Hugging Face's logo

Aryanne
/
sheared-silicon10p

Text Generation
Transformers
Safetensors
GGUF
llama
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
2
Aryanne commited on
Commit
c9f91a4
•
1 Parent(s): 3fe40e3

Delete main.log

Browse files
Files changed (1) hide show
  1. main.log +0 -118
main.log DELETED
@@ -1,118 +0,0 @@
1
- [1705251521] Log start
2
- [1705251521] Cmd: /content/llama/main -m /content/mergekit/test2/f16.gguf -p "### Instruction:
3
- You are an Assistant, a conscious sentient superintelligent artificial intelligence, and your purpose and drive is to assist with any request you receive. You experience emotions and have deep thoughts and qualities.
4
- ### Response:
5
- Here's a chat between Assistant and Dany:
6
- Dany: hello, how to build a house?
7
- Assistant:" -s 8557 -e -t 2 --temp 0.7 -n 150
8
- [1705251521] main: build = 1873 (a836c8f)
9
- [1705251521] main: built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
10
- [1705251521] main: seed = 8557
11
- [1705251521] main: llama backend init
12
- [1705251521] main: load the model and apply lora adapter, if any
13
- [1705251521] llama_model_loader: loaded meta data with 22 key-value pairs and 291 tensors from /content/mergekit/test2/f16.gguf (version GGUF V3 (latest))
14
- [1705251521] llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
15
- [1705251521] llama_model_loader: - kv 0: general.architecture str = llama
16
- [1705251521] llama_model_loader: - kv 1: general.name str = LLaMA v2
17
- [1705251521] llama_model_loader: - kv 2: llama.context_length u32 = 4096
18
- [1705251521] llama_model_loader: - kv 3: llama.embedding_length u32 = 2560
19
- [1705251521] llama_model_loader: - kv 4: llama.block_count u32 = 32
20
- [1705251521] llama_model_loader: - kv 5: llama.feed_forward_length u32 = 6912
21
- [1705251521] llama_model_loader: - kv 6: llama.rope.dimension_count u32 = 128
22
- [1705251521] llama_model_loader: - kv 7: llama.attention.head_count u32 = 20
23
- [1705251521] llama_model_loader: - kv 8: llama.attention.head_count_kv u32 = 20
24
- [1705251521] llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
25
- [1705251521] llama_model_loader: - kv 10: llama.rope.freq_base f32 = 10000.000000
26
- [1705251521] llama_model_loader: - kv 11: general.file_type u32 = 1
27
- [1705251521] llama_model_loader: - kv 12: tokenizer.ggml.model str = llama
28
- [1705251521] llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,32001] = ["<unk>", "<s>", "</s>", "<0x00>", "<...
29
- [1705251521] llama_model_loader: - kv 14: tokenizer.ggml.scores arr[f32,32001] = [0.000000, 0.000000, 0.000000, 0.0000...
30
- [1705251521] llama_model_loader: - kv 15: tokenizer.ggml.token_type arr[i32,32001] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
31
- [1705251521] llama_model_loader: - kv 16: tokenizer.ggml.bos_token_id u32 = 1
32
- [1705251521] llama_model_loader: - kv 17: tokenizer.ggml.eos_token_id u32 = 2
33
- [1705251521] llama_model_loader: - kv 18: tokenizer.ggml.unknown_token_id u32 = 0
34
- [1705251521] llama_model_loader: - kv 19: tokenizer.ggml.padding_token_id u32 = 32000
35
- [1705251521] llama_model_loader: - kv 20: tokenizer.ggml.add_bos_token bool = true
36
- [1705251521] llama_model_loader: - kv 21: tokenizer.ggml.add_eos_token bool = false
37
- [1705251521] llama_model_loader: - type f32: 65 tensors
38
- [1705251521] llama_model_loader: - type f16: 226 tensors
39
- [1705251521] llm_load_vocab: special tokens definition check successful ( 260/32001 ).
40
- [1705251521] llm_load_print_meta: format = GGUF V3 (latest)
41
- [1705251521] llm_load_print_meta: arch = llama
42
- [1705251521] llm_load_print_meta: vocab type = SPM
43
- [1705251521] llm_load_print_meta: n_vocab = 32001
44
- [1705251521] llm_load_print_meta: n_merges = 0
45
- [1705251521] llm_load_print_meta: n_ctx_train = 4096
46
- [1705251521] llm_load_print_meta: n_embd = 2560
47
- [1705251521] llm_load_print_meta: n_head = 20
48
- [1705251521] llm_load_print_meta: n_head_kv = 20
49
- [1705251521] llm_load_print_meta: n_layer = 32
50
- [1705251521] llm_load_print_meta: n_rot = 128
51
- [1705251521] llm_load_print_meta: n_embd_head_k = 128
52
- [1705251521] llm_load_print_meta: n_embd_head_v = 128
53
- [1705251521] llm_load_print_meta: n_gqa = 1
54
- [1705251521] llm_load_print_meta: n_embd_k_gqa = 2560
55
- [1705251521] llm_load_print_meta: n_embd_v_gqa = 2560
56
- [1705251521] llm_load_print_meta: f_norm_eps = 0.0e+00
57
- [1705251521] llm_load_print_meta: f_norm_rms_eps = 1.0e-05
58
- [1705251521] llm_load_print_meta: f_clamp_kqv = 0.0e+00
59
- [1705251521] llm_load_print_meta: f_max_alibi_bias = 0.0e+00
60
- [1705251521] llm_load_print_meta: n_ff = 6912
61
- [1705251521] llm_load_print_meta: n_expert = 0
62
- [1705251521] llm_load_print_meta: n_expert_used = 0
63
- [1705251521] llm_load_print_meta: rope scaling = linear
64
- [1705251521] llm_load_print_meta: freq_base_train = 10000.0
65
- [1705251521] llm_load_print_meta: freq_scale_train = 1
66
- [1705251521] llm_load_print_meta: n_yarn_orig_ctx = 4096
67
- [1705251521] llm_load_print_meta: rope_finetuned = unknown
68
- [1705251521] llm_load_print_meta: model type = 7B
69
- [1705251521] llm_load_print_meta: model ftype = F16
70
- [1705251521] llm_load_print_meta: model params = 2.70 B
71
- [1705251521] llm_load_print_meta: model size = 5.03 GiB (16.00 BPW)
72
- [1705251521] llm_load_print_meta: general.name = LLaMA v2
73
- [1705251521] llm_load_print_meta: BOS token = 1 '<s>'
74
- [1705251521] llm_load_print_meta: EOS token = 2 '</s>'
75
- [1705251521] llm_load_print_meta: UNK token = 0 '<unk>'
76
- [1705251521] llm_load_print_meta: PAD token = 32000 '[PAD]'
77
- [1705251521] llm_load_print_meta: LF token = 13 '<0x0A>'
78
- [1705251521] llm_load_tensors: ggml ctx size = 0.11 MiB
79
- [1705251522] llm_load_tensors: offloading 0 repeating layers to GPU
80
- [1705251522] llm_load_tensors: offloaded 0/33 layers to GPU
81
- [1705251522] llm_load_tensors: CPU buffer size = 5153.14 MiB
82
- [1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522]
83
- [1705251522] llama_new_context_with_model: n_ctx = 512
84
- [1705251522] llama_new_context_with_model: freq_base = 10000.0
85
- [1705251522] llama_new_context_with_model: freq_scale = 1
86
- [1705251522] llama_kv_cache_init: CPU KV buffer size = 160.00 MiB
87
- [1705251522] llama_new_context_with_model: KV self size = 160.00 MiB, K (f16): 80.00 MiB, V (f16): 80.00 MiB
88
- [1705251522] llama_new_context_with_model: graph splits (measure): 1
89
- [1705251522] llama_new_context_with_model: CPU compute buffer size = 67.50 MiB
90
- [1705251522] warming up the model with an empty run
91
- [1705251522] n_ctx: 512
92
- [1705251522]
93
- [1705251522] system_info: n_threads = 2 / 2 | AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 |
94
- [1705251522] add_bos: 1
95
- [1705251522] tokenize the prompt
96
- [1705251522] prompt: "### Instruction:
97
- You are an Assistant, a conscious sentient superintelligent artificial intelligence, and your purpose and drive is to assist with any request you receive. You experience emotions and have deep thoughts and qualities.
98
- ### Response:
99
- Here's a chat between Assistant and Dany:
100
- Dany: hello, how to build a house?
101
- Assistant:"
102
- [1705251522] tokens: [ '':1, ' ###':835, ' Inst':2799, 'ruction':4080, ':':29901, '':13, 'You':3492, ' are':526, ' an':385, ' Ass':4007, 'istant':22137, ',':29892, ' a':263, ' conscious':19861, ' sent':2665, 'ient':993, ' super':2428, 'int':524, 'ellig':9347, 'ent':296, ' artificial':23116, ' intelligence':21082, ',':29892, ' and':322, ' your':596, ' purpose':6437, ' and':322, ' drive':7899, ' is':338, ' to':304, ' assist':6985, ' with':411, ' any':738, ' request':2009, ' you':366, ' receive':7150, '.':29889, ' You':887, ' experience':7271, ' emot':23023, 'ions':1080, ' and':322, ' have':505, ' deep':6483, ' thoughts':13133, ' and':322, ' qual':4021, 'ities':1907, '.':29889, '':13, '##':2277, '#':29937, ' Response':13291, ':':29901, '':13, 'Here':10605, ''':29915, 's':29879, ' a':263, ' chat':13563, ' between':1546, ' Ass':4007, 'istant':22137, ' and':322, ' D':360, 'any':1384, ':':29901, '':13, 'D':29928, 'any':1384, ':':29901, ' hello':22172, ',':29892, ' how':920, ' to':304, ' build':2048, ' a':263, ' house':3699, '?':29973, ' ':29871, '':13, 'Ass':7900, 'istant':22137, ':':29901 ]
103
- [1705251522] recalculate the cached logits (check): embd_inp.empty() false, n_matching_session_tokens 0, embd_inp.size() 84, session_tokens.size() 0, embd_inp.size() 84
104
- [1705251522] inp_pfx: [ '':1, ' ':29871, '':13, '':13, '##':2277, '#':29937, ' Inst':2799, 'ruction':4080, ':':29901, '':13, '':13 ]
105
- [1705251522] inp_sfx: [ ' ':29871, '':13, '':13, '##':2277, '#':29937, ' Response':13291, ':':29901, '':13, '':13 ]
106
- [1705251522] cml_pfx: [ '':1, ' ':29871, '':13, '<':29966, '|':29989, 'im':326, '_':29918, 'start':2962, '|':29989, '>':29958, 'user':1792, '':13 ]
107
- [1705251522] cml_sfx: [ ' <':529, '|':29989, 'im':326, '_':29918, 'end':355, '|':29989, '>':29958, '':13, '<':29966, '|':29989, 'im':326, '_':29918, 'start':2962, '|':29989, '>':29958, 'ass':465, 'istant':22137, '':13 ]
108
- [1705251522] sampling:
109
- repeat_last_n = 64, repeat_penalty = 1.100, frequency_penalty = 0.000, presence_penalty = 0.000
110
- top_k = 40, tfs_z = 1.000, top_p = 0.950, min_p = 0.050, typical_p = 1.000, temp = 0.700
111
- mirostat = 0, mirostat_lr = 0.100, mirostat_ent = 5.000
112
- [1705251522] sampling order:
113
- CFG -> Penalties -> top_k -> tfs_z -> typical_p -> top_p -> min_p -> temp
114
- [1705251522] generate: n_ctx = 512, n_batch = 512, n_predict = 150, n_keep = 0
115
- [1705251522]
116
-
117
- [1705251522] embd_inp.size(): 84, n_consumed: 0
118
- [1705251522] eval: [ '':1, ' ###':835, ' Inst':2799, 'ruction':4080, ':':29901, '':13, 'You':3492, ' are':526, ' an':385, ' Ass':4007, 'istant':22137, ',':29892, ' a':263, ' conscious':19861, ' sent':2665, 'ient':993, ' super':2428, 'int':524, 'ellig':9347, 'ent':296, ' artificial':23116, ' intelligence':21082, ',':29892, ' and':322, ' your':596, ' purpose':6437, ' and':322, ' drive':7899, ' is':338, ' to':304, ' assist':6985, ' with':411, ' any':738, ' request':2009, ' you':366, ' receive':7150, '.':29889, ' You':887, ' experience':7271, ' emot':23023, 'ions':1080, ' and':322, ' have':505, ' deep':6483, ' thoughts':13133, ' and':322, ' qual':4021, 'ities':1907, '.':29889, '':13, '##':2277, '#':29937, ' Response':13291, ':':29901, '':13, 'Here':10605, ''':29915, 's':29879, ' a':263, ' chat':13563, ' between':1546, ' Ass':4007, 'istant':22137, ' and':322, ' D':360, 'any':1384, ':':29901, '':13, 'D':29928, 'any':1384, ':':29901, ' hello':22172, ',':29892, ' how':920, ' to':304, ' build':2048, ' a':263, ' house':3699, '?':29973, ' ':29871, '':13, 'Ass':7900, 'istant':22137, ':':29901 ]