[63]13.1771,[64]13.2745,[65]13.1781,[66]13.1492,[67]13.1156,[68]12.9666,[69]12.8456,[70]12.7901,[71]12.6826,[72]12.6225,[73]12.6125,[74]12.4541,[75]12.2968,[76]12.1497,[77]12.0929,[78]12.0466,[79]11.9901,[80]11.8566,[81]11.8788,[82]11.8605,[83]11.7600,[84]11.7977,[85]11.8118,[86]11.7243,[87]11.6730,[88]11.6907,[89]11.7222,[90]11.7713,[91]11.7661,[92]11.6451,[93]11.5223,[94]11.3895,[95]11.2641,[96]11.1625,[97]11.0382,[98]10.9238,[99]10.8909,[100]10.9085,[101]10.9367,[102]11.0992,[103]11.2595,[104]11.3831,[105]11.5695,[106]11.6981,[107]11.7478,[108]11.6854,[109]11.6897,[110]11.6608,[111]11.6162,[112]11.5353,[113]11.5548,[114]11.6218,[115]11.6450,[116]11.6650,[117]11.6904,[118]11.7413,[119]11.7404,[120]11.7336,[121]11.7401,[122]11.6601,[123]11.7384,[124]11.8247,[125]11.9005,[126]11.9950,[127]12.0828,[128]12.1601,
+Final estimate: PPL = 12.1601 +/- 0.19553
+
+llama_perf_context_print:        load time =    1323.17 ms
+llama_perf_context_print: prompt eval time =   30083.36 ms / 65536 tokens (    0.46 ms per token,  2178.48 tokens per second)
+llama_perf_context_print:        eval time =       0.00 ms /     1 runs   (    0.00 ms per token,      inf tokens per second)
+llama_perf_context_print:       total time =   31921.65 ms / 65537 tokens