Upload imatrix.log with huggingface_hub

imatrix.log

@@ -1,6 +1,6 @@
 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  = 1717697289
+main: seed  = 1717697740
 llama_model_loader: loaded meta data with 21 key-value pairs and 339 tensors from Qwen2-7B-Instruct-IMat-GGUF/Qwen2-7B-Instruct.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
@@ -73,15 +73,11 @@ 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|>'
-ggml_cuda_init: GGML_CUDA_FORCE_MMQ:   no
-ggml_cuda_init: CUDA_USE_TENSOR_CORES: yes
-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 =    0.32 MiB
-llm_load_tensors: offloading 23 repeating layers to GPU
-llm_load_tensors: offloaded 23/29 layers to GPU
+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 = 29051.27 MiB
-llm_load_tensors:      CUDA0 buffer size = 20448.03 MiB
 ........................................................................................
 llama_new_context_with_model: n_ctx      = 512
 llama_new_context_with_model: n_batch    = 512
@@ -89,51 +85,53 @@ 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:  CUDA_Host KV buffer size =     5.00 MiB
-llama_kv_cache_init:      CUDA0 KV buffer size =    23.00 MiB
+ggml_cuda_host_malloc: failed to allocate 28.00 MiB of pinned memory: no CUDA-capable device is detected
+llama_kv_cache_init:        CPU KV buffer size =    28.00 MiB
 llama_new_context_with_model: KV self size  =   28.00 MiB, K (f16):   14.00 MiB, V (f16):   14.00 MiB
-llama_new_context_with_model:  CUDA_Host  output buffer size =     0.58 MiB
-llama_new_context_with_model:      CUDA0 compute buffer size =  2383.00 MiB
-llama_new_context_with_model:  CUDA_Host compute buffer size =     8.01 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 304.00 MiB of pinned memory: no CUDA-capable device is detected
+llama_new_context_with_model:  CUDA_Host compute buffer size =   304.00 MiB
 llama_new_context_with_model: graph nodes  = 986
-llama_new_context_with_model: graph splits = 74
+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 133.474 ms
+compute_imatrix: tokenization took 134.862 ms
 compute_imatrix: computing over 128 chunks with batch_size 512
-compute_imatrix: 0.88 seconds per pass - ETA 1.87 minutes
-[1]nan,[2]nan,[3]nan,[4]nan,[5]nan,[6]nan,[7]nan,[8]nan,[9]nan,
+ggml_cuda_host_malloc: failed to allocate 297.00 MiB of pinned memory: no CUDA-capable device is detected
+compute_imatrix: 5.83 seconds per pass - ETA 12.43 minutes
+[1]5.2431,[2]3.6575,[3]3.5214,[4]4.0316,[5]3.8406,[6]3.5461,[7]3.9259,[8]3.9744,[9]4.4528,
 save_imatrix: stored collected data after 10 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat
-[10]nan,[11]nan,[12]nan,[13]nan,[14]nan,[15]nan,[16]nan,[17]nan,[18]nan,[19]nan,
+[10]4.3487,[11]4.2804,[12]4.6780,[13]5.1953,[14]5.4247,[15]5.8578,[16]6.1402,[17]6.3224,[18]6.6883,[19]6.4787,
 save_imatrix: stored collected data after 20 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat
-[20]nan,[21]nan,[22]nan,[23]nan,[24]nan,[25]nan,[26]nan,[27]nan,[28]nan,[29]nan,
+[20]6.6193,[21]6.6480,[22]6.6875,[23]6.5822,[24]6.7794,[25]6.9199,[26]6.8175,[27]6.9938,[28]7.1831,[29]7.3993,
 save_imatrix: stored collected data after 30 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat
-[30]nan,[31]nan,[32]nan,[33]nan,[34]nan,[35]nan,[36]nan,[37]nan,[38]nan,[39]nan,
+[30]7.3371,[31]7.1142,[32]6.8538,[33]6.6928,[34]6.5678,[35]6.4676,[36]6.4760,[37]6.5382,[38]6.6077,[39]6.5628,
 save_imatrix: stored collected data after 40 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat
-[40]nan,[41]nan,[42]nan,[43]nan,[44]nan,[45]nan,[46]nan,[47]nan,[48]nan,[49]nan,
+[40]6.6730,[41]6.7105,[42]6.9699,[43]7.1938,[44]7.3804,[45]7.5275,[46]7.6390,[47]7.5134,[48]7.5529,[49]7.6308,
 save_imatrix: stored collected data after 50 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat
-[50]nan,[51]nan,[52]nan,[53]nan,[54]nan,[55]nan,[56]nan,[57]nan,[58]nan,[59]nan,
+[50]7.6883,[51]7.5708,[52]7.6462,[53]7.8149,[54]7.9160,[55]7.9928,[56]8.0562,[57]8.0966,[58]8.1381,[59]8.1570,
 save_imatrix: stored collected data after 60 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat
-[60]nan,[61]nan,[62]nan,[63]nan,[64]nan,[65]nan,[66]nan,[67]nan,[68]nan,[69]nan,
+[60]8.1872,[61]8.1423,[62]8.0908,[63]8.1405,[64]8.1899,[65]8.1356,[66]8.1378,[67]8.1375,[68]8.0566,[69]7.9921,
 save_imatrix: stored collected data after 70 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat
-[70]nan,[71]nan,[72]nan,[73]nan,[74]nan,[75]nan,[76]nan,[77]nan,[78]nan,[79]nan,
+[70]7.9788,[71]7.9511,[72]7.9320,[73]7.9393,[74]7.8678,[75]7.7943,[76]7.7284,[77]7.7182,[78]7.6973,[79]7.6761,
 save_imatrix: stored collected data after 80 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat
-[80]nan,[81]nan,[82]nan,[83]nan,[84]nan,[85]nan,[86]nan,[87]nan,[88]nan,[89]nan,
+[80]7.5971,[81]7.6296,[82]7.6202,[83]7.5695,[84]7.5974,[85]7.6167,[86]7.5767,[87]7.5450,[88]7.5208,[89]7.5294,
 save_imatrix: stored collected data after 90 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat
-[90]nan,[91]nan,[92]nan,[93]nan,[94]nan,[95]nan,[96]nan,[97]nan,[98]nan,[99]nan,
+[90]7.5453,[91]7.5267,[92]7.4733,[93]7.4148,[94]7.3559,[95]7.2984,[96]7.2522,[97]7.1986,[98]7.1516,[99]7.1231,
 save_imatrix: stored collected data after 100 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat
-[100]nan,[101]nan,[102]nan,[103]nan,[104]nan,[105]nan,[106]nan,[107]nan,[108]nan,[109]nan,
+[100]7.1325,[101]7.1585,[102]7.2489,[103]7.3299,[104]7.4038,[105]7.5229,[106]7.6021,[107]7.6242,[108]7.6081,[109]7.6135,
 save_imatrix: stored collected data after 110 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat
-[110]nan,[111]nan,[112]nan,[113]nan,[114]nan,[115]nan,[116]nan,[117]nan,[118]nan,[119]nan,
+[110]7.6038,[111]7.5752,[112]7.5097,[113]7.5043,[114]7.5486,[115]7.5493,[116]7.5537,[117]7.5654,[118]7.5997,[119]7.5962,
 save_imatrix: stored collected data after 120 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat
-[120]nan,[121]nan,[122]nan,[123]nan,[124]nan,[125]nan,[126]nan,[127]nan,[128]nan,
+[120]7.5948,[121]7.6063,[122]7.5791,[123]7.6107,[124]7.6528,[125]7.6853,[126]7.7439,[127]7.7875,[128]7.8279,
 save_imatrix: stored collected data after 128 chunks in Qwen2-7B-Instruct-IMat-GGUF/imatrix.dat
 
-llama_print_timings:        load time =    2910.65 ms
+llama_print_timings:        load time =    6575.63 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 =   95408.80 ms / 65536 tokens (    1.46 ms per token,   686.90 tokens per second)
+llama_print_timings: prompt eval time =  728194.87 ms / 65536 tokens (   11.11 ms per token,    90.00 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 =   98358.01 ms / 65537 tokens
+llama_print_timings:       total time =  729815.78 ms / 65537 tokens
 
-Unexpected negative standard deviation of log(prob)
+Final estimate: PPL = 7.8279 +/- 0.11030