Hugging Face's logo

legraphista
/
K2-ckpt_360-IMat-GGUF

Text Generation
GGUF
English
nlp
llm
quantized
GGUF
imatrix
quantization
imat
static
16bit
8bit
6bit
5bit
4bit
3bit
2bit
1bit
Model card Files Community
legraphista commited on
Commit
32d83d1
•
1 Parent(s): a887c33

Upload imatrix.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. imatrix.log +156 -0
imatrix.log ADDED
@@ -0,0 +1,156 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ main: build = 3058 (30e238b2)
2
+ main: built with cc (Ubuntu 13.2.0-23ubuntu4) 13.2.0 for x86_64-linux-gnu
3
+ main: seed = 1717202742
4
+ llama_model_loader: additional 2 GGUFs metadata loaded.
5
+ llama_model_loader: loaded meta data with 28 key-value pairs and 723 tensors from K2-ckpt_360.Q8_0/K2-ckpt_360.Q8_0-00001-of-00003.gguf (version GGUF V3 (latest))
6
+ llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
7
+ llama_model_loader: - kv 0: general.architecture str = llama
8
+ llama_model_loader: - kv 1: general.name str = K2-ckpt_360
9
+ llama_model_loader: - kv 2: llama.block_count u32 = 80
10
+ llama_model_loader: - kv 3: llama.context_length u32 = 2048
11
+ llama_model_loader: - kv 4: llama.embedding_length u32 = 8192
12
+ llama_model_loader: - kv 5: llama.feed_forward_length u32 = 22016
13
+ llama_model_loader: - kv 6: llama.attention.head_count u32 = 64
14
+ llama_model_loader: - kv 7: llama.attention.head_count_kv u32 = 64
15
+ llama_model_loader: - kv 8: llama.rope.freq_base f32 = 10000.000000
16
+ llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
17
+ llama_model_loader: - kv 10: general.file_type u32 = 7
18
+ llama_model_loader: - kv 11: llama.vocab_size u32 = 32032
19
+ llama_model_loader: - kv 12: llama.rope.dimension_count u32 = 128
20
+ llama_model_loader: - kv 13: tokenizer.ggml.model str = llama
21
+ llama_model_loader: - kv 14: tokenizer.ggml.pre str = default
22
+ llama_model_loader: - kv 15: tokenizer.ggml.tokens arr[str,32032] = ["<unk>", "<s>", "</s>", "<0x00>", "<...
23
+ llama_model_loader: - kv 16: tokenizer.ggml.scores arr[f32,32032] = [0.000000, 0.000000, 0.000000, 0.0000...
24
+ llama_model_loader: - kv 17: tokenizer.ggml.token_type arr[i32,32032] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
25
+ llama_model_loader: - kv 18: tokenizer.ggml.bos_token_id u32 = 2
26
+ llama_model_loader: - kv 19: tokenizer.ggml.eos_token_id u32 = 2
27
+ llama_model_loader: - kv 20: tokenizer.ggml.unknown_token_id u32 = 0
28
+ llama_model_loader: - kv 21: tokenizer.ggml.padding_token_id u32 = 0
29
+ llama_model_loader: - kv 22: tokenizer.ggml.add_bos_token bool = false
30
+ llama_model_loader: - kv 23: tokenizer.ggml.add_eos_token bool = false
31
+ llama_model_loader: - kv 24: general.quantization_version u32 = 2
32
+ llama_model_loader: - kv 25: split.no u16 = 0
33
+ llama_model_loader: - kv 26: split.count u16 = 3
34
+ llama_model_loader: - kv 27: split.tensors.count i32 = 723
35
+ llama_model_loader: - type f32: 161 tensors
36
+ llama_model_loader: - type q8_0: 562 tensors
37
+ llm_load_vocab: special tokens cache size = 291
38
+ llm_load_vocab: token to piece cache size = 0.3373 MB
39
+ llm_load_print_meta: format = GGUF V3 (latest)
40
+ llm_load_print_meta: arch = llama
41
+ llm_load_print_meta: vocab type = SPM
42
+ llm_load_print_meta: n_vocab = 32032
43
+ llm_load_print_meta: n_merges = 0
44
+ llm_load_print_meta: n_ctx_train = 2048
45
+ llm_load_print_meta: n_embd = 8192
46
+ llm_load_print_meta: n_head = 64
47
+ llm_load_print_meta: n_head_kv = 64
48
+ llm_load_print_meta: n_layer = 80
49
+ llm_load_print_meta: n_rot = 128
50
+ llm_load_print_meta: n_embd_head_k = 128
51
+ llm_load_print_meta: n_embd_head_v = 128
52
+ llm_load_print_meta: n_gqa = 1
53
+ llm_load_print_meta: n_embd_k_gqa = 8192
54
+ llm_load_print_meta: n_embd_v_gqa = 8192
55
+ llm_load_print_meta: f_norm_eps = 0.0e+00
56
+ llm_load_print_meta: f_norm_rms_eps = 1.0e-05
57
+ llm_load_print_meta: f_clamp_kqv = 0.0e+00
58
+ llm_load_print_meta: f_max_alibi_bias = 0.0e+00
59
+ llm_load_print_meta: f_logit_scale = 0.0e+00
60
+ llm_load_print_meta: n_ff = 22016
61
+ llm_load_print_meta: n_expert = 0
62
+ llm_load_print_meta: n_expert_used = 0
63
+ llm_load_print_meta: causal attn = 1
64
+ llm_load_print_meta: pooling type = 0
65
+ llm_load_print_meta: rope type = 0
66
+ llm_load_print_meta: rope scaling = linear
67
+ llm_load_print_meta: freq_base_train = 10000.0
68
+ llm_load_print_meta: freq_scale_train = 1
69
+ llm_load_print_meta: n_yarn_orig_ctx = 2048
70
+ llm_load_print_meta: rope_finetuned = unknown
71
+ llm_load_print_meta: ssm_d_conv = 0
72
+ llm_load_print_meta: ssm_d_inner = 0
73
+ llm_load_print_meta: ssm_d_state = 0
74
+ llm_load_print_meta: ssm_dt_rank = 0
75
+ llm_load_print_meta: model type = 65B
76
+ llm_load_print_meta: model ftype = Q8_0
77
+ llm_load_print_meta: model params = 65.29 B
78
+ llm_load_print_meta: model size = 64.61 GiB (8.50 BPW)
79
+ llm_load_print_meta: general.name = K2-ckpt_360
80
+ llm_load_print_meta: BOS token = 2 '</s>'
81
+ llm_load_print_meta: EOS token = 2 '</s>'
82
+ llm_load_print_meta: UNK token = 0 '<unk>'
83
+ llm_load_print_meta: PAD token = 0 '<unk>'
84
+ llm_load_print_meta: LF token = 13 '<0x0A>'
85
+ ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
86
+ ggml_cuda_init: CUDA_USE_TENSOR_CORES: yes
87
+ ggml_cuda_init: found 1 CUDA devices:
88
+ Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9, VMM: yes
89
+ llm_load_tensors: ggml ctx size = 0.74 MiB
90
+ llm_load_tensors: offloading 20 repeating layers to GPU
91
+ llm_load_tensors: offloaded 20/81 layers to GPU
92
+ llm_load_tensors: CPU buffer size = 24509.70 MiB
93
+ llm_load_tensors: CPU buffer size = 24426.62 MiB
94
+ llm_load_tensors: CPU buffer size = 17220.48 MiB
95
+ llm_load_tensors: CUDA0 buffer size = 16406.25 MiB
96
+ ....................................................................................................
97
+ llama_new_context_with_model: n_ctx = 512
98
+ llama_new_context_with_model: n_batch = 512
99
+ llama_new_context_with_model: n_ubatch = 512
100
+ llama_new_context_with_model: flash_attn = 0
101
+ llama_new_context_with_model: freq_base = 10000.0
102
+ llama_new_context_with_model: freq_scale = 1
103
+ llama_kv_cache_init: CUDA_Host KV buffer size = 960.00 MiB
104
+ llama_kv_cache_init: CUDA0 KV buffer size = 320.00 MiB
105
+ llama_new_context_with_model: KV self size = 1280.00 MiB, K (f16): 640.00 MiB, V (f16): 640.00 MiB
106
+ llama_new_context_with_model: CUDA_Host output buffer size = 0.12 MiB
107
+ llama_new_context_with_model: CUDA0 compute buffer size = 344.45 MiB
108
+ llama_new_context_with_model: CUDA_Host compute buffer size = 33.01 MiB
109
+ llama_new_context_with_model: graph nodes = 2566
110
+ llama_new_context_with_model: graph splits = 664
111
+
112
+ system_info: n_threads = 32 / 32 | AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | 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 |
113
+ compute_imatrix: tokenizing the input ..
114
+ compute_imatrix: tokenization took 90.613 ms
115
+ compute_imatrix: computing over 151 chunks with batch_size 512
116
+ compute_imatrix: 54.64 seconds per pass - ETA 2 hours 17.50 minutes
117
+ [1]2.5539,[2]2.1725,[3]2.2401,[4]2.3300,[5]2.6606,[6]2.6351,[7]2.4401,[8]2.7931,[9]2.9649,
118
+ save_imatrix: stored collected data after 10 chunks in K2-ckpt_360-IMat-GGUF/imatrix.dat
119
+ [10]3.1688,[11]3.2642,[12]3.0681,[13]3.1229,[14]3.3242,[15]3.6052,[16]3.7343,[17]3.9537,[18]4.1038,[19]4.2571,
120
+ save_imatrix: stored collected data after 20 chunks in K2-ckpt_360-IMat-GGUF/imatrix.dat
121
+ [20]4.3761,[21]4.4609,[22]4.3091,[23]4.1686,[24]4.1532,[25]4.1627,[26]4.1712,[27]4.1575,[28]4.2221,[29]4.3438,
122
+ save_imatrix: stored collected data after 30 chunks in K2-ckpt_360-IMat-GGUF/imatrix.dat
123
+ [30]4.4658,[31]4.4285,[32]4.4013,[33]4.4066,[34]4.4415,[35]4.4515,[36]4.4150,[37]4.2677,[38]4.1633,[39]4.1454,
124
+ save_imatrix: stored collected data after 40 chunks in K2-ckpt_360-IMat-GGUF/imatrix.dat
125
+ [40]4.1309,[41]4.1052,[42]4.1051,[43]4.0700,[44]4.0656,[45]4.0514,[46]4.0371,[47]4.0569,[48]4.1215,[49]4.1808,
126
+ save_imatrix: stored collected data after 50 chunks in K2-ckpt_360-IMat-GGUF/imatrix.dat
127
+ [50]4.2053,[51]4.2157,[52]4.2462,[53]4.3301,[54]4.3998,[55]4.4450,[56]4.4333,[57]4.4086,[58]4.4343,[59]4.4672,
128
+ save_imatrix: stored collected data after 60 chunks in K2-ckpt_360-IMat-GGUF/imatrix.dat
129
+ [60]4.5250,[61]4.4823,[62]4.5074,[63]4.5355,[64]4.5937,[65]4.6457,[66]4.6640,[67]4.7075,[68]4.7445,[69]4.7587,
130
+ save_imatrix: stored collected data after 70 chunks in K2-ckpt_360-IMat-GGUF/imatrix.dat
131
+ [70]4.7712,[71]4.7811,[72]4.7778,[73]4.7534,[74]4.7181,[75]4.7263,[76]4.7284,[77]4.7388,[78]4.7089,[79]4.7126,
132
+ save_imatrix: stored collected data after 80 chunks in K2-ckpt_360-IMat-GGUF/imatrix.dat
133
+ [80]4.7190,[81]4.6978,[82]4.6902,[83]4.6675,[84]4.6722,[85]4.6693,[86]4.6627,[87]4.6610,[88]4.6630,[89]4.6458,
134
+ save_imatrix: stored collected data after 90 chunks in K2-ckpt_360-IMat-GGUF/imatrix.dat
135
+ [90]4.6360,[91]4.6361,[92]4.6215,[93]4.6015,[94]4.5871,[95]4.5457,[96]4.5578,[97]4.5484,[98]4.5443,[99]4.5292,
136
+ save_imatrix: stored collected data after 100 chunks in K2-ckpt_360-IMat-GGUF/imatrix.dat
137
+ [100]4.5199,[101]4.5321,[102]4.5079,[103]4.4911,[104]4.4818,[105]4.4947,[106]4.5010,[107]4.5164,[108]4.5313,[109]4.4987,
138
+ save_imatrix: stored collected data after 110 chunks in K2-ckpt_360-IMat-GGUF/imatrix.dat
139
+ [110]4.4669,[111]4.4338,[112]4.4028,[113]4.3726,[114]4.3421,[115]4.3136,[116]4.2847,[117]4.2740,[118]4.2853,[119]4.2989,
140
+ save_imatrix: stored collected data after 120 chunks in K2-ckpt_360-IMat-GGUF/imatrix.dat
141
+ [120]4.3347,[121]4.3653,[122]4.4021,[123]4.4374,[124]4.4908,[125]4.5376,[126]4.5504,[127]4.5590,[128]4.5281,[129]4.5314,
142
+ save_imatrix: stored collected data after 130 chunks in K2-ckpt_360-IMat-GGUF/imatrix.dat
143
+ [130]4.5324,[131]4.5179,[132]4.4969,[133]4.4791,[134]4.4977,[135]4.5185,[136]4.5240,[137]4.5240,[138]4.5372,[139]4.5527,
144
+ save_imatrix: stored collected data after 140 chunks in K2-ckpt_360-IMat-GGUF/imatrix.dat
145
+ [140]4.5666,[141]4.5727,[142]4.5798,[143]4.5811,[144]4.5694,[145]4.5811,[146]4.5913,[147]4.5950,[148]4.6098,[149]4.6184,
146
+ save_imatrix: stored collected data after 150 chunks in K2-ckpt_360-IMat-GGUF/imatrix.dat
147
+ [150]4.6283,[151]4.6390,
148
+ save_imatrix: stored collected data after 151 chunks in K2-ckpt_360-IMat-GGUF/imatrix.dat
149
+
150
+ llama_print_timings: load time = 80625.37 ms
151
+ llama_print_timings: sample time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
152
+ llama_print_timings: prompt eval time = 5710379.48 ms / 77312 tokens ( 73.86 ms per token, 13.54 tokens per second)
153
+ llama_print_timings: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
154
+ llama_print_timings: total time = 5750793.99 ms / 77313 tokens
155
+
156
+ Final estimate: PPL = 4.6390 +/- 0.05047