Hugging Face's logo

legraphista
/
Meta-Llama-3.1-8B-Instruct-IMat-GGUF

Text Generation
GGUF
PyTorch
facebook
meta
llama
llama-3
quantized
GGUF
quantization
imat
imatrix
static
16bit
8bit
6bit
5bit
4bit
3bit
2bit
1bit
conversational
Model card Files Community
legraphista commited on
Commit
3c931d6
•
1 Parent(s): cf02d73

Upload imatrix.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. imatrix.log +147 -0
imatrix.log ADDED
@@ -0,0 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ llama_model_loader: loaded meta data with 29 key-value pairs and 292 tensors from Meta-Llama-3.1-8B-Instruct-IMat-GGUF/Meta-Llama-3.1-8B-Instruct.Q8_0.gguf.hardlink.gguf (version GGUF V3 (latest))
2
+ llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
3
+ llama_model_loader: - kv 0: general.architecture str = llama
4
+ llama_model_loader: - kv 1: general.type str = model
5
+ llama_model_loader: - kv 2: general.name str = Meta Llama 3.1 8B Instruct
6
+ llama_model_loader: - kv 3: general.finetune str = Instruct
7
+ llama_model_loader: - kv 4: general.basename str = Meta-Llama-3.1
8
+ llama_model_loader: - kv 5: general.size_label str = 8B
9
+ llama_model_loader: - kv 6: general.license str = llama3.1
10
+ llama_model_loader: - kv 7: general.tags arr[str,6] = ["facebook", "meta", "pytorch", "llam...
11
+ llama_model_loader: - kv 8: general.languages arr[str,8] = ["en", "de", "fr", "it", "pt", "hi", ...
12
+ llama_model_loader: - kv 9: llama.block_count u32 = 32
13
+ llama_model_loader: - kv 10: llama.context_length u32 = 131072
14
+ llama_model_loader: - kv 11: llama.embedding_length u32 = 4096
15
+ llama_model_loader: - kv 12: llama.feed_forward_length u32 = 14336
16
+ llama_model_loader: - kv 13: llama.attention.head_count u32 = 32
17
+ llama_model_loader: - kv 14: llama.attention.head_count_kv u32 = 8
18
+ llama_model_loader: - kv 15: llama.rope.freq_base f32 = 500000.000000
19
+ llama_model_loader: - kv 16: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
20
+ llama_model_loader: - kv 17: general.file_type u32 = 7
21
+ llama_model_loader: - kv 18: llama.vocab_size u32 = 128256
22
+ llama_model_loader: - kv 19: llama.rope.dimension_count u32 = 128
23
+ llama_model_loader: - kv 20: tokenizer.ggml.model str = gpt2
24
+ llama_model_loader: - kv 21: tokenizer.ggml.pre str = llama-bpe
25
+ llama_model_loader: - kv 22: tokenizer.ggml.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ...
26
+ llama_model_loader: - kv 23: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
27
+ llama_model_loader: - kv 24: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
28
+ llama_model_loader: - kv 25: tokenizer.ggml.bos_token_id u32 = 128000
29
+ llama_model_loader: - kv 26: tokenizer.ggml.eos_token_id u32 = 128009
30
+ llama_model_loader: - kv 27: tokenizer.chat_template str = {% set loop_messages = messages %}{% ...
31
+ llama_model_loader: - kv 28: general.quantization_version u32 = 2
32
+ llama_model_loader: - type f32: 66 tensors
33
+ llama_model_loader: - type q8_0: 226 tensors
34
+ llm_load_vocab: special tokens cache size = 256
35
+ llm_load_vocab: token to piece cache size = 0.7999 MB
36
+ llm_load_print_meta: format = GGUF V3 (latest)
37
+ llm_load_print_meta: arch = llama
38
+ llm_load_print_meta: vocab type = BPE
39
+ llm_load_print_meta: n_vocab = 128256
40
+ llm_load_print_meta: n_merges = 280147
41
+ llm_load_print_meta: vocab_only = 0
42
+ llm_load_print_meta: n_ctx_train = 131072
43
+ llm_load_print_meta: n_embd = 4096
44
+ llm_load_print_meta: n_layer = 32
45
+ llm_load_print_meta: n_head = 32
46
+ llm_load_print_meta: n_head_kv = 8
47
+ llm_load_print_meta: n_rot = 128
48
+ llm_load_print_meta: n_swa = 0
49
+ llm_load_print_meta: n_embd_head_k = 128
50
+ llm_load_print_meta: n_embd_head_v = 128
51
+ llm_load_print_meta: n_gqa = 4
52
+ llm_load_print_meta: n_embd_k_gqa = 1024
53
+ llm_load_print_meta: n_embd_v_gqa = 1024
54
+ llm_load_print_meta: f_norm_eps = 0.0e+00
55
+ llm_load_print_meta: f_norm_rms_eps = 1.0e-05
56
+ llm_load_print_meta: f_clamp_kqv = 0.0e+00
57
+ llm_load_print_meta: f_max_alibi_bias = 0.0e+00
58
+ llm_load_print_meta: f_logit_scale = 0.0e+00
59
+ llm_load_print_meta: n_ff = 14336
60
+ llm_load_print_meta: n_expert = 0
61
+ llm_load_print_meta: n_expert_used = 0
62
+ llm_load_print_meta: causal attn = 1
63
+ llm_load_print_meta: pooling type = 0
64
+ llm_load_print_meta: rope type = 0
65
+ llm_load_print_meta: rope scaling = linear
66
+ llm_load_print_meta: freq_base_train = 500000.0
67
+ llm_load_print_meta: freq_scale_train = 1
68
+ llm_load_print_meta: n_ctx_orig_yarn = 131072
69
+ llm_load_print_meta: rope_finetuned = unknown
70
+ llm_load_print_meta: ssm_d_conv = 0
71
+ llm_load_print_meta: ssm_d_inner = 0
72
+ llm_load_print_meta: ssm_d_state = 0
73
+ llm_load_print_meta: ssm_dt_rank = 0
74
+ llm_load_print_meta: model type = 8B
75
+ llm_load_print_meta: model ftype = Q8_0
76
+ llm_load_print_meta: model params = 8.03 B
77
+ llm_load_print_meta: model size = 7.95 GiB (8.50 BPW)
78
+ llm_load_print_meta: general.name = Meta Llama 3.1 8B Instruct
79
+ llm_load_print_meta: BOS token = 128000 '<|begin_of_text|>'
80
+ llm_load_print_meta: EOS token = 128009 '<|eot_id|>'
81
+ llm_load_print_meta: LF token = 128 'Ä'
82
+ llm_load_print_meta: EOT token = 128009 '<|eot_id|>'
83
+ llm_load_print_meta: max token length = 256
84
+ ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
85
+ ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
86
+ ggml_cuda_init: found 1 CUDA devices:
87
+ Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9, VMM: yes
88
+ llm_load_tensors: ggml ctx size = 0.27 MiB
89
+ llm_load_tensors: offloading 32 repeating layers to GPU
90
+ llm_load_tensors: offloading non-repeating layers to GPU
91
+ llm_load_tensors: offloaded 33/33 layers to GPU
92
+ llm_load_tensors: CPU buffer size = 532.31 MiB
93
+ llm_load_tensors: CUDA0 buffer size = 7605.34 MiB
94
+ .........................................................................................
95
+ llama_new_context_with_model: n_ctx = 512
96
+ llama_new_context_with_model: n_batch = 512
97
+ llama_new_context_with_model: n_ubatch = 512
98
+ llama_new_context_with_model: flash_attn = 0
99
+ llama_new_context_with_model: freq_base = 500000.0
100
+ llama_new_context_with_model: freq_scale = 1
101
+ llama_kv_cache_init: CUDA0 KV buffer size = 64.00 MiB
102
+ llama_new_context_with_model: KV self size = 64.00 MiB, K (f16): 32.00 MiB, V (f16): 32.00 MiB
103
+ llama_new_context_with_model: CUDA_Host output buffer size = 0.49 MiB
104
+ llama_new_context_with_model: CUDA0 compute buffer size = 258.50 MiB
105
+ llama_new_context_with_model: CUDA_Host compute buffer size = 9.01 MiB
106
+ llama_new_context_with_model: graph nodes = 1030
107
+ llama_new_context_with_model: graph splits = 2
108
+
109
+ 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 |
110
+ compute_imatrix: tokenizing the input ..
111
+ compute_imatrix: tokenization took 40.567 ms
112
+ compute_imatrix: computing over 125 chunks with batch_size 512
113
+ compute_imatrix: 0.67 seconds per pass - ETA 1.40 minutes
114
+ [1]5.6450,[2]4.4702,[3]4.0740,[4]5.0229,[5]5.2037,[6]4.4021,[7]4.6701,[8]5.1378,[9]5.3205,
115
+ save_imatrix: stored collected data after 10 chunks in Meta-Llama-3.1-8B-Instruct-IMat-GGUF/imatrix.dat
116
+ [10]4.8485,[11]5.2853,[12]5.7849,[13]6.2502,[14]6.6483,[15]6.9530,[16]7.2090,[17]7.3963,[18]7.1322,[19]6.8074,
117
+ save_imatrix: stored collected data after 20 chunks in Meta-Llama-3.1-8B-Instruct-IMat-GGUF/imatrix.dat
118
+ [20]6.7943,[21]6.9043,[22]6.8396,[23]7.1398,[24]7.1030,[25]7.4353,[26]7.4332,[27]7.4675,[28]7.7040,[29]7.7057,
119
+ save_imatrix: stored collected data after 30 chunks in Meta-Llama-3.1-8B-Instruct-IMat-GGUF/imatrix.dat
120
+ [30]7.6655,[31]7.2633,[32]6.8970,[33]6.7255,[34]6.5763,[35]6.6251,[36]6.6641,[37]6.5966,[38]6.6691,[39]6.8314,
121
+ save_imatrix: stored collected data after 40 chunks in Meta-Llama-3.1-8B-Instruct-IMat-GGUF/imatrix.dat
122
+ [40]6.9164,[41]6.9534,[42]7.0537,[43]7.2634,[44]7.3427,[45]7.5240,[46]7.4093,[47]7.5276,[48]7.6077,[49]7.7031,
123
+ save_imatrix: stored collected data after 50 chunks in Meta-Llama-3.1-8B-Instruct-IMat-GGUF/imatrix.dat
124
+ [50]7.5974,[51]7.6994,[52]7.8264,[53]7.9057,[54]7.9634,[55]8.0354,[56]8.0725,[57]8.1231,[58]8.1399,[59]8.1486,
125
+ save_imatrix: stored collected data after 60 chunks in Meta-Llama-3.1-8B-Instruct-IMat-GGUF/imatrix.dat
126
+ [60]8.1036,[61]8.0840,[62]8.1257,[63]8.1674,[64]8.0841,[65]8.0472,[66]8.0453,[67]8.0126,[68]7.9960,[69]7.9754,
127
+ save_imatrix: stored collected data after 70 chunks in Meta-Llama-3.1-8B-Instruct-IMat-GGUF/imatrix.dat
128
+ [70]7.9684,[71]7.9568,[72]7.9475,[73]7.9085,[74]7.8517,[75]7.8432,[76]7.8412,[77]7.7991,[78]7.7869,[79]7.8144,
129
+ save_imatrix: stored collected data after 80 chunks in Meta-Llama-3.1-8B-Instruct-IMat-GGUF/imatrix.dat
130
+ [80]7.8355,[81]7.8187,[82]7.8068,[83]7.8325,[84]7.7284,[85]7.7280,[86]7.7349,[87]7.7448,[88]7.7729,[89]7.7736,
131
+ save_imatrix: stored collected data after 90 chunks in Meta-Llama-3.1-8B-Instruct-IMat-GGUF/imatrix.dat
132
+ [90]7.7163,[91]7.6404,[92]7.5762,[93]7.5210,[94]7.4600,[95]7.4064,[96]7.3665,[97]7.3742,[98]7.4158,[99]7.5038,
133
+ save_imatrix: stored collected data after 100 chunks in Meta-Llama-3.1-8B-Instruct-IMat-GGUF/imatrix.dat
134
+ [100]7.5790,[101]7.6302,[102]7.7523,[103]7.7770,[104]7.8144,[105]7.7421,[106]7.7473,[107]7.6992,[108]7.6483,[109]7.5837,
135
+ save_imatrix: stored collected data after 110 chunks in Meta-Llama-3.1-8B-Instruct-IMat-GGUF/imatrix.dat
136
+ [110]7.6274,[111]7.6830,[112]7.6914,[113]7.6846,[114]7.7188,[115]7.7524,[116]7.7605,[117]7.7820,[118]7.8124,[119]7.7604,
137
+ save_imatrix: stored collected data after 120 chunks in Meta-Llama-3.1-8B-Instruct-IMat-GGUF/imatrix.dat
138
+ [120]7.7775,[121]7.7835,[122]7.8095,[123]7.8550,[124]7.8913,[125]7.9140,
139
+ save_imatrix: stored collected data after 125 chunks in Meta-Llama-3.1-8B-Instruct-IMat-GGUF/imatrix.dat
140
+
141
+ llama_print_timings: load time = 2039.67 ms
142
+ llama_print_timings: sample time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
143
+ llama_print_timings: prompt eval time = 71215.49 ms / 64000 tokens ( 1.11 ms per token, 898.68 tokens per second)
144
+ llama_print_timings: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
145
+ llama_print_timings: total time = 73402.48 ms / 64001 tokens
146
+
147
+ Final estimate: PPL = 7.9140 +/- 0.11223