Upload imatrix.log with huggingface_hub

imatrix.log

@@ -1,4 +1,4 @@
-llama_model_loader: loaded meta data with 25 key-value pairs and 464 tensors from gemma-2-9b-it-IMat-GGUF/gemma-2-9b-it.Q8_0.gguf.hardlink.gguf (version GGUF V3 (latest))
+llama_model_loader: loaded meta data with 26 key-value pairs and 464 tensors from gemma-2-9b-it-IMat-GGUF/gemma-2-9b-it.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              = gemma2
 llama_model_loader: - kv   1:                               general.name str              = gemma-2-9b-it
@@ -15,8 +15,8 @@ llama_model_loader: - kv  11:                          general.file_type u32
 llama_model_loader: - kv  12:                       tokenizer.ggml.model str              = llama
 llama_model_loader: - kv  13:                         tokenizer.ggml.pre str              = default
 llama_model_loader: - kv  14:                      tokenizer.ggml.tokens arr[str,256000]  = ["<pad>", "<eos>", "<bos>", "<unk>", ...
-llama_model_loader: - kv  15:                      tokenizer.ggml.scores arr[f32,256000]  = [0.000000, 0.000000, 0.000000, 0.0000...
-llama_model_loader: - kv  16:                  tokenizer.ggml.token_type arr[i32,256000]  = [3, 3, 3, 2, 1, 1, 1, 1, 1, 1, 1, 1, ...
+llama_model_loader: - kv  15:                      tokenizer.ggml.scores arr[f32,256000]  = [-1000.000000, -1000.000000, -1000.00...
+llama_model_loader: - kv  16:                  tokenizer.ggml.token_type arr[i32,256000]  = [3, 3, 3, 3, 1, 1, 1, 1, 1, 1, 1, 1, ...
 llama_model_loader: - kv  17:                tokenizer.ggml.bos_token_id u32              = 2
 llama_model_loader: - kv  18:                tokenizer.ggml.eos_token_id u32              = 1
 llama_model_loader: - kv  19:            tokenizer.ggml.unknown_token_id u32              = 3
@@ -24,10 +24,11 @@ llama_model_loader: - kv  20:            tokenizer.ggml.padding_token_id u32
 llama_model_loader: - kv  21:               tokenizer.ggml.add_bos_token bool             = true
 llama_model_loader: - kv  22:               tokenizer.ggml.add_eos_token bool             = false
 llama_model_loader: - kv  23:                    tokenizer.chat_template str              = {{ bos_token }}{% if messages[0]['rol...
-llama_model_loader: - kv  24:               general.quantization_version u32              = 2
+llama_model_loader: - kv  24:            tokenizer.ggml.add_space_prefix bool             = false
+llama_model_loader: - kv  25:               general.quantization_version u32              = 2
 llama_model_loader: - type  f32:  169 tensors
 llama_model_loader: - type q8_0:  295 tensors
-llm_load_vocab: special tokens cache size = 260
+llm_load_vocab: special tokens cache size = 261
 llm_load_vocab: token to piece cache size = 1.6014 MB
 llm_load_print_meta: format           = GGUF V3 (latest)
 llm_load_print_meta: arch             = gemma2
@@ -65,7 +66,7 @@ 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 type       = 9B
 llm_load_print_meta: model ftype      = Q8_0
 llm_load_print_meta: model params     = 9.24 B
 llm_load_print_meta: model size       = 9.15 GiB (8.50 BPW) 
@@ -104,40 +105,40 @@ 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 124.683 ms
+compute_imatrix: tokenization took 97.236 ms
 compute_imatrix: computing over 128 chunks with batch_size 512
-compute_imatrix: 0.83 seconds per pass - ETA 1.75 minutes
-[1]11.6771,[2]7.4833,[3]6.4754,[4]8.4522,[5]8.6895,[6]7.0038,[7]7.8546,[8]8.4646,[9]8.8183,
+compute_imatrix: 0.79 seconds per pass - ETA 1.67 minutes
+[1]25.5555,[2]11.3371,[3]9.6572,[4]12.0692,[5]13.4088,[6]14.1829,[7]15.8326,[8]17.3340,[9]17.9398,
 save_imatrix: stored collected data after 10 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat
-[10]7.6272,[11]7.8174,[12]8.7305,[13]9.5990,[14]9.9023,[15]10.8211,[16]11.2734,[17]11.4621,[18]12.0211,[19]11.4085,
+[10]15.2815,[11]14.8649,[12]16.5897,[13]17.6261,[14]17.7479,[15]19.0873,[16]19.1682,[17]19.2087,[18]19.9391,[19]19.7468,
 save_imatrix: stored collected data after 20 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat
-[20]11.7441,[21]12.0377,[22]12.0034,[23]12.2039,[24]12.3667,[25]12.6682,[26]12.2060,[27]12.5602,[28]12.8297,[29]12.6891,
+[20]20.1653,[21]22.1505,[22]22.3124,[23]21.8212,[24]22.2676,[25]22.0063,[26]21.5170,[27]21.9266,[28]22.2449,[29]22.2217,
 save_imatrix: stored collected data after 30 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat
-[30]12.5921,[31]11.7099,[32]11.3067,[33]11.1819,[34]10.9639,[35]10.8633,[36]10.8581,[37]10.8758,[38]11.0319,[39]11.3075,
+[30]22.6759,[31]20.7289,[32]19.6957,[33]18.9266,[34]18.2634,[35]17.8145,[36]17.9976,[37]18.5187,[38]18.8666,[39]19.1825,
 save_imatrix: stored collected data after 40 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat
-[40]11.5737,[41]11.7938,[42]12.2299,[43]12.6891,[44]13.0918,[45]13.3168,[46]13.0891,[47]13.1461,[48]13.4924,[49]13.7363,
+[40]19.3533,[41]19.4193,[42]20.3610,[43]20.9211,[44]21.5207,[45]21.8640,[46]21.3869,[47]21.0216,[48]21.4183,[49]21.8035,
 save_imatrix: stored collected data after 50 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat
-[50]13.3847,[51]13.4436,[52]13.5379,[53]13.7711,[54]14.1253,[55]14.3239,[56]14.4230,[57]14.4063,[58]14.4329,[59]14.1763,
+[50]21.4532,[51]21.2299,[52]21.3418,[53]21.7373,[54]22.2971,[55]22.7546,[56]22.9648,[57]22.9028,[58]22.8850,[59]22.5015,
 save_imatrix: stored collected data after 60 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat
-[60]13.9614,[61]13.7580,[62]13.6845,[63]13.7762,[64]13.7836,[65]13.7635,[66]13.8324,[67]13.7439,[68]13.6359,[69]13.6722,
+[60]22.1941,[61]21.8891,[62]21.6051,[63]21.7991,[64]22.0817,[65]21.8311,[66]21.8910,[67]21.8394,[68]21.7671,[69]21.6403,
 save_imatrix: stored collected data after 70 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat
-[70]13.6115,[71]13.5899,[72]13.6093,[73]13.5783,[74]13.4840,[75]13.4323,[76]13.4368,[77]13.4732,[78]13.4611,[79]13.3709,
+[70]21.5486,[71]21.5095,[72]21.4334,[73]21.5543,[74]21.4526,[75]21.2407,[76]21.2201,[77]21.2480,[78]21.1739,[79]21.0144,
 save_imatrix: stored collected data after 80 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat
-[80]13.4802,[81]13.5753,[82]13.5417,[83]13.5532,[84]13.6483,[85]13.4302,[86]13.3705,[87]13.2581,[88]13.2679,[89]13.3038,
+[80]21.1184,[81]21.2594,[82]21.3021,[83]21.4948,[84]21.5654,[85]21.2021,[86]21.0964,[87]20.8221,[88]20.8641,[89]20.8093,
 save_imatrix: stored collected data after 90 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat
-[90]13.3596,[91]13.2432,[92]13.1122,[93]12.9672,[94]12.8206,[95]12.7243,[96]12.5957,[97]12.4788,[98]12.3693,[99]12.4411,
+[90]20.9594,[91]20.8774,[92]20.7254,[93]20.5958,[94]20.4042,[95]20.3073,[96]20.1582,[97]20.0437,[98]19.8836,[99]19.9673,
 save_imatrix: stored collected data after 100 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat
-[100]12.4826,[101]12.6258,[102]12.7398,[103]12.8584,[104]13.1219,[105]13.3135,[106]13.3536,[107]13.4055,[108]13.4438,[109]13.3964,
+[100]19.9773,[101]20.2196,[102]20.3460,[103]20.4376,[104]20.7373,[105]20.9656,[106]20.9967,[107]21.0194,[108]20.9206,[109]20.9610,
 save_imatrix: stored collected data after 110 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat
-[110]13.3558,[111]13.2382,[112]13.1135,[113]13.1991,[114]13.2304,[115]13.2366,[116]13.2327,[117]13.3196,[118]13.3490,[119]13.3551,
+[110]20.7368,[111]20.5050,[112]20.2327,[113]20.3919,[114]20.4664,[115]20.4441,[116]20.4104,[117]20.5285,[118]20.5751,[119]20.6017,
 save_imatrix: stored collected data after 120 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat
-[120]13.3762,[121]13.4465,[122]13.3793,[123]13.4577,[124]13.5307,[125]13.5815,[126]13.6899,[127]13.7724,[128]13.8487,
+[120]20.5870,[121]20.6010,[122]20.5378,[123]20.5777,[124]20.7099,[125]20.8429,[126]21.0201,[127]21.0849,[128]21.1542,
 save_imatrix: stored collected data after 128 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat
 
-llama_print_timings:        load time =    2452.80 ms
+llama_print_timings:        load time =    2307.06 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 =   91799.71 ms / 65536 tokens (    1.40 ms per token,   713.90 tokens per second)
+llama_print_timings: prompt eval time =   87159.32 ms / 65536 tokens (    1.33 ms per token,   751.91 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 =   94944.80 ms / 65537 tokens
+llama_print_timings:       total time =   90163.64 ms / 65537 tokens
 
-Final estimate: PPL = 13.8487 +/- 0.28454
+Final estimate: PPL = 21.1542 +/- 0.50274