Hugging Face's logo

MaziyarPanahi
/
Mistral-Large-Instruct-2407-GGUF

Text Generation
GGUF
quantized
2-bit
3-bit
4-bit precision
5-bit
6-bit
8-bit precision
GGUF
Model card Files Community
14
MaziyarPanahi commited on
Commit
ed4c6e5
•
1 Parent(s): 92bc38e

Upload folder using huggingface_hub (#2)

Browse files

- 9d5c7a506a58e29852e7e8625a78be6c85fb60a69fdaee80514086db80211fb1 (d1179784e9e0afa83ee4a8fbd06608a07e0c042a)
- 2ab61c88b21bf88256ad560156ed5249a7e0efd655db1cb7260b8e307142275b (440a6a23326df5a85ca0a61230bfdf128554debd)
- d6b4353aac181bc0bf9954f07449aa14c4ba524986196f752e921e55950a3157 (af580c0cafe7d64227923ae9cff5d3e411bd7c2a)
- ca13154ada5ed238f54d3b129dda448d0ff3625fa510f136647ed61ef215222e (1319ad18996722a355a1ef25de8488d4ba601933)
- e7ed12650e9be9a330ac74b5490863cc3adb518d9dc247a1b57be27474fcb4c9 (619ae7a717eb0157c491837f84bfe233b7eb01cf)

Files changed (6) hide show
  1. .gitattributes +4 -0
  2. Mistral-Large-Instruct-2407.IQ1_M.gguf +3 -0
  3. Mistral-Large-Instruct-2407.IQ1_S.gguf +3 -0
  4. Mistral-Large-Instruct-2407.IQ2_XS.gguf +3 -0
  5. Mistral-Large-Instruct-2407.Q2_K.gguf +3 -0
  6. main.log +192 -0
.gitattributes CHANGED
@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ Mistral-Large-Instruct-2407.IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Mistral-Large-Instruct-2407.IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Mistral-Large-Instruct-2407.IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Mistral-Large-Instruct-2407.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
Mistral-Large-Instruct-2407.IQ1_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa215c16979664ac7c3770daf32f1dd8e654c3720f9352f2a8fc7e244db764a6
3
+ size 28386313984
Mistral-Large-Instruct-2407.IQ1_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d607e5595a22ce7746c39674d1556d85352a785fa4ef1629e129ac4b2673bb17
3
+ size 25959778048
Mistral-Large-Instruct-2407.IQ2_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7d6d45263dab502aec5b0253d4fcaa8b8bceaf5fe98dc9d245a32a158604eb7
3
+ size 36081157888
Mistral-Large-Instruct-2407.Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b27c3d07abab9ebe36a19f590b3cfd0d74cdea2a96f88ef2d7bfc546e994217
3
+ size 45196297984
main.log ADDED
@@ -0,0 +1,192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [1721889628] Log start
2
+ [1721889628] Cmd: /home/maziyar/apps/fine-tuning/quantize/gguf/llama.cpp/llama-cli -m Mistral-Large-Instruct-2407.IQ1_M.gguf -p "I have 10 apples." -n 1024 -t 40
3
+ [1721889628] main: build = 3450 (b115105f)
4
+ [1721889628] main: built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
5
+ [1721889628] main: seed = 1721889628
6
+ [1721889628] main: llama backend init
7
+ [1721889628] main: load the model and apply lora adapter, if any
8
+ [1721889628] llama_model_loader: loaded meta data with 38 key-value pairs and 795 tensors from Mistral-Large-Instruct-2407.IQ1_M.gguf (version GGUF V3 (latest))
9
+ [1721889628] llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
10
+ [1721889628] llama_model_loader: - kv 0: general.architecture str = llama
11
+ [1721889628] llama_model_loader: - kv 1: general.type str = model
12
+ [1721889628] llama_model_loader: - kv 2: general.name str = Models Mistralai Mistral Large Instru...
13
+ [1721889628] llama_model_loader: - kv 3: general.version str = 2407
14
+ [1721889628] llama_model_loader: - kv 4: general.finetune str = Instruct
15
+ [1721889628] llama_model_loader: - kv 5: general.basename str = models-mistralai-Mistral
16
+ [1721889628] llama_model_loader: - kv 6: general.size_label str = Large
17
+ [1721889628] llama_model_loader: - kv 7: general.license str = other
18
+ [1721889628] llama_model_loader: - kv 8: general.license.name str = mrl
19
+ [1721889628] llama_model_loader: - kv 9: general.license.link str = https://mistral.ai/licenses/MRL-0.1.md
20
+ [1721889628] llama_model_loader: - kv 10: general.languages arr[str,10] = ["en", "fr", "de", "es", "it", "pt", ...
21
+ [1721889628] llama_model_loader: - kv 11: llama.block_count u32 = 88
22
+ [1721889628] llama_model_loader: - kv 12: llama.context_length u32 = 32768
23
+ [1721889628] llama_model_loader: - kv 13: llama.embedding_length u32 = 12288
24
+ [1721889628] llama_model_loader: - kv 14: llama.feed_forward_length u32 = 28672
25
+ [1721889628] llama_model_loader: - kv 15: llama.attention.head_count u32 = 96
26
+ [1721889628] llama_model_loader: - kv 16: llama.attention.head_count_kv u32 = 8
27
+ [1721889628] llama_model_loader: - kv 17: llama.rope.freq_base f32 = 1000000.000000
28
+ [1721889628] llama_model_loader: - kv 18: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
29
+ [1721889628] llama_model_loader: - kv 19: general.file_type u32 = 31
30
+ [1721889628] llama_model_loader: - kv 20: llama.vocab_size u32 = 32768
31
+ [1721889628] llama_model_loader: - kv 21: llama.rope.dimension_count u32 = 128
32
+ [1721889628] llama_model_loader: - kv 22: tokenizer.ggml.add_space_prefix bool = false
33
+ [1721889628] llama_model_loader: - kv 23: tokenizer.ggml.model str = llama
34
+ [1721889628] llama_model_loader: - kv 24: tokenizer.ggml.pre str = default
35
+ [1721889628] llama_model_loader: - kv 25: tokenizer.ggml.tokens arr[str,32768] = ["<unk>", "<s>", "</s>", "[INST]", "[...
36
+ [1721889628] llama_model_loader: - kv 26: tokenizer.ggml.scores arr[f32,32768] = [-1000.000000, -1000.000000, -1000.00...
37
+ [1721889628] llama_model_loader: - kv 27: tokenizer.ggml.token_type arr[i32,32768] = [3, 3, 3, 4, 4, 4, 4, 4, 4, 4, 4, 4, ...
38
+ [1721889628] llama_model_loader: - kv 28: tokenizer.ggml.bos_token_id u32 = 1
39
+ [1721889628] llama_model_loader: - kv 29: tokenizer.ggml.eos_token_id u32 = 2
40
+ [1721889628] llama_model_loader: - kv 30: tokenizer.ggml.unknown_token_id u32 = 0
41
+ [1721889628] llama_model_loader: - kv 31: tokenizer.ggml.add_bos_token bool = true
42
+ [1721889628] llama_model_loader: - kv 32: tokenizer.ggml.add_eos_token bool = false
43
+ [1721889628] llama_model_loader: - kv 33: general.quantization_version u32 = 2
44
+ [1721889628] llama_model_loader: - kv 34: quantize.imatrix.file str = ./Mistral-Large-Instruct-2407-GGUF_im...
45
+ [1721889628] llama_model_loader: - kv 35: quantize.imatrix.dataset str = group_40.txt
46
+ [1721889628] llama_model_loader: - kv 36: quantize.imatrix.entries_count i32 = 616
47
+ [1721889628] llama_model_loader: - kv 37: quantize.imatrix.chunks_count i32 = 73
48
+ [1721889628] llama_model_loader: - type f32: 177 tensors
49
+ [1721889628] llama_model_loader: - type q2_K: 12 tensors
50
+ [1721889628] llama_model_loader: - type q4_K: 88 tensors
51
+ [1721889628] llama_model_loader: - type q5_K: 1 tensors
52
+ [1721889628] llama_model_loader: - type iq2_xxs: 88 tensors
53
+ [1721889628] llama_model_loader: - type iq1_m: 429 tensors
54
+ [1721889628] llm_load_vocab: special tokens cache size = 771
55
+ [1721889628] llm_load_vocab: token to piece cache size = 0.1732 MB
56
+ [1721889628] llm_load_print_meta: format = GGUF V3 (latest)
57
+ [1721889628] llm_load_print_meta: arch = llama
58
+ [1721889628] llm_load_print_meta: vocab type = SPM
59
+ [1721889628] llm_load_print_meta: n_vocab = 32768
60
+ [1721889628] llm_load_print_meta: n_merges = 0
61
+ [1721889628] llm_load_print_meta: vocab_only = 0
62
+ [1721889628] llm_load_print_meta: n_ctx_train = 32768
63
+ [1721889628] llm_load_print_meta: n_embd = 12288
64
+ [1721889628] llm_load_print_meta: n_layer = 88
65
+ [1721889628] llm_load_print_meta: n_head = 96
66
+ [1721889628] llm_load_print_meta: n_head_kv = 8
67
+ [1721889628] llm_load_print_meta: n_rot = 128
68
+ [1721889628] llm_load_print_meta: n_swa = 0
69
+ [1721889628] llm_load_print_meta: n_embd_head_k = 128
70
+ [1721889628] llm_load_print_meta: n_embd_head_v = 128
71
+ [1721889628] llm_load_print_meta: n_gqa = 12
72
+ [1721889628] llm_load_print_meta: n_embd_k_gqa = 1024
73
+ [1721889628] llm_load_print_meta: n_embd_v_gqa = 1024
74
+ [1721889628] llm_load_print_meta: f_norm_eps = 0.0e+00
75
+ [1721889628] llm_load_print_meta: f_norm_rms_eps = 1.0e-05
76
+ [1721889628] llm_load_print_meta: f_clamp_kqv = 0.0e+00
77
+ [1721889628] llm_load_print_meta: f_max_alibi_bias = 0.0e+00
78
+ [1721889628] llm_load_print_meta: f_logit_scale = 0.0e+00
79
+ [1721889628] llm_load_print_meta: n_ff = 28672
80
+ [1721889628] llm_load_print_meta: n_expert = 0
81
+ [1721889628] llm_load_print_meta: n_expert_used = 0
82
+ [1721889628] llm_load_print_meta: causal attn = 1
83
+ [1721889628] llm_load_print_meta: pooling type = 0
84
+ [1721889628] llm_load_print_meta: rope type = 0
85
+ [1721889628] llm_load_print_meta: rope scaling = linear
86
+ [1721889628] llm_load_print_meta: freq_base_train = 1000000.0
87
+ [1721889628] llm_load_print_meta: freq_scale_train = 1
88
+ [1721889628] llm_load_print_meta: n_ctx_orig_yarn = 32768
89
+ [1721889628] llm_load_print_meta: rope_finetuned = unknown
90
+ [1721889628] llm_load_print_meta: ssm_d_conv = 0
91
+ [1721889628] llm_load_print_meta: ssm_d_inner = 0
92
+ [1721889628] llm_load_print_meta: ssm_d_state = 0
93
+ [1721889628] llm_load_print_meta: ssm_dt_rank = 0
94
+ [1721889628] llm_load_print_meta: model type = ?B
95
+ [1721889628] llm_load_print_meta: model ftype = IQ1_M - 1.75 bpw
96
+ [1721889628] llm_load_print_meta: model params = 122.61 B
97
+ [1721889628] llm_load_print_meta: model size = 26.44 GiB (1.85 BPW)
98
+ [1721889628] llm_load_print_meta: general.name = Models Mistralai Mistral Large Instruct 2407
99
+ [1721889628] llm_load_print_meta: BOS token = 1 '<s>'
100
+ [1721889628] llm_load_print_meta: EOS token = 2 '</s>'
101
+ [1721889628] llm_load_print_meta: UNK token = 0 '<unk>'
102
+ [1721889628] llm_load_print_meta: LF token = 781 '<0x0A>'
103
+ [1721889628] llm_load_print_meta: max token length = 48
104
+ [1721889628] llm_load_tensors: ggml ctx size = 0.37 MiB
105
+ [1721889630] llm_load_tensors: CPU buffer size = 27070.55 MiB
106
+ [1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630] .[1721889630]
107
+ [1721889630] llama_new_context_with_model: n_ctx = 32768
108
+ [1721889630] llama_new_context_with_model: n_batch = 2048
109
+ [1721889630] llama_new_context_with_model: n_ubatch = 512
110
+ [1721889630] llama_new_context_with_model: flash_attn = 0
111
+ [1721889630] llama_new_context_with_model: freq_base = 1000000.0
112
+ [1721889630] llama_new_context_with_model: freq_scale = 1
113
+ [1721889637] llama_kv_cache_init: CPU KV buffer size = 11264.00 MiB
114
+ [1721889637] llama_new_context_with_model: KV self size = 11264.00 MiB, K (f16): 5632.00 MiB, V (f16): 5632.00 MiB
115
+ [1721889637] llama_new_context_with_model: CPU output buffer size = 0.13 MiB
116
+ [1721889637] llama_new_context_with_model: CPU compute buffer size = 6304.01 MiB
117
+ [1721889637] llama_new_context_with_model: graph nodes = 2822
118
+ [1721889637] llama_new_context_with_model: graph splits = 1
119
+ [1721889637] warming up the model with an empty run
120
+ [1721889643] n_ctx: 32768
121
+ [1721889643]
122
+ [1721889643] system_info: n_threads = 40 / 80 | 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 = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 |
123
+ [1721889643] add_bos: 1
124
+ [1721889643] tokenize the prompt
125
+ [1721889643] prompt: "I have 10 apples."
126
+ [1721889643] tokens: [ '<s>':1, 'I':29505, ' have':1274, ' ':29473, '1':29508, '0':29502, ' ap':1747, 'ples':3583, '.':29491 ]
127
+ [1721889643] recalculate the cached logits (check): embd_inp.empty() false, n_matching_session_tokens 0, embd_inp.size() 9, session_tokens.size() 0, embd_inp.size() 9
128
+ [1721889643] sampling:
129
+ repeat_last_n = 64, repeat_penalty = 1.000, frequency_penalty = 0.000, presence_penalty = 0.000
130
+ top_k = 40, tfs_z = 1.000, top_p = 0.950, min_p = 0.050, typical_p = 1.000, temp = 0.800
131
+ mirostat = 0, mirostat_lr = 0.100, mirostat_ent = 5.000
132
+ [1721889643] sampling order:
133
+ CFG -> Penalties -> top_k -> tfs_z -> typical_p -> top_p -> min_p -> temperature
134
+ [1721889643] generate: n_ctx = 32768, n_batch = 2048, n_predict = 1024, n_keep = 1
135
+ [1721889643]
136
+
137
+ [1721889643] embd_inp.size(): 9, n_consumed: 0
138
+ [1721889643] eval: [ '<s>':1, 'I':29505, ' have':1274, ' ':29473, '1':29508, '0':29502, ' ap':1747, 'ples':3583, '.':29491 ]
139
+ [1721889651] n_past = 9
140
+ [1721889651] last: [ '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<s>':1, 'I':29505, ' have':1274, ' ':29473, '1':29508, '0':29502, ' ap':1747, 'ples':3583, '.':29491, '':781 ]
141
+ [1721889651] n_remain: 1023
142
+ [1721889651] eval: [ '':781 ]
143
+ [1721889652] n_past = 10
144
+ [1721889652] last: [ '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<s>':1, 'I':29505, ' have':1274, ' ':29473, '1':29508, '0':29502, ' ap':1747, 'ples':3583, '.':29491, '':781, '':781 ]
145
+ [1721889652] n_remain: 1022
146
+ [1721889652] eval: [ '':781 ]
147
+ [1721889653] n_past = 11
148
+ [1721889653] last: [ '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<s>':1, 'I':29505, ' have':1274, ' ':29473, '1':29508, '0':29502, ' ap':1747, 'ples':3583, '.':29491, '':781, '':781, '1':29508 ]
149
+ [1721889653] n_remain: 1021
150
+ [1721889653] eval: [ '1':29508 ]
151
+ [1721889654] n_past = 12
152
+ [1721889654] last: [ '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<s>':1, 'I':29505, ' have':1274, ' ':29473, '1':29508, '0':29502, ' ap':1747, 'ples':3583, '.':29491, '':781, '':781, '1':29508, '0':29502 ]
153
+ [1721889654] n_remain: 1020
154
+ [1721889654] eval: [ '0':29502 ]
155
+ [1721889655] n_past = 13
156
+ [1721889655] last: [ '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<s>':1, 'I':29505, ' have':1274, ' ':29473, '1':29508, '0':29502, ' ap':1747, 'ples':3583, '.':29491, '':781, '':781, '1':29508, '0':29502, ' ap':1747 ]
157
+ [1721889655] n_remain: 1019
158
+ [1721889655] eval: [ ' ap':1747 ]
159
+ [1721889656] n_past = 14
160
+ [1721889656] last: [ '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<s>':1, 'I':29505, ' have':1274, ' ':29473, '1':29508, '0':29502, ' ap':1747, 'ples':3583, '.':29491, '':781, '':781, '1':29508, '0':29502, ' ap':1747, 'ples':3583 ]
161
+ [1721889656] n_remain: 1018
162
+ [1721889656] eval: [ 'ples':3583 ]
163
+ [1721889657] n_past = 15
164
+ [1721889657] last: [ '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<s>':1, 'I':29505, ' have':1274, ' ':29473, '1':29508, '0':29502, ' ap':1747, 'ples':3583, '.':29491, '':781, '':781, '1':29508, '0':29502, ' ap':1747, 'ples':3583, ' are':1228 ]
165
+ [1721889657] n_remain: 1017
166
+ [1721889657] eval: [ ' are':1228 ]
167
+ [1721889658] n_past = 16
168
+ [1721889658] last: [ '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<s>':1, 'I':29505, ' have':1274, ' ':29473, '1':29508, '0':29502, ' ap':1747, 'ples':3583, '.':29491, '':781, '':781, '1':29508, '0':29502, ' ap':1747, 'ples':3583, ' are':1228, ' ':29473 ]
169
+ [1721889658] n_remain: 1016
170
+ [1721889658] eval: [ ' ':29473 ]
171
+ [1721889659] n_past = 17
172
+ [1721889659] last: [ '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<s>':1, 'I':29505, ' have':1274, ' ':29473, '1':29508, '0':29502, ' ap':1747, 'ples':3583, '.':29491, '':781, '':781, '1':29508, '0':29502, ' ap':1747, 'ples':3583, ' are':1228, ' ':29473, '5':29550 ]
173
+ [1721889659] n_remain: 1015
174
+ [1721889659] eval: [ '5':29550 ]
175
+ [1721889660] n_past = 18
176
+ [1721889660] last: [ '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<s>':1, 'I':29505, ' have':1274, ' ':29473, '1':29508, '0':29502, ' ap':1747, 'ples':3583, '.':29491, '':781, '':781, '1':29508, '0':29502, ' ap':1747, 'ples':3583, ' are':1228, ' ':29473, '5':29550, '0':29502 ]
177
+ [1721889660] n_remain: 1014
178
+ [1721889660] eval: [ '0':29502 ]
179
+ [1721889662] n_past = 19
180
+ [1721889662] last: [ '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<s>':1, 'I':29505, ' have':1274, ' ':29473, '1':29508, '0':29502, ' ap':1747, 'ples':3583, '.':29491, '':781, '':781, '1':29508, '0':29502, ' ap':1747, 'ples':3583, ' are':1228, ' ':29473, '5':29550, '0':29502, '%':29591 ]
181
+ [1721889662] n_remain: 1013
182
+ [1721889662] eval: [ '%':29591 ]
183
+ [1721889663] n_past = 20
184
+ [1721889663] last: [ '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<unk>':0, '<s>':1, 'I':29505, ' have':1274, ' ':29473, '1':29508, '0':29502, ' ap':1747, 'ples':3583, '.':29491, '':781, '':781, '1':29508, '0':29502, ' ap':1747, 'ples':3583, ' are':1228, ' ':29473, '5':29550, '0':29502, '%':29591, ' of':1070 ]
185
+ [1721889663] n_remain: 1012
186
+ [1721889663] eval: [ ' of':1070 ]
187
+ [1721889663]
188
+ [1721889663] llama_print_timings: load time = 15039.00 ms
189
+ [1721889663] llama_print_timings: sample time = 0.60 ms / 12 runs ( 0.05 ms per token, 19867.55 tokens per second)
190
+ [1721889663] llama_print_timings: prompt eval time = 8032.80 ms / 9 tokens ( 892.53 ms per token, 1.12 tokens per second)
191
+ [1721889663] llama_print_timings: eval time = 11690.98 ms / 11 runs ( 1062.82 ms per token, 0.94 tokens per second)
192
+ [1721889663] llama_print_timings: total time = 20028.03 ms / 20 tokens