Hugging Face's logo

legraphista
/
neo_7b_sft_v0.1-IMat-GGUF

Text Generation
GGUF
quantized
GGUF
imatrix
quantization
imat
static
16bit
8bit
6bit
5bit
4bit
3bit
2bit
1bit
conversational
Model card Files Community
legraphista commited on
Commit
063d3bc
•
1 Parent(s): 8475138

Upload imatrix.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. imatrix.log +145 -0
imatrix.log ADDED
@@ -0,0 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ main: build = 3051 (5921b8f0)
2
+ main: built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
3
+ main: seed = 1717152257
4
+ llama_model_loader: loaded meta data with 24 key-value pairs and 255 tensors from neo_7b_sft_v0.1-IMat-GGUF/neo_7b_sft_v0.1.gguf (version GGUF V3 (latest))
5
+ llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
6
+ llama_model_loader: - kv 0: general.architecture str = llama
7
+ llama_model_loader: - kv 1: general.name str = neo_7b_sft_v0.1
8
+ llama_model_loader: - kv 2: llama.block_count u32 = 28
9
+ llama_model_loader: - kv 3: llama.context_length u32 = 8192
10
+ llama_model_loader: - kv 4: llama.embedding_length u32 = 3072
11
+ llama_model_loader: - kv 5: llama.feed_forward_length u32 = 24576
12
+ llama_model_loader: - kv 6: llama.attention.head_count u32 = 16
13
+ llama_model_loader: - kv 7: llama.attention.head_count_kv u32 = 16
14
+ llama_model_loader: - kv 8: llama.rope.freq_base f32 = 10000.000000
15
+ llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
16
+ llama_model_loader: - kv 10: general.file_type u32 = 0
17
+ llama_model_loader: - kv 11: llama.vocab_size u32 = 64256
18
+ llama_model_loader: - kv 12: llama.rope.dimension_count u32 = 192
19
+ llama_model_loader: - kv 13: tokenizer.ggml.model str = llama
20
+ llama_model_loader: - kv 14: tokenizer.ggml.pre str = default
21
+ llama_model_loader: - kv 15: tokenizer.ggml.tokens arr[str,64256] = ["<unk>", "<s>", "</s>", "<0x00>", "<...
22
+ llama_model_loader: - kv 16: tokenizer.ggml.scores arr[f32,64256] = [0.000000, 0.000000, 0.000000, 0.0000...
23
+ llama_model_loader: - kv 17: tokenizer.ggml.token_type arr[i32,64256] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
24
+ llama_model_loader: - kv 18: tokenizer.ggml.bos_token_id u32 = 1
25
+ llama_model_loader: - kv 19: tokenizer.ggml.eos_token_id u32 = 2
26
+ llama_model_loader: - kv 20: tokenizer.ggml.add_bos_token bool = false
27
+ llama_model_loader: - kv 21: tokenizer.ggml.add_eos_token bool = false
28
+ llama_model_loader: - kv 22: tokenizer.chat_template str = {% set system_message = 'You are a he...
29
+ llama_model_loader: - kv 23: general.quantization_version u32 = 2
30
+ llama_model_loader: - type f32: 255 tensors
31
+ llm_load_vocab: special tokens cache size = 515
32
+ llm_load_vocab: token to piece cache size = 0.7263 MB
33
+ llm_load_print_meta: format = GGUF V3 (latest)
34
+ llm_load_print_meta: arch = llama
35
+ llm_load_print_meta: vocab type = SPM
36
+ llm_load_print_meta: n_vocab = 64256
37
+ llm_load_print_meta: n_merges = 0
38
+ llm_load_print_meta: n_ctx_train = 8192
39
+ llm_load_print_meta: n_embd = 3072
40
+ llm_load_print_meta: n_head = 16
41
+ llm_load_print_meta: n_head_kv = 16
42
+ llm_load_print_meta: n_layer = 28
43
+ llm_load_print_meta: n_rot = 192
44
+ llm_load_print_meta: n_embd_head_k = 192
45
+ llm_load_print_meta: n_embd_head_v = 192
46
+ llm_load_print_meta: n_gqa = 1
47
+ llm_load_print_meta: n_embd_k_gqa = 3072
48
+ llm_load_print_meta: n_embd_v_gqa = 3072
49
+ llm_load_print_meta: f_norm_eps = 0.0e+00
50
+ llm_load_print_meta: f_norm_rms_eps = 1.0e-05
51
+ llm_load_print_meta: f_clamp_kqv = 0.0e+00
52
+ llm_load_print_meta: f_max_alibi_bias = 0.0e+00
53
+ llm_load_print_meta: f_logit_scale = 0.0e+00
54
+ llm_load_print_meta: n_ff = 24576
55
+ llm_load_print_meta: n_expert = 0
56
+ llm_load_print_meta: n_expert_used = 0
57
+ llm_load_print_meta: causal attn = 1
58
+ llm_load_print_meta: pooling type = 0
59
+ llm_load_print_meta: rope type = 0
60
+ llm_load_print_meta: rope scaling = linear
61
+ llm_load_print_meta: freq_base_train = 10000.0
62
+ llm_load_print_meta: freq_scale_train = 1
63
+ llm_load_print_meta: n_yarn_orig_ctx = 8192
64
+ llm_load_print_meta: rope_finetuned = unknown
65
+ llm_load_print_meta: ssm_d_conv = 0
66
+ llm_load_print_meta: ssm_d_inner = 0
67
+ llm_load_print_meta: ssm_d_state = 0
68
+ llm_load_print_meta: ssm_dt_rank = 0
69
+ llm_load_print_meta: model type = ?B
70
+ llm_load_print_meta: model ftype = all F32
71
+ llm_load_print_meta: model params = 7.79 B
72
+ llm_load_print_meta: model size = 29.03 GiB (32.00 BPW)
73
+ llm_load_print_meta: general.name = neo_7b_sft_v0.1
74
+ llm_load_print_meta: BOS token = 1 '<s>'
75
+ llm_load_print_meta: EOS token = 2 '</s>'
76
+ llm_load_print_meta: UNK token = 0 '<unk>'
77
+ llm_load_print_meta: LF token = 13 '<0x0A>'
78
+ ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
79
+ ggml_cuda_init: CUDA_USE_TENSOR_CORES: yes
80
+ ggml_cuda_init: found 1 CUDA devices:
81
+ Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9, VMM: yes
82
+ llm_load_tensors: ggml ctx size = 0.26 MiB
83
+ llm_load_tensors: offloading 22 repeating layers to GPU
84
+ llm_load_tensors: offloaded 22/29 layers to GPU
85
+ llm_load_tensors: CPU buffer size = 29730.67 MiB
86
+ llm_load_tensors: CUDA0 buffer size = 22176.52 MiB
87
+ .................................................................................................
88
+ llama_new_context_with_model: n_ctx = 512
89
+ llama_new_context_with_model: n_batch = 512
90
+ llama_new_context_with_model: n_ubatch = 512
91
+ llama_new_context_with_model: flash_attn = 0
92
+ llama_new_context_with_model: freq_base = 10000.0
93
+ llama_new_context_with_model: freq_scale = 1
94
+ llama_kv_cache_init: CUDA_Host KV buffer size = 36.00 MiB
95
+ llama_kv_cache_init: CUDA0 KV buffer size = 132.00 MiB
96
+ llama_new_context_with_model: KV self size = 168.00 MiB, K (f16): 84.00 MiB, V (f16): 84.00 MiB
97
+ llama_new_context_with_model: CUDA_Host output buffer size = 0.25 MiB
98
+ llama_new_context_with_model: CUDA0 compute buffer size = 884.50 MiB
99
+ llama_new_context_with_model: CUDA_Host compute buffer size = 13.01 MiB
100
+ llama_new_context_with_model: graph nodes = 902
101
+ llama_new_context_with_model: graph splits = 70
102
+
103
+ 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 |
104
+ compute_imatrix: tokenizing the input ..
105
+ compute_imatrix: tokenization took 94.53 ms
106
+ compute_imatrix: computing over 149 chunks with batch_size 512
107
+ compute_imatrix: 0.92 seconds per pass - ETA 2.28 minutes
108
+ [1]6.9087,[2]4.9464,[3]5.5776,[4]5.6370,[5]5.4654,[6]5.4102,[7]4.7098,[8]4.8687,[9]4.9457,
109
+ save_imatrix: stored collected data after 10 chunks in neo_7b_sft_v0.1-IMat-GGUF/imatrix.dat
110
+ [10]5.3631,[11]5.3031,[12]4.9517,[13]5.3067,[14]5.7762,[15]6.0604,[16]6.5393,[17]6.8275,[18]7.0775,[19]7.2396,
111
+ save_imatrix: stored collected data after 20 chunks in neo_7b_sft_v0.1-IMat-GGUF/imatrix.dat
112
+ [20]7.6090,[21]7.3325,[22]7.3046,[23]7.4432,[24]7.6053,[25]7.5198,[26]7.4926,[27]7.6715,[28]7.9040,[29]8.1177,
113
+ save_imatrix: stored collected data after 30 chunks in neo_7b_sft_v0.1-IMat-GGUF/imatrix.dat
114
+ [30]8.1330,[31]8.2365,[32]8.3080,[33]8.3659,[34]8.2829,[35]8.1805,[36]7.8166,[37]7.6196,[38]7.2773,[39]7.2020,
115
+ save_imatrix: stored collected data after 40 chunks in neo_7b_sft_v0.1-IMat-GGUF/imatrix.dat
116
+ [40]7.1117,[41]7.0423,[42]7.0131,[43]7.0513,[44]7.0433,[45]6.9766,[46]7.0585,[47]7.1493,[48]7.3117,[49]7.3431,
117
+ save_imatrix: stored collected data after 50 chunks in neo_7b_sft_v0.1-IMat-GGUF/imatrix.dat
118
+ [50]7.5558,[51]7.7420,[52]7.9529,[53]8.1337,[54]8.2862,[55]8.2058,[56]8.2031,[57]8.3415,[58]8.4436,[59]8.4034,
119
+ save_imatrix: stored collected data after 60 chunks in neo_7b_sft_v0.1-IMat-GGUF/imatrix.dat
120
+ [60]8.3390,[61]8.3636,[62]8.4492,[63]8.5299,[64]8.6364,[65]8.7142,[66]8.7962,[67]8.8080,[68]8.8470,[69]8.8577,
121
+ save_imatrix: stored collected data after 70 chunks in neo_7b_sft_v0.1-IMat-GGUF/imatrix.dat
122
+ [70]8.8172,[71]8.7114,[72]8.5987,[73]8.5845,[74]8.6847,[75]8.7115,[76]8.6591,[77]8.6226,[78]8.6239,[79]8.5747,
123
+ save_imatrix: stored collected data after 80 chunks in neo_7b_sft_v0.1-IMat-GGUF/imatrix.dat
124
+ [80]8.4730,[81]8.2890,[82]8.1267,[83]8.1267,[84]8.1288,[85]8.1302,[86]8.0806,[87]8.0983,[88]8.0851,[89]8.0748,
125
+ save_imatrix: stored collected data after 90 chunks in neo_7b_sft_v0.1-IMat-GGUF/imatrix.dat
126
+ [90]8.0567,[91]8.0261,[92]8.0150,[93]7.9759,[94]7.8792,[95]7.9289,[96]7.9894,[97]8.0096,[98]7.9770,[99]7.9935,
127
+ save_imatrix: stored collected data after 100 chunks in neo_7b_sft_v0.1-IMat-GGUF/imatrix.dat
128
+ [100]8.0289,[101]7.9490,[102]7.8935,[103]7.8883,[104]7.9199,[105]7.9198,[106]7.9549,[107]7.9926,[108]7.9428,[109]7.8852,
129
+ save_imatrix: stored collected data after 110 chunks in neo_7b_sft_v0.1-IMat-GGUF/imatrix.dat
130
+ [110]7.8331,[111]7.7686,[112]7.6997,[113]7.6362,[114]7.5856,[115]7.5369,[116]7.5122,[117]7.5222,[118]7.5262,[119]7.6019,
131
+ save_imatrix: stored collected data after 120 chunks in neo_7b_sft_v0.1-IMat-GGUF/imatrix.dat
132
+ [120]7.6779,[121]7.7421,[122]7.8017,[123]7.8961,[124]7.8799,[125]7.9118,[126]7.8995,[127]7.9356,[128]7.9227,[129]7.9105,
133
+ save_imatrix: stored collected data after 130 chunks in neo_7b_sft_v0.1-IMat-GGUF/imatrix.dat
134
+ [130]7.8760,[131]7.8445,[132]7.8829,[133]7.9431,[134]7.9423,[135]7.9438,[136]7.9568,[137]7.9834,[138]7.9895,[139]7.9990,
135
+ save_imatrix: stored collected data after 140 chunks in neo_7b_sft_v0.1-IMat-GGUF/imatrix.dat
136
+ [140]8.0310,[141]8.0578,[142]8.0334,[143]8.0987,[144]8.1383,[145]8.1734,[146]8.2294,[147]8.2535,[148]8.3020,[149]8.3237,
137
+ save_imatrix: stored collected data after 149 chunks in neo_7b_sft_v0.1-IMat-GGUF/imatrix.dat
138
+
139
+ llama_print_timings: load time = 3161.43 ms
140
+ llama_print_timings: sample time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
141
+ llama_print_timings: prompt eval time = 124844.08 ms / 76288 tokens ( 1.64 ms per token, 611.07 tokens per second)
142
+ llama_print_timings: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
143
+ llama_print_timings: total time = 127790.46 ms / 76289 tokens
144
+
145
+ Final estimate: PPL = 8.3237 +/- 0.12004