Upload imatrix.log with huggingface_hub

imatrix.log

@@ -0,0 +1,137 @@
+main: build = 3086 (554c247c)
+main: built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
+main: seed  = 1717701152
+llama_model_loader: loaded meta data with 21 key-value pairs and 338 tensors from Qwen2-1.5B-IMat-GGUF/Qwen2-1.5B.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.name str              = Qwen2-1.5B
+llama_model_loader: - kv   2:                          qwen2.block_count u32              = 28
+llama_model_loader: - kv   3:                       qwen2.context_length u32              = 131072
+llama_model_loader: - kv   4:                     qwen2.embedding_length u32              = 1536
+llama_model_loader: - kv   5:                  qwen2.feed_forward_length u32              = 8960
+llama_model_loader: - kv   6:                 qwen2.attention.head_count u32              = 12
+llama_model_loader: - kv   7:              qwen2.attention.head_count_kv u32              = 2
+llama_model_loader: - kv   8:                       qwen2.rope.freq_base f32              = 1000000.000000
+llama_model_loader: - kv   9:     qwen2.attention.layer_norm_rms_epsilon f32              = 0.000001
+llama_model_loader: - kv  10:                          general.file_type u32              = 0
+llama_model_loader: - kv  11:                       tokenizer.ggml.model str              = gpt2
+llama_model_loader: - kv  12:                         tokenizer.ggml.pre str              = qwen2
+llama_model_loader: - kv  13:                      tokenizer.ggml.tokens arr[str,151936]  = ["!", "\"", "#", "$", "%", "&", "'", ...
+llama_model_loader: - kv  14:                  tokenizer.ggml.token_type arr[i32,151936]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
+llama_model_loader: - kv  15:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
+llama_model_loader: - kv  16:                tokenizer.ggml.eos_token_id u32              = 151643
+llama_model_loader: - kv  17:            tokenizer.ggml.padding_token_id u32              = 151643
+llama_model_loader: - kv  18:                tokenizer.ggml.bos_token_id u32              = 151643
+llama_model_loader: - kv  19:                    tokenizer.chat_template str              = {% for message in messages %}{% if lo...
+llama_model_loader: - kv  20:               general.quantization_version u32              = 2
+llama_model_loader: - type  f32:  338 tensors
+llm_load_vocab: special tokens cache size = 293
+llm_load_vocab: token to piece cache size = 0.9338 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: n_ctx_train      = 131072
+llm_load_print_meta: n_embd           = 1536
+llm_load_print_meta: n_head           = 12
+llm_load_print_meta: n_head_kv        = 2
+llm_load_print_meta: n_layer          = 28
+llm_load_print_meta: n_rot            = 128
+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_yarn_orig_ctx  = 131072
+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      = all F32
+llm_load_print_meta: model params     = 1.54 B
+llm_load_print_meta: model size       = 5.75 GiB (32.00 BPW) 
+llm_load_print_meta: general.name     = Qwen2-1.5B
+llm_load_print_meta: BOS token        = 151643 '<|endoftext|>'
+llm_load_print_meta: EOS token        = 151643 '<|endoftext|>'
+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|>'
+ggml_cuda_init: failed to initialize CUDA: no CUDA-capable device is detected
+llm_load_tensors: ggml ctx size =    0.16 MiB
+llm_load_tensors: offloading 0 repeating layers to GPU
+llm_load_tensors: offloaded 0/29 layers to GPU
+llm_load_tensors:        CPU buffer size =  5888.80 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
+ggml_cuda_host_malloc: failed to allocate 14.00 MiB of pinned memory: no CUDA-capable device is detected
+llama_kv_cache_init:        CPU 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
+ggml_cuda_host_malloc: failed to allocate 0.58 MiB of pinned memory: no CUDA-capable device is detected
+llama_new_context_with_model:        CPU  output buffer size =     0.58 MiB
+ggml_cuda_host_malloc: failed to allocate 299.75 MiB of pinned memory: no CUDA-capable device is detected
+llama_new_context_with_model:  CUDA_Host compute buffer size =   299.75 MiB
+llama_new_context_with_model: graph nodes  = 986
+llama_new_context_with_model: graph splits = 1
+
+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 132.724 ms
+compute_imatrix: computing over 128 chunks with batch_size 512
+ggml_cuda_host_malloc: failed to allocate 296.75 MiB of pinned memory: no CUDA-capable device is detected
+compute_imatrix: 1.39 seconds per pass - ETA 2.95 minutes
+[1]6.8310,[2]5.0865,[3]4.9045,[4]5.7534,[5]5.5805,[6]5.0977,[7]5.6114,[8]5.8680,[9]6.4515,
+save_imatrix: stored collected data after 10 chunks in Qwen2-1.5B-IMat-GGUF/imatrix.dat
+[10]6.1249,[11]5.9925,[12]6.4407,[13]7.0994,[14]7.3519,[15]7.9053,[16]8.2930,[17]8.3769,[18]8.8281,[19]8.5072,
+save_imatrix: stored collected data after 20 chunks in Qwen2-1.5B-IMat-GGUF/imatrix.dat
+[20]8.6061,[21]8.6876,[22]8.6361,[23]8.5178,[24]8.7923,[25]8.9344,[26]8.8643,[27]9.1011,[28]9.3344,[29]9.6089,
+save_imatrix: stored collected data after 30 chunks in Qwen2-1.5B-IMat-GGUF/imatrix.dat
+[30]9.4937,[31]9.1482,[32]8.7634,[33]8.5299,[34]8.3876,[35]8.2342,[36]8.2597,[37]8.3609,[38]8.4612,[39]8.4937,
+save_imatrix: stored collected data after 40 chunks in Qwen2-1.5B-IMat-GGUF/imatrix.dat
+[40]8.6398,[41]8.6845,[42]9.0562,[43]9.4092,[44]9.7224,[45]9.9733,[46]10.1141,[47]9.9399,[48]9.9791,[49]10.0713,
+save_imatrix: stored collected data after 50 chunks in Qwen2-1.5B-IMat-GGUF/imatrix.dat
+[50]10.1292,[51]10.0033,[52]10.0878,[53]10.2782,[54]10.3869,[55]10.4997,[56]10.5322,[57]10.5581,[58]10.5937,[59]10.5862,
+save_imatrix: stored collected data after 60 chunks in Qwen2-1.5B-IMat-GGUF/imatrix.dat
+[60]10.5942,[61]10.5091,[62]10.4544,[63]10.5051,[64]10.5805,[65]10.5179,[66]10.5171,[67]10.5130,[68]10.4356,[69]10.3929,
+save_imatrix: stored collected data after 70 chunks in Qwen2-1.5B-IMat-GGUF/imatrix.dat
+[70]10.3745,[71]10.3297,[72]10.3021,[73]10.3111,[74]10.2226,[75]10.1434,[76]10.0614,[77]10.0333,[78]10.0192,[79]9.9961,
+save_imatrix: stored collected data after 80 chunks in Qwen2-1.5B-IMat-GGUF/imatrix.dat
+[80]9.9322,[81]9.9510,[82]9.9338,[83]9.8650,[84]9.9019,[85]9.9247,[86]9.8608,[87]9.8144,[88]9.7875,[89]9.8041,
+save_imatrix: stored collected data after 90 chunks in Qwen2-1.5B-IMat-GGUF/imatrix.dat
+[90]9.8123,[91]9.7907,[92]9.6967,[93]9.6038,[94]9.5072,[95]9.4135,[96]9.3363,[97]9.2462,[98]9.1638,[99]9.1250,
+save_imatrix: stored collected data after 100 chunks in Qwen2-1.5B-IMat-GGUF/imatrix.dat
+[100]9.1297,[101]9.1536,[102]9.2735,[103]9.3740,[104]9.4593,[105]9.6004,[106]9.6949,[107]9.7324,[108]9.6984,[109]9.6914,
+save_imatrix: stored collected data after 110 chunks in Qwen2-1.5B-IMat-GGUF/imatrix.dat
+[110]9.6954,[111]9.6790,[112]9.6371,[113]9.6607,[114]9.7115,[115]9.7024,[116]9.7042,[117]9.7184,[118]9.7535,[119]9.7425,
+save_imatrix: stored collected data after 120 chunks in Qwen2-1.5B-IMat-GGUF/imatrix.dat
+[120]9.7342,[121]9.7356,[122]9.6908,[123]9.7388,[124]9.8151,[125]9.8718,[126]9.9517,[127]10.0170,[128]10.0816,
+save_imatrix: stored collected data after 128 chunks in Qwen2-1.5B-IMat-GGUF/imatrix.dat
+
+llama_print_timings:        load time =    1724.51 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 =  200282.33 ms / 65536 tokens (    3.06 ms per token,   327.22 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 =  201514.46 ms / 65537 tokens
+
+Final estimate: PPL = 10.0816 +/- 0.14686