helcig commited on
Commit
9543aaf
·
verified ·
1 Parent(s): 8bfb0dd

Delete files missing locally

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. Llama-3.1-8B-Instruct/ll_bsearch_kl0.01_sha_bw6.80_4-8bit/model.safetensors.index.json +0 -299
  2. Llama-3.1-8B-Instruct/ll_bsearch_kl0.01_sha_bw6.80_4-8bit/quantization_config.txt +0 -249
  3. Llama-3.1-8B-Instruct/ll_bsearch_kl0.01_sha_bw6.80_4-8bit/special_tokens_map.json +0 -17
  4. Llama-3.1-8B-Instruct/ll_bsearch_kl0.01_sha_bw6.80_4-8bit/tokenizer.json +0 -3
  5. Llama-3.1-8B-Instruct/ll_bsearch_kl0.01_sha_bw6.80_4-8bit/tokenizer_config.json +0 -2063
  6. Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw6.65_5-6-7-8bit/README.md +0 -17
  7. Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw6.65_5-6-7-8bit/chat_template.jinja +0 -109
  8. Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw6.65_5-6-7-8bit/config.json +0 -39
  9. Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw6.65_5-6-7-8bit/generation_config.json +0 -12
  10. Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw6.65_5-6-7-8bit/model-00001-of-00004.safetensors +0 -3
  11. Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw6.65_5-6-7-8bit/model-00002-of-00004.safetensors +0 -3
  12. Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw6.65_5-6-7-8bit/model-00003-of-00004.safetensors +0 -3
  13. Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw6.65_5-6-7-8bit/model-00004-of-00004.safetensors +0 -3
  14. Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw6.65_5-6-7-8bit/model.safetensors.index.json +0 -299
  15. Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw6.65_5-6-7-8bit/quantization_config.txt +0 -252
  16. Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw6.65_5-6-7-8bit/special_tokens_map.json +0 -17
  17. Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw6.65_5-6-7-8bit/tokenizer.json +0 -3
  18. Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw6.65_5-6-7-8bit/tokenizer_config.json +0 -2063
  19. Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw7.54_4-8bit/README.md +0 -17
  20. Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw7.54_4-8bit/chat_template.jinja +0 -109
  21. Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw7.54_4-8bit/config.json +0 -39
  22. Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw7.54_4-8bit/generation_config.json +0 -12
  23. Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw7.54_4-8bit/model-00001-of-00004.safetensors +0 -3
  24. Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw7.54_4-8bit/model-00002-of-00004.safetensors +0 -3
  25. Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw7.54_4-8bit/model-00003-of-00004.safetensors +0 -3
  26. Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw7.54_4-8bit/model-00004-of-00004.safetensors +0 -3
  27. Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw7.54_4-8bit/model.safetensors.index.json +0 -299
  28. Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw7.54_4-8bit/quantization_config.txt +0 -250
  29. Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw7.54_4-8bit/special_tokens_map.json +0 -17
  30. Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw7.54_4-8bit/tokenizer.json +0 -3
  31. Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw7.54_4-8bit/tokenizer_config.json +0 -2063
  32. Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw6.00_5-6-7-8bit/README.md +0 -16
  33. Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw6.00_5-6-7-8bit/chat_template.jinja +0 -109
  34. Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw6.00_5-6-7-8bit/config.json +0 -39
  35. Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw6.00_5-6-7-8bit/generation_config.json +0 -12
  36. Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw6.00_5-6-7-8bit/model-00001-of-00004.safetensors +0 -3
  37. Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw6.00_5-6-7-8bit/model-00002-of-00004.safetensors +0 -3
  38. Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw6.00_5-6-7-8bit/model-00003-of-00004.safetensors +0 -3
  39. Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw6.00_5-6-7-8bit/model-00004-of-00004.safetensors +0 -3
  40. Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw6.00_5-6-7-8bit/model.safetensors.index.json +0 -299
  41. Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw6.00_5-6-7-8bit/quantization_config.txt +0 -251
  42. Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw6.00_5-6-7-8bit/special_tokens_map.json +0 -17
  43. Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw6.00_5-6-7-8bit/tokenizer.json +0 -3
  44. Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw6.00_5-6-7-8bit/tokenizer_config.json +0 -2063
  45. Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw7.56_4-8bit/README.md +0 -16
  46. Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw7.56_4-8bit/chat_template.jinja +0 -109
  47. Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw7.56_4-8bit/config.json +0 -39
  48. Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw7.56_4-8bit/generation_config.json +0 -12
  49. Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw7.56_4-8bit/model-00001-of-00004.safetensors +0 -3
  50. Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw7.56_4-8bit/model-00002-of-00004.safetensors +0 -3
Llama-3.1-8B-Instruct/ll_bsearch_kl0.01_sha_bw6.80_4-8bit/model.safetensors.index.json DELETED
@@ -1,299 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_parameters": 8030261248,
4
- "total_size": 16060522496
5
- },
6
- "weight_map": {
7
- "lm_head.weight": "model-00004-of-00004.safetensors",
8
- "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
- "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
17
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
18
- "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
19
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
20
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
21
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
22
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
23
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
24
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
25
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
26
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
27
- "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
28
- "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
29
- "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
30
- "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
31
- "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
32
- "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
33
- "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
34
- "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
35
- "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
36
- "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
37
- "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
38
- "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
39
- "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
40
- "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
41
- "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
42
- "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
43
- "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
44
- "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
45
- "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
46
- "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
47
- "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
48
- "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
49
- "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
50
- "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
- "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
- "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
53
- "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
54
- "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
55
- "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
56
- "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
57
- "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
58
- "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
59
- "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
60
- "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
61
- "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
62
- "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
63
- "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
64
- "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
65
- "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
66
- "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
67
- "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
68
- "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
69
- "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
70
- "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
71
- "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
72
- "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
73
- "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
74
- "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
75
- "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
76
- "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
77
- "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
78
- "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
79
- "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
80
- "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
81
- "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
82
- "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
83
- "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
84
- "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
85
- "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
86
- "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
- "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
- "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
89
- "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
90
- "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
91
- "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
92
- "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
93
- "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
94
- "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
95
- "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
96
- "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
97
- "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
98
- "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
99
- "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
100
- "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
101
- "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
102
- "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
103
- "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
104
- "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
105
- "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
106
- "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
107
- "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
108
- "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
109
- "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
110
- "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
111
- "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
112
- "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
113
- "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
114
- "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
115
- "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
116
- "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
117
- "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
118
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
119
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
120
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
121
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
122
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
123
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
124
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
125
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
126
- "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
127
- "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
128
- "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
129
- "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
130
- "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
131
- "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
132
- "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
133
- "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
134
- "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
135
- "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
136
- "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
137
- "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
138
- "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
139
- "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
140
- "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
141
- "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
142
- "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
143
- "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
144
- "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
145
- "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
146
- "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
147
- "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
148
- "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
149
- "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
150
- "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
151
- "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
152
- "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
153
- "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
154
- "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
155
- "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
156
- "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
157
- "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
158
- "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
159
- "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
160
- "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
161
- "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
162
- "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
163
- "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
164
- "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
165
- "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
166
- "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
167
- "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
168
- "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
169
- "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
170
- "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
171
- "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
172
- "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
173
- "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
174
- "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
175
- "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
176
- "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
177
- "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
178
- "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
179
- "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
180
- "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
181
- "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
182
- "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
183
- "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
184
- "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
185
- "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
186
- "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
187
- "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
188
- "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
189
- "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
190
- "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
191
- "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
192
- "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
193
- "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
194
- "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
- "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
- "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
197
- "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
198
- "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
199
- "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
200
- "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
201
- "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
202
- "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
203
- "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
204
- "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
205
- "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
206
- "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
207
- "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
208
- "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
209
- "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
210
- "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
211
- "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
212
- "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
213
- "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
214
- "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
215
- "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
216
- "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
217
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
218
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
219
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
220
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
221
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
222
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
223
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
224
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
225
- "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
226
- "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
227
- "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
228
- "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
229
- "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
230
- "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
- "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
- "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
233
- "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
234
- "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
235
- "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
236
- "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
237
- "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
238
- "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
239
- "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
240
- "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
241
- "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
242
- "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
243
- "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
244
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
245
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
246
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
247
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
248
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
249
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
250
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
251
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
252
- "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
253
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
254
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
255
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
256
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
257
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
258
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
259
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
260
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
261
- "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
262
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
263
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
264
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
265
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
266
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
269
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
270
- "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
271
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
272
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
273
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
274
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
275
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
276
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
277
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
278
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
279
- "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
280
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
281
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
282
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
283
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
284
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
285
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
286
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
287
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
288
- "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
289
- "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
290
- "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
291
- "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
292
- "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
293
- "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
294
- "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
295
- "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
296
- "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
297
- "model.norm.weight": "model-00004-of-00004.safetensors"
298
- }
299
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Llama-3.1-8B-Instruct/ll_bsearch_kl0.01_sha_bw6.80_4-8bit/quantization_config.txt DELETED
@@ -1,249 +0,0 @@
1
- # Model: meta-llama/Llama-3.1-8B-Instruct
2
- # Layer directory: /nfs/scistore19/alistgrp/mhelcig/local/data/search/4_5_6_7_8bit_asym_g128/Llama-3.1-8B-Instruct/6bit/
3
- # Sensitivity method: shapley
4
- # Estimation method: permutation_separate
5
- # Available bitwidths: [4, 8]
6
- # Bitwidth map: {4: 4.3125, 5: 5.3125, 6: 6.3125, 7: 7.3125, 8: 8.3125}
7
- #
8
- # Mode: binary_search_constraint
9
- # Constraint max_kl: 0.01
10
- # Weights: nll=0.0, kl=0.0, eap=1.0
11
- #
12
- # Average bitwidth: 6.7981
13
- # Total params: 6979321856
14
- # Total bits: 47445966848
15
- # Final KL: 0.009849
16
- # Final EAP: 0.967613
17
- # Final ETL: 0.032387
18
- # Satisfies constraints: True
19
- # Solver calls: 6
20
- # Evaluations: 6
21
- #
22
- # Bitwidth distribution:
23
- # 8-bit: 179 layers (79.9%)
24
- # 4-bit: 45 layers (20.1%)
25
- #
26
- model.layers.0.self_attn.q_proj: 8
27
- model.layers.0.self_attn.k_proj: 8
28
- model.layers.0.self_attn.v_proj: 8
29
- model.layers.0.self_attn.o_proj: 8
30
- model.layers.0.mlp.gate_proj: 4
31
- model.layers.0.mlp.up_proj: 4
32
- model.layers.0.mlp.down_proj: 8
33
- model.layers.1.self_attn.q_proj: 8
34
- model.layers.1.self_attn.k_proj: 8
35
- model.layers.1.self_attn.v_proj: 8
36
- model.layers.1.self_attn.o_proj: 8
37
- model.layers.1.mlp.gate_proj: 8
38
- model.layers.1.mlp.up_proj: 8
39
- model.layers.1.mlp.down_proj: 8
40
- model.layers.2.self_attn.q_proj: 8
41
- model.layers.2.self_attn.k_proj: 8
42
- model.layers.2.self_attn.v_proj: 8
43
- model.layers.2.self_attn.o_proj: 8
44
- model.layers.2.mlp.gate_proj: 8
45
- model.layers.2.mlp.up_proj: 8
46
- model.layers.2.mlp.down_proj: 4
47
- model.layers.3.self_attn.q_proj: 8
48
- model.layers.3.self_attn.k_proj: 8
49
- model.layers.3.self_attn.v_proj: 8
50
- model.layers.3.self_attn.o_proj: 8
51
- model.layers.3.mlp.gate_proj: 8
52
- model.layers.3.mlp.up_proj: 8
53
- model.layers.3.mlp.down_proj: 4
54
- model.layers.4.self_attn.q_proj: 8
55
- model.layers.4.self_attn.k_proj: 8
56
- model.layers.4.self_attn.v_proj: 8
57
- model.layers.4.self_attn.o_proj: 8
58
- model.layers.4.mlp.gate_proj: 8
59
- model.layers.4.mlp.up_proj: 8
60
- model.layers.4.mlp.down_proj: 8
61
- model.layers.5.self_attn.q_proj: 8
62
- model.layers.5.self_attn.k_proj: 8
63
- model.layers.5.self_attn.v_proj: 8
64
- model.layers.5.self_attn.o_proj: 8
65
- model.layers.5.mlp.gate_proj: 8
66
- model.layers.5.mlp.up_proj: 8
67
- model.layers.5.mlp.down_proj: 4
68
- model.layers.6.self_attn.q_proj: 8
69
- model.layers.6.self_attn.k_proj: 8
70
- model.layers.6.self_attn.v_proj: 8
71
- model.layers.6.self_attn.o_proj: 8
72
- model.layers.6.mlp.gate_proj: 8
73
- model.layers.6.mlp.up_proj: 8
74
- model.layers.6.mlp.down_proj: 4
75
- model.layers.7.self_attn.q_proj: 8
76
- model.layers.7.self_attn.k_proj: 8
77
- model.layers.7.self_attn.v_proj: 8
78
- model.layers.7.self_attn.o_proj: 8
79
- model.layers.7.mlp.gate_proj: 8
80
- model.layers.7.mlp.up_proj: 8
81
- model.layers.7.mlp.down_proj: 4
82
- model.layers.8.self_attn.q_proj: 8
83
- model.layers.8.self_attn.k_proj: 8
84
- model.layers.8.self_attn.v_proj: 8
85
- model.layers.8.self_attn.o_proj: 8
86
- model.layers.8.mlp.gate_proj: 8
87
- model.layers.8.mlp.up_proj: 8
88
- model.layers.8.mlp.down_proj: 4
89
- model.layers.9.self_attn.q_proj: 8
90
- model.layers.9.self_attn.k_proj: 8
91
- model.layers.9.self_attn.v_proj: 8
92
- model.layers.9.self_attn.o_proj: 8
93
- model.layers.9.mlp.gate_proj: 4
94
- model.layers.9.mlp.up_proj: 4
95
- model.layers.9.mlp.down_proj: 4
96
- model.layers.10.self_attn.q_proj: 8
97
- model.layers.10.self_attn.k_proj: 8
98
- model.layers.10.self_attn.v_proj: 8
99
- model.layers.10.self_attn.o_proj: 8
100
- model.layers.10.mlp.gate_proj: 8
101
- model.layers.10.mlp.up_proj: 8
102
- model.layers.10.mlp.down_proj: 4
103
- model.layers.11.self_attn.q_proj: 8
104
- model.layers.11.self_attn.k_proj: 8
105
- model.layers.11.self_attn.v_proj: 8
106
- model.layers.11.self_attn.o_proj: 8
107
- model.layers.11.mlp.gate_proj: 8
108
- model.layers.11.mlp.up_proj: 8
109
- model.layers.11.mlp.down_proj: 4
110
- model.layers.12.self_attn.q_proj: 8
111
- model.layers.12.self_attn.k_proj: 8
112
- model.layers.12.self_attn.v_proj: 8
113
- model.layers.12.self_attn.o_proj: 8
114
- model.layers.12.mlp.gate_proj: 4
115
- model.layers.12.mlp.up_proj: 4
116
- model.layers.12.mlp.down_proj: 4
117
- model.layers.13.self_attn.q_proj: 8
118
- model.layers.13.self_attn.k_proj: 8
119
- model.layers.13.self_attn.v_proj: 8
120
- model.layers.13.self_attn.o_proj: 8
121
- model.layers.13.mlp.gate_proj: 4
122
- model.layers.13.mlp.up_proj: 4
123
- model.layers.13.mlp.down_proj: 8
124
- model.layers.14.self_attn.q_proj: 8
125
- model.layers.14.self_attn.k_proj: 8
126
- model.layers.14.self_attn.v_proj: 8
127
- model.layers.14.self_attn.o_proj: 8
128
- model.layers.14.mlp.gate_proj: 8
129
- model.layers.14.mlp.up_proj: 8
130
- model.layers.14.mlp.down_proj: 4
131
- model.layers.15.self_attn.q_proj: 8
132
- model.layers.15.self_attn.k_proj: 8
133
- model.layers.15.self_attn.v_proj: 8
134
- model.layers.15.self_attn.o_proj: 8
135
- model.layers.15.mlp.gate_proj: 8
136
- model.layers.15.mlp.up_proj: 8
137
- model.layers.15.mlp.down_proj: 8
138
- model.layers.16.self_attn.q_proj: 8
139
- model.layers.16.self_attn.k_proj: 8
140
- model.layers.16.self_attn.v_proj: 8
141
- model.layers.16.self_attn.o_proj: 8
142
- model.layers.16.mlp.gate_proj: 8
143
- model.layers.16.mlp.up_proj: 8
144
- model.layers.16.mlp.down_proj: 4
145
- model.layers.17.self_attn.q_proj: 8
146
- model.layers.17.self_attn.k_proj: 8
147
- model.layers.17.self_attn.v_proj: 8
148
- model.layers.17.self_attn.o_proj: 8
149
- model.layers.17.mlp.gate_proj: 8
150
- model.layers.17.mlp.up_proj: 8
151
- model.layers.17.mlp.down_proj: 8
152
- model.layers.18.self_attn.q_proj: 8
153
- model.layers.18.self_attn.k_proj: 8
154
- model.layers.18.self_attn.v_proj: 8
155
- model.layers.18.self_attn.o_proj: 8
156
- model.layers.18.mlp.gate_proj: 8
157
- model.layers.18.mlp.up_proj: 8
158
- model.layers.18.mlp.down_proj: 4
159
- model.layers.19.self_attn.q_proj: 8
160
- model.layers.19.self_attn.k_proj: 8
161
- model.layers.19.self_attn.v_proj: 8
162
- model.layers.19.self_attn.o_proj: 8
163
- model.layers.19.mlp.gate_proj: 8
164
- model.layers.19.mlp.up_proj: 8
165
- model.layers.19.mlp.down_proj: 4
166
- model.layers.20.self_attn.q_proj: 8
167
- model.layers.20.self_attn.k_proj: 8
168
- model.layers.20.self_attn.v_proj: 8
169
- model.layers.20.self_attn.o_proj: 8
170
- model.layers.20.mlp.gate_proj: 8
171
- model.layers.20.mlp.up_proj: 8
172
- model.layers.20.mlp.down_proj: 4
173
- model.layers.21.self_attn.q_proj: 8
174
- model.layers.21.self_attn.k_proj: 8
175
- model.layers.21.self_attn.v_proj: 8
176
- model.layers.21.self_attn.o_proj: 8
177
- model.layers.21.mlp.gate_proj: 4
178
- model.layers.21.mlp.up_proj: 4
179
- model.layers.21.mlp.down_proj: 4
180
- model.layers.22.self_attn.q_proj: 8
181
- model.layers.22.self_attn.k_proj: 8
182
- model.layers.22.self_attn.v_proj: 8
183
- model.layers.22.self_attn.o_proj: 8
184
- model.layers.22.mlp.gate_proj: 8
185
- model.layers.22.mlp.up_proj: 8
186
- model.layers.22.mlp.down_proj: 4
187
- model.layers.23.self_attn.q_proj: 8
188
- model.layers.23.self_attn.k_proj: 8
189
- model.layers.23.self_attn.v_proj: 8
190
- model.layers.23.self_attn.o_proj: 8
191
- model.layers.23.mlp.gate_proj: 8
192
- model.layers.23.mlp.up_proj: 8
193
- model.layers.23.mlp.down_proj: 4
194
- model.layers.24.self_attn.q_proj: 8
195
- model.layers.24.self_attn.k_proj: 8
196
- model.layers.24.self_attn.v_proj: 8
197
- model.layers.24.self_attn.o_proj: 8
198
- model.layers.24.mlp.gate_proj: 4
199
- model.layers.24.mlp.up_proj: 4
200
- model.layers.24.mlp.down_proj: 4
201
- model.layers.25.self_attn.q_proj: 8
202
- model.layers.25.self_attn.k_proj: 8
203
- model.layers.25.self_attn.v_proj: 8
204
- model.layers.25.self_attn.o_proj: 8
205
- model.layers.25.mlp.gate_proj: 4
206
- model.layers.25.mlp.up_proj: 4
207
- model.layers.25.mlp.down_proj: 4
208
- model.layers.26.self_attn.q_proj: 8
209
- model.layers.26.self_attn.k_proj: 8
210
- model.layers.26.self_attn.v_proj: 8
211
- model.layers.26.self_attn.o_proj: 8
212
- model.layers.26.mlp.gate_proj: 4
213
- model.layers.26.mlp.up_proj: 4
214
- model.layers.26.mlp.down_proj: 4
215
- model.layers.27.self_attn.q_proj: 8
216
- model.layers.27.self_attn.k_proj: 8
217
- model.layers.27.self_attn.v_proj: 8
218
- model.layers.27.self_attn.o_proj: 8
219
- model.layers.27.mlp.gate_proj: 4
220
- model.layers.27.mlp.up_proj: 4
221
- model.layers.27.mlp.down_proj: 4
222
- model.layers.28.self_attn.q_proj: 8
223
- model.layers.28.self_attn.k_proj: 8
224
- model.layers.28.self_attn.v_proj: 8
225
- model.layers.28.self_attn.o_proj: 8
226
- model.layers.28.mlp.gate_proj: 4
227
- model.layers.28.mlp.up_proj: 4
228
- model.layers.28.mlp.down_proj: 4
229
- model.layers.29.self_attn.q_proj: 8
230
- model.layers.29.self_attn.k_proj: 8
231
- model.layers.29.self_attn.v_proj: 8
232
- model.layers.29.self_attn.o_proj: 8
233
- model.layers.29.mlp.gate_proj: 8
234
- model.layers.29.mlp.up_proj: 8
235
- model.layers.29.mlp.down_proj: 4
236
- model.layers.30.self_attn.q_proj: 8
237
- model.layers.30.self_attn.k_proj: 8
238
- model.layers.30.self_attn.v_proj: 8
239
- model.layers.30.self_attn.o_proj: 8
240
- model.layers.30.mlp.gate_proj: 8
241
- model.layers.30.mlp.up_proj: 8
242
- model.layers.30.mlp.down_proj: 4
243
- model.layers.31.self_attn.q_proj: 8
244
- model.layers.31.self_attn.k_proj: 8
245
- model.layers.31.self_attn.v_proj: 8
246
- model.layers.31.self_attn.o_proj: 8
247
- model.layers.31.mlp.gate_proj: 8
248
- model.layers.31.mlp.up_proj: 8
249
- model.layers.31.mlp.down_proj: 8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Llama-3.1-8B-Instruct/ll_bsearch_kl0.01_sha_bw6.80_4-8bit/special_tokens_map.json DELETED
@@ -1,17 +0,0 @@
1
- {
2
- "bos_token": {
3
- "content": "<|begin_of_text|>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "<|eot_id|>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": "<|eot_id|>"
17
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Llama-3.1-8B-Instruct/ll_bsearch_kl0.01_sha_bw6.80_4-8bit/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
- size 17209920
 
 
 
 
Llama-3.1-8B-Instruct/ll_bsearch_kl0.01_sha_bw6.80_4-8bit/tokenizer_config.json DELETED
@@ -1,2063 +0,0 @@
1
- {
2
- "added_tokens_decoder": {
3
- "128000": {
4
- "content": "<|begin_of_text|>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "128001": {
12
- "content": "<|end_of_text|>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "128002": {
20
- "content": "<|reserved_special_token_0|>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "128003": {
28
- "content": "<|reserved_special_token_1|>",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "128004": {
36
- "content": "<|finetune_right_pad_id|>",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- },
43
- "128005": {
44
- "content": "<|reserved_special_token_2|>",
45
- "lstrip": false,
46
- "normalized": false,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": true
50
- },
51
- "128006": {
52
- "content": "<|start_header_id|>",
53
- "lstrip": false,
54
- "normalized": false,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": true
58
- },
59
- "128007": {
60
- "content": "<|end_header_id|>",
61
- "lstrip": false,
62
- "normalized": false,
63
- "rstrip": false,
64
- "single_word": false,
65
- "special": true
66
- },
67
- "128008": {
68
- "content": "<|eom_id|>",
69
- "lstrip": false,
70
- "normalized": false,
71
- "rstrip": false,
72
- "single_word": false,
73
- "special": true
74
- },
75
- "128009": {
76
- "content": "<|eot_id|>",
77
- "lstrip": false,
78
- "normalized": false,
79
- "rstrip": false,
80
- "single_word": false,
81
- "special": true
82
- },
83
- "128010": {
84
- "content": "<|python_tag|>",
85
- "lstrip": false,
86
- "normalized": false,
87
- "rstrip": false,
88
- "single_word": false,
89
- "special": true
90
- },
91
- "128011": {
92
- "content": "<|reserved_special_token_3|>",
93
- "lstrip": false,
94
- "normalized": false,
95
- "rstrip": false,
96
- "single_word": false,
97
- "special": true
98
- },
99
- "128012": {
100
- "content": "<|reserved_special_token_4|>",
101
- "lstrip": false,
102
- "normalized": false,
103
- "rstrip": false,
104
- "single_word": false,
105
- "special": true
106
- },
107
- "128013": {
108
- "content": "<|reserved_special_token_5|>",
109
- "lstrip": false,
110
- "normalized": false,
111
- "rstrip": false,
112
- "single_word": false,
113
- "special": true
114
- },
115
- "128014": {
116
- "content": "<|reserved_special_token_6|>",
117
- "lstrip": false,
118
- "normalized": false,
119
- "rstrip": false,
120
- "single_word": false,
121
- "special": true
122
- },
123
- "128015": {
124
- "content": "<|reserved_special_token_7|>",
125
- "lstrip": false,
126
- "normalized": false,
127
- "rstrip": false,
128
- "single_word": false,
129
- "special": true
130
- },
131
- "128016": {
132
- "content": "<|reserved_special_token_8|>",
133
- "lstrip": false,
134
- "normalized": false,
135
- "rstrip": false,
136
- "single_word": false,
137
- "special": true
138
- },
139
- "128017": {
140
- "content": "<|reserved_special_token_9|>",
141
- "lstrip": false,
142
- "normalized": false,
143
- "rstrip": false,
144
- "single_word": false,
145
- "special": true
146
- },
147
- "128018": {
148
- "content": "<|reserved_special_token_10|>",
149
- "lstrip": false,
150
- "normalized": false,
151
- "rstrip": false,
152
- "single_word": false,
153
- "special": true
154
- },
155
- "128019": {
156
- "content": "<|reserved_special_token_11|>",
157
- "lstrip": false,
158
- "normalized": false,
159
- "rstrip": false,
160
- "single_word": false,
161
- "special": true
162
- },
163
- "128020": {
164
- "content": "<|reserved_special_token_12|>",
165
- "lstrip": false,
166
- "normalized": false,
167
- "rstrip": false,
168
- "single_word": false,
169
- "special": true
170
- },
171
- "128021": {
172
- "content": "<|reserved_special_token_13|>",
173
- "lstrip": false,
174
- "normalized": false,
175
- "rstrip": false,
176
- "single_word": false,
177
- "special": true
178
- },
179
- "128022": {
180
- "content": "<|reserved_special_token_14|>",
181
- "lstrip": false,
182
- "normalized": false,
183
- "rstrip": false,
184
- "single_word": false,
185
- "special": true
186
- },
187
- "128023": {
188
- "content": "<|reserved_special_token_15|>",
189
- "lstrip": false,
190
- "normalized": false,
191
- "rstrip": false,
192
- "single_word": false,
193
- "special": true
194
- },
195
- "128024": {
196
- "content": "<|reserved_special_token_16|>",
197
- "lstrip": false,
198
- "normalized": false,
199
- "rstrip": false,
200
- "single_word": false,
201
- "special": true
202
- },
203
- "128025": {
204
- "content": "<|reserved_special_token_17|>",
205
- "lstrip": false,
206
- "normalized": false,
207
- "rstrip": false,
208
- "single_word": false,
209
- "special": true
210
- },
211
- "128026": {
212
- "content": "<|reserved_special_token_18|>",
213
- "lstrip": false,
214
- "normalized": false,
215
- "rstrip": false,
216
- "single_word": false,
217
- "special": true
218
- },
219
- "128027": {
220
- "content": "<|reserved_special_token_19|>",
221
- "lstrip": false,
222
- "normalized": false,
223
- "rstrip": false,
224
- "single_word": false,
225
- "special": true
226
- },
227
- "128028": {
228
- "content": "<|reserved_special_token_20|>",
229
- "lstrip": false,
230
- "normalized": false,
231
- "rstrip": false,
232
- "single_word": false,
233
- "special": true
234
- },
235
- "128029": {
236
- "content": "<|reserved_special_token_21|>",
237
- "lstrip": false,
238
- "normalized": false,
239
- "rstrip": false,
240
- "single_word": false,
241
- "special": true
242
- },
243
- "128030": {
244
- "content": "<|reserved_special_token_22|>",
245
- "lstrip": false,
246
- "normalized": false,
247
- "rstrip": false,
248
- "single_word": false,
249
- "special": true
250
- },
251
- "128031": {
252
- "content": "<|reserved_special_token_23|>",
253
- "lstrip": false,
254
- "normalized": false,
255
- "rstrip": false,
256
- "single_word": false,
257
- "special": true
258
- },
259
- "128032": {
260
- "content": "<|reserved_special_token_24|>",
261
- "lstrip": false,
262
- "normalized": false,
263
- "rstrip": false,
264
- "single_word": false,
265
- "special": true
266
- },
267
- "128033": {
268
- "content": "<|reserved_special_token_25|>",
269
- "lstrip": false,
270
- "normalized": false,
271
- "rstrip": false,
272
- "single_word": false,
273
- "special": true
274
- },
275
- "128034": {
276
- "content": "<|reserved_special_token_26|>",
277
- "lstrip": false,
278
- "normalized": false,
279
- "rstrip": false,
280
- "single_word": false,
281
- "special": true
282
- },
283
- "128035": {
284
- "content": "<|reserved_special_token_27|>",
285
- "lstrip": false,
286
- "normalized": false,
287
- "rstrip": false,
288
- "single_word": false,
289
- "special": true
290
- },
291
- "128036": {
292
- "content": "<|reserved_special_token_28|>",
293
- "lstrip": false,
294
- "normalized": false,
295
- "rstrip": false,
296
- "single_word": false,
297
- "special": true
298
- },
299
- "128037": {
300
- "content": "<|reserved_special_token_29|>",
301
- "lstrip": false,
302
- "normalized": false,
303
- "rstrip": false,
304
- "single_word": false,
305
- "special": true
306
- },
307
- "128038": {
308
- "content": "<|reserved_special_token_30|>",
309
- "lstrip": false,
310
- "normalized": false,
311
- "rstrip": false,
312
- "single_word": false,
313
- "special": true
314
- },
315
- "128039": {
316
- "content": "<|reserved_special_token_31|>",
317
- "lstrip": false,
318
- "normalized": false,
319
- "rstrip": false,
320
- "single_word": false,
321
- "special": true
322
- },
323
- "128040": {
324
- "content": "<|reserved_special_token_32|>",
325
- "lstrip": false,
326
- "normalized": false,
327
- "rstrip": false,
328
- "single_word": false,
329
- "special": true
330
- },
331
- "128041": {
332
- "content": "<|reserved_special_token_33|>",
333
- "lstrip": false,
334
- "normalized": false,
335
- "rstrip": false,
336
- "single_word": false,
337
- "special": true
338
- },
339
- "128042": {
340
- "content": "<|reserved_special_token_34|>",
341
- "lstrip": false,
342
- "normalized": false,
343
- "rstrip": false,
344
- "single_word": false,
345
- "special": true
346
- },
347
- "128043": {
348
- "content": "<|reserved_special_token_35|>",
349
- "lstrip": false,
350
- "normalized": false,
351
- "rstrip": false,
352
- "single_word": false,
353
- "special": true
354
- },
355
- "128044": {
356
- "content": "<|reserved_special_token_36|>",
357
- "lstrip": false,
358
- "normalized": false,
359
- "rstrip": false,
360
- "single_word": false,
361
- "special": true
362
- },
363
- "128045": {
364
- "content": "<|reserved_special_token_37|>",
365
- "lstrip": false,
366
- "normalized": false,
367
- "rstrip": false,
368
- "single_word": false,
369
- "special": true
370
- },
371
- "128046": {
372
- "content": "<|reserved_special_token_38|>",
373
- "lstrip": false,
374
- "normalized": false,
375
- "rstrip": false,
376
- "single_word": false,
377
- "special": true
378
- },
379
- "128047": {
380
- "content": "<|reserved_special_token_39|>",
381
- "lstrip": false,
382
- "normalized": false,
383
- "rstrip": false,
384
- "single_word": false,
385
- "special": true
386
- },
387
- "128048": {
388
- "content": "<|reserved_special_token_40|>",
389
- "lstrip": false,
390
- "normalized": false,
391
- "rstrip": false,
392
- "single_word": false,
393
- "special": true
394
- },
395
- "128049": {
396
- "content": "<|reserved_special_token_41|>",
397
- "lstrip": false,
398
- "normalized": false,
399
- "rstrip": false,
400
- "single_word": false,
401
- "special": true
402
- },
403
- "128050": {
404
- "content": "<|reserved_special_token_42|>",
405
- "lstrip": false,
406
- "normalized": false,
407
- "rstrip": false,
408
- "single_word": false,
409
- "special": true
410
- },
411
- "128051": {
412
- "content": "<|reserved_special_token_43|>",
413
- "lstrip": false,
414
- "normalized": false,
415
- "rstrip": false,
416
- "single_word": false,
417
- "special": true
418
- },
419
- "128052": {
420
- "content": "<|reserved_special_token_44|>",
421
- "lstrip": false,
422
- "normalized": false,
423
- "rstrip": false,
424
- "single_word": false,
425
- "special": true
426
- },
427
- "128053": {
428
- "content": "<|reserved_special_token_45|>",
429
- "lstrip": false,
430
- "normalized": false,
431
- "rstrip": false,
432
- "single_word": false,
433
- "special": true
434
- },
435
- "128054": {
436
- "content": "<|reserved_special_token_46|>",
437
- "lstrip": false,
438
- "normalized": false,
439
- "rstrip": false,
440
- "single_word": false,
441
- "special": true
442
- },
443
- "128055": {
444
- "content": "<|reserved_special_token_47|>",
445
- "lstrip": false,
446
- "normalized": false,
447
- "rstrip": false,
448
- "single_word": false,
449
- "special": true
450
- },
451
- "128056": {
452
- "content": "<|reserved_special_token_48|>",
453
- "lstrip": false,
454
- "normalized": false,
455
- "rstrip": false,
456
- "single_word": false,
457
- "special": true
458
- },
459
- "128057": {
460
- "content": "<|reserved_special_token_49|>",
461
- "lstrip": false,
462
- "normalized": false,
463
- "rstrip": false,
464
- "single_word": false,
465
- "special": true
466
- },
467
- "128058": {
468
- "content": "<|reserved_special_token_50|>",
469
- "lstrip": false,
470
- "normalized": false,
471
- "rstrip": false,
472
- "single_word": false,
473
- "special": true
474
- },
475
- "128059": {
476
- "content": "<|reserved_special_token_51|>",
477
- "lstrip": false,
478
- "normalized": false,
479
- "rstrip": false,
480
- "single_word": false,
481
- "special": true
482
- },
483
- "128060": {
484
- "content": "<|reserved_special_token_52|>",
485
- "lstrip": false,
486
- "normalized": false,
487
- "rstrip": false,
488
- "single_word": false,
489
- "special": true
490
- },
491
- "128061": {
492
- "content": "<|reserved_special_token_53|>",
493
- "lstrip": false,
494
- "normalized": false,
495
- "rstrip": false,
496
- "single_word": false,
497
- "special": true
498
- },
499
- "128062": {
500
- "content": "<|reserved_special_token_54|>",
501
- "lstrip": false,
502
- "normalized": false,
503
- "rstrip": false,
504
- "single_word": false,
505
- "special": true
506
- },
507
- "128063": {
508
- "content": "<|reserved_special_token_55|>",
509
- "lstrip": false,
510
- "normalized": false,
511
- "rstrip": false,
512
- "single_word": false,
513
- "special": true
514
- },
515
- "128064": {
516
- "content": "<|reserved_special_token_56|>",
517
- "lstrip": false,
518
- "normalized": false,
519
- "rstrip": false,
520
- "single_word": false,
521
- "special": true
522
- },
523
- "128065": {
524
- "content": "<|reserved_special_token_57|>",
525
- "lstrip": false,
526
- "normalized": false,
527
- "rstrip": false,
528
- "single_word": false,
529
- "special": true
530
- },
531
- "128066": {
532
- "content": "<|reserved_special_token_58|>",
533
- "lstrip": false,
534
- "normalized": false,
535
- "rstrip": false,
536
- "single_word": false,
537
- "special": true
538
- },
539
- "128067": {
540
- "content": "<|reserved_special_token_59|>",
541
- "lstrip": false,
542
- "normalized": false,
543
- "rstrip": false,
544
- "single_word": false,
545
- "special": true
546
- },
547
- "128068": {
548
- "content": "<|reserved_special_token_60|>",
549
- "lstrip": false,
550
- "normalized": false,
551
- "rstrip": false,
552
- "single_word": false,
553
- "special": true
554
- },
555
- "128069": {
556
- "content": "<|reserved_special_token_61|>",
557
- "lstrip": false,
558
- "normalized": false,
559
- "rstrip": false,
560
- "single_word": false,
561
- "special": true
562
- },
563
- "128070": {
564
- "content": "<|reserved_special_token_62|>",
565
- "lstrip": false,
566
- "normalized": false,
567
- "rstrip": false,
568
- "single_word": false,
569
- "special": true
570
- },
571
- "128071": {
572
- "content": "<|reserved_special_token_63|>",
573
- "lstrip": false,
574
- "normalized": false,
575
- "rstrip": false,
576
- "single_word": false,
577
- "special": true
578
- },
579
- "128072": {
580
- "content": "<|reserved_special_token_64|>",
581
- "lstrip": false,
582
- "normalized": false,
583
- "rstrip": false,
584
- "single_word": false,
585
- "special": true
586
- },
587
- "128073": {
588
- "content": "<|reserved_special_token_65|>",
589
- "lstrip": false,
590
- "normalized": false,
591
- "rstrip": false,
592
- "single_word": false,
593
- "special": true
594
- },
595
- "128074": {
596
- "content": "<|reserved_special_token_66|>",
597
- "lstrip": false,
598
- "normalized": false,
599
- "rstrip": false,
600
- "single_word": false,
601
- "special": true
602
- },
603
- "128075": {
604
- "content": "<|reserved_special_token_67|>",
605
- "lstrip": false,
606
- "normalized": false,
607
- "rstrip": false,
608
- "single_word": false,
609
- "special": true
610
- },
611
- "128076": {
612
- "content": "<|reserved_special_token_68|>",
613
- "lstrip": false,
614
- "normalized": false,
615
- "rstrip": false,
616
- "single_word": false,
617
- "special": true
618
- },
619
- "128077": {
620
- "content": "<|reserved_special_token_69|>",
621
- "lstrip": false,
622
- "normalized": false,
623
- "rstrip": false,
624
- "single_word": false,
625
- "special": true
626
- },
627
- "128078": {
628
- "content": "<|reserved_special_token_70|>",
629
- "lstrip": false,
630
- "normalized": false,
631
- "rstrip": false,
632
- "single_word": false,
633
- "special": true
634
- },
635
- "128079": {
636
- "content": "<|reserved_special_token_71|>",
637
- "lstrip": false,
638
- "normalized": false,
639
- "rstrip": false,
640
- "single_word": false,
641
- "special": true
642
- },
643
- "128080": {
644
- "content": "<|reserved_special_token_72|>",
645
- "lstrip": false,
646
- "normalized": false,
647
- "rstrip": false,
648
- "single_word": false,
649
- "special": true
650
- },
651
- "128081": {
652
- "content": "<|reserved_special_token_73|>",
653
- "lstrip": false,
654
- "normalized": false,
655
- "rstrip": false,
656
- "single_word": false,
657
- "special": true
658
- },
659
- "128082": {
660
- "content": "<|reserved_special_token_74|>",
661
- "lstrip": false,
662
- "normalized": false,
663
- "rstrip": false,
664
- "single_word": false,
665
- "special": true
666
- },
667
- "128083": {
668
- "content": "<|reserved_special_token_75|>",
669
- "lstrip": false,
670
- "normalized": false,
671
- "rstrip": false,
672
- "single_word": false,
673
- "special": true
674
- },
675
- "128084": {
676
- "content": "<|reserved_special_token_76|>",
677
- "lstrip": false,
678
- "normalized": false,
679
- "rstrip": false,
680
- "single_word": false,
681
- "special": true
682
- },
683
- "128085": {
684
- "content": "<|reserved_special_token_77|>",
685
- "lstrip": false,
686
- "normalized": false,
687
- "rstrip": false,
688
- "single_word": false,
689
- "special": true
690
- },
691
- "128086": {
692
- "content": "<|reserved_special_token_78|>",
693
- "lstrip": false,
694
- "normalized": false,
695
- "rstrip": false,
696
- "single_word": false,
697
- "special": true
698
- },
699
- "128087": {
700
- "content": "<|reserved_special_token_79|>",
701
- "lstrip": false,
702
- "normalized": false,
703
- "rstrip": false,
704
- "single_word": false,
705
- "special": true
706
- },
707
- "128088": {
708
- "content": "<|reserved_special_token_80|>",
709
- "lstrip": false,
710
- "normalized": false,
711
- "rstrip": false,
712
- "single_word": false,
713
- "special": true
714
- },
715
- "128089": {
716
- "content": "<|reserved_special_token_81|>",
717
- "lstrip": false,
718
- "normalized": false,
719
- "rstrip": false,
720
- "single_word": false,
721
- "special": true
722
- },
723
- "128090": {
724
- "content": "<|reserved_special_token_82|>",
725
- "lstrip": false,
726
- "normalized": false,
727
- "rstrip": false,
728
- "single_word": false,
729
- "special": true
730
- },
731
- "128091": {
732
- "content": "<|reserved_special_token_83|>",
733
- "lstrip": false,
734
- "normalized": false,
735
- "rstrip": false,
736
- "single_word": false,
737
- "special": true
738
- },
739
- "128092": {
740
- "content": "<|reserved_special_token_84|>",
741
- "lstrip": false,
742
- "normalized": false,
743
- "rstrip": false,
744
- "single_word": false,
745
- "special": true
746
- },
747
- "128093": {
748
- "content": "<|reserved_special_token_85|>",
749
- "lstrip": false,
750
- "normalized": false,
751
- "rstrip": false,
752
- "single_word": false,
753
- "special": true
754
- },
755
- "128094": {
756
- "content": "<|reserved_special_token_86|>",
757
- "lstrip": false,
758
- "normalized": false,
759
- "rstrip": false,
760
- "single_word": false,
761
- "special": true
762
- },
763
- "128095": {
764
- "content": "<|reserved_special_token_87|>",
765
- "lstrip": false,
766
- "normalized": false,
767
- "rstrip": false,
768
- "single_word": false,
769
- "special": true
770
- },
771
- "128096": {
772
- "content": "<|reserved_special_token_88|>",
773
- "lstrip": false,
774
- "normalized": false,
775
- "rstrip": false,
776
- "single_word": false,
777
- "special": true
778
- },
779
- "128097": {
780
- "content": "<|reserved_special_token_89|>",
781
- "lstrip": false,
782
- "normalized": false,
783
- "rstrip": false,
784
- "single_word": false,
785
- "special": true
786
- },
787
- "128098": {
788
- "content": "<|reserved_special_token_90|>",
789
- "lstrip": false,
790
- "normalized": false,
791
- "rstrip": false,
792
- "single_word": false,
793
- "special": true
794
- },
795
- "128099": {
796
- "content": "<|reserved_special_token_91|>",
797
- "lstrip": false,
798
- "normalized": false,
799
- "rstrip": false,
800
- "single_word": false,
801
- "special": true
802
- },
803
- "128100": {
804
- "content": "<|reserved_special_token_92|>",
805
- "lstrip": false,
806
- "normalized": false,
807
- "rstrip": false,
808
- "single_word": false,
809
- "special": true
810
- },
811
- "128101": {
812
- "content": "<|reserved_special_token_93|>",
813
- "lstrip": false,
814
- "normalized": false,
815
- "rstrip": false,
816
- "single_word": false,
817
- "special": true
818
- },
819
- "128102": {
820
- "content": "<|reserved_special_token_94|>",
821
- "lstrip": false,
822
- "normalized": false,
823
- "rstrip": false,
824
- "single_word": false,
825
- "special": true
826
- },
827
- "128103": {
828
- "content": "<|reserved_special_token_95|>",
829
- "lstrip": false,
830
- "normalized": false,
831
- "rstrip": false,
832
- "single_word": false,
833
- "special": true
834
- },
835
- "128104": {
836
- "content": "<|reserved_special_token_96|>",
837
- "lstrip": false,
838
- "normalized": false,
839
- "rstrip": false,
840
- "single_word": false,
841
- "special": true
842
- },
843
- "128105": {
844
- "content": "<|reserved_special_token_97|>",
845
- "lstrip": false,
846
- "normalized": false,
847
- "rstrip": false,
848
- "single_word": false,
849
- "special": true
850
- },
851
- "128106": {
852
- "content": "<|reserved_special_token_98|>",
853
- "lstrip": false,
854
- "normalized": false,
855
- "rstrip": false,
856
- "single_word": false,
857
- "special": true
858
- },
859
- "128107": {
860
- "content": "<|reserved_special_token_99|>",
861
- "lstrip": false,
862
- "normalized": false,
863
- "rstrip": false,
864
- "single_word": false,
865
- "special": true
866
- },
867
- "128108": {
868
- "content": "<|reserved_special_token_100|>",
869
- "lstrip": false,
870
- "normalized": false,
871
- "rstrip": false,
872
- "single_word": false,
873
- "special": true
874
- },
875
- "128109": {
876
- "content": "<|reserved_special_token_101|>",
877
- "lstrip": false,
878
- "normalized": false,
879
- "rstrip": false,
880
- "single_word": false,
881
- "special": true
882
- },
883
- "128110": {
884
- "content": "<|reserved_special_token_102|>",
885
- "lstrip": false,
886
- "normalized": false,
887
- "rstrip": false,
888
- "single_word": false,
889
- "special": true
890
- },
891
- "128111": {
892
- "content": "<|reserved_special_token_103|>",
893
- "lstrip": false,
894
- "normalized": false,
895
- "rstrip": false,
896
- "single_word": false,
897
- "special": true
898
- },
899
- "128112": {
900
- "content": "<|reserved_special_token_104|>",
901
- "lstrip": false,
902
- "normalized": false,
903
- "rstrip": false,
904
- "single_word": false,
905
- "special": true
906
- },
907
- "128113": {
908
- "content": "<|reserved_special_token_105|>",
909
- "lstrip": false,
910
- "normalized": false,
911
- "rstrip": false,
912
- "single_word": false,
913
- "special": true
914
- },
915
- "128114": {
916
- "content": "<|reserved_special_token_106|>",
917
- "lstrip": false,
918
- "normalized": false,
919
- "rstrip": false,
920
- "single_word": false,
921
- "special": true
922
- },
923
- "128115": {
924
- "content": "<|reserved_special_token_107|>",
925
- "lstrip": false,
926
- "normalized": false,
927
- "rstrip": false,
928
- "single_word": false,
929
- "special": true
930
- },
931
- "128116": {
932
- "content": "<|reserved_special_token_108|>",
933
- "lstrip": false,
934
- "normalized": false,
935
- "rstrip": false,
936
- "single_word": false,
937
- "special": true
938
- },
939
- "128117": {
940
- "content": "<|reserved_special_token_109|>",
941
- "lstrip": false,
942
- "normalized": false,
943
- "rstrip": false,
944
- "single_word": false,
945
- "special": true
946
- },
947
- "128118": {
948
- "content": "<|reserved_special_token_110|>",
949
- "lstrip": false,
950
- "normalized": false,
951
- "rstrip": false,
952
- "single_word": false,
953
- "special": true
954
- },
955
- "128119": {
956
- "content": "<|reserved_special_token_111|>",
957
- "lstrip": false,
958
- "normalized": false,
959
- "rstrip": false,
960
- "single_word": false,
961
- "special": true
962
- },
963
- "128120": {
964
- "content": "<|reserved_special_token_112|>",
965
- "lstrip": false,
966
- "normalized": false,
967
- "rstrip": false,
968
- "single_word": false,
969
- "special": true
970
- },
971
- "128121": {
972
- "content": "<|reserved_special_token_113|>",
973
- "lstrip": false,
974
- "normalized": false,
975
- "rstrip": false,
976
- "single_word": false,
977
- "special": true
978
- },
979
- "128122": {
980
- "content": "<|reserved_special_token_114|>",
981
- "lstrip": false,
982
- "normalized": false,
983
- "rstrip": false,
984
- "single_word": false,
985
- "special": true
986
- },
987
- "128123": {
988
- "content": "<|reserved_special_token_115|>",
989
- "lstrip": false,
990
- "normalized": false,
991
- "rstrip": false,
992
- "single_word": false,
993
- "special": true
994
- },
995
- "128124": {
996
- "content": "<|reserved_special_token_116|>",
997
- "lstrip": false,
998
- "normalized": false,
999
- "rstrip": false,
1000
- "single_word": false,
1001
- "special": true
1002
- },
1003
- "128125": {
1004
- "content": "<|reserved_special_token_117|>",
1005
- "lstrip": false,
1006
- "normalized": false,
1007
- "rstrip": false,
1008
- "single_word": false,
1009
- "special": true
1010
- },
1011
- "128126": {
1012
- "content": "<|reserved_special_token_118|>",
1013
- "lstrip": false,
1014
- "normalized": false,
1015
- "rstrip": false,
1016
- "single_word": false,
1017
- "special": true
1018
- },
1019
- "128127": {
1020
- "content": "<|reserved_special_token_119|>",
1021
- "lstrip": false,
1022
- "normalized": false,
1023
- "rstrip": false,
1024
- "single_word": false,
1025
- "special": true
1026
- },
1027
- "128128": {
1028
- "content": "<|reserved_special_token_120|>",
1029
- "lstrip": false,
1030
- "normalized": false,
1031
- "rstrip": false,
1032
- "single_word": false,
1033
- "special": true
1034
- },
1035
- "128129": {
1036
- "content": "<|reserved_special_token_121|>",
1037
- "lstrip": false,
1038
- "normalized": false,
1039
- "rstrip": false,
1040
- "single_word": false,
1041
- "special": true
1042
- },
1043
- "128130": {
1044
- "content": "<|reserved_special_token_122|>",
1045
- "lstrip": false,
1046
- "normalized": false,
1047
- "rstrip": false,
1048
- "single_word": false,
1049
- "special": true
1050
- },
1051
- "128131": {
1052
- "content": "<|reserved_special_token_123|>",
1053
- "lstrip": false,
1054
- "normalized": false,
1055
- "rstrip": false,
1056
- "single_word": false,
1057
- "special": true
1058
- },
1059
- "128132": {
1060
- "content": "<|reserved_special_token_124|>",
1061
- "lstrip": false,
1062
- "normalized": false,
1063
- "rstrip": false,
1064
- "single_word": false,
1065
- "special": true
1066
- },
1067
- "128133": {
1068
- "content": "<|reserved_special_token_125|>",
1069
- "lstrip": false,
1070
- "normalized": false,
1071
- "rstrip": false,
1072
- "single_word": false,
1073
- "special": true
1074
- },
1075
- "128134": {
1076
- "content": "<|reserved_special_token_126|>",
1077
- "lstrip": false,
1078
- "normalized": false,
1079
- "rstrip": false,
1080
- "single_word": false,
1081
- "special": true
1082
- },
1083
- "128135": {
1084
- "content": "<|reserved_special_token_127|>",
1085
- "lstrip": false,
1086
- "normalized": false,
1087
- "rstrip": false,
1088
- "single_word": false,
1089
- "special": true
1090
- },
1091
- "128136": {
1092
- "content": "<|reserved_special_token_128|>",
1093
- "lstrip": false,
1094
- "normalized": false,
1095
- "rstrip": false,
1096
- "single_word": false,
1097
- "special": true
1098
- },
1099
- "128137": {
1100
- "content": "<|reserved_special_token_129|>",
1101
- "lstrip": false,
1102
- "normalized": false,
1103
- "rstrip": false,
1104
- "single_word": false,
1105
- "special": true
1106
- },
1107
- "128138": {
1108
- "content": "<|reserved_special_token_130|>",
1109
- "lstrip": false,
1110
- "normalized": false,
1111
- "rstrip": false,
1112
- "single_word": false,
1113
- "special": true
1114
- },
1115
- "128139": {
1116
- "content": "<|reserved_special_token_131|>",
1117
- "lstrip": false,
1118
- "normalized": false,
1119
- "rstrip": false,
1120
- "single_word": false,
1121
- "special": true
1122
- },
1123
- "128140": {
1124
- "content": "<|reserved_special_token_132|>",
1125
- "lstrip": false,
1126
- "normalized": false,
1127
- "rstrip": false,
1128
- "single_word": false,
1129
- "special": true
1130
- },
1131
- "128141": {
1132
- "content": "<|reserved_special_token_133|>",
1133
- "lstrip": false,
1134
- "normalized": false,
1135
- "rstrip": false,
1136
- "single_word": false,
1137
- "special": true
1138
- },
1139
- "128142": {
1140
- "content": "<|reserved_special_token_134|>",
1141
- "lstrip": false,
1142
- "normalized": false,
1143
- "rstrip": false,
1144
- "single_word": false,
1145
- "special": true
1146
- },
1147
- "128143": {
1148
- "content": "<|reserved_special_token_135|>",
1149
- "lstrip": false,
1150
- "normalized": false,
1151
- "rstrip": false,
1152
- "single_word": false,
1153
- "special": true
1154
- },
1155
- "128144": {
1156
- "content": "<|reserved_special_token_136|>",
1157
- "lstrip": false,
1158
- "normalized": false,
1159
- "rstrip": false,
1160
- "single_word": false,
1161
- "special": true
1162
- },
1163
- "128145": {
1164
- "content": "<|reserved_special_token_137|>",
1165
- "lstrip": false,
1166
- "normalized": false,
1167
- "rstrip": false,
1168
- "single_word": false,
1169
- "special": true
1170
- },
1171
- "128146": {
1172
- "content": "<|reserved_special_token_138|>",
1173
- "lstrip": false,
1174
- "normalized": false,
1175
- "rstrip": false,
1176
- "single_word": false,
1177
- "special": true
1178
- },
1179
- "128147": {
1180
- "content": "<|reserved_special_token_139|>",
1181
- "lstrip": false,
1182
- "normalized": false,
1183
- "rstrip": false,
1184
- "single_word": false,
1185
- "special": true
1186
- },
1187
- "128148": {
1188
- "content": "<|reserved_special_token_140|>",
1189
- "lstrip": false,
1190
- "normalized": false,
1191
- "rstrip": false,
1192
- "single_word": false,
1193
- "special": true
1194
- },
1195
- "128149": {
1196
- "content": "<|reserved_special_token_141|>",
1197
- "lstrip": false,
1198
- "normalized": false,
1199
- "rstrip": false,
1200
- "single_word": false,
1201
- "special": true
1202
- },
1203
- "128150": {
1204
- "content": "<|reserved_special_token_142|>",
1205
- "lstrip": false,
1206
- "normalized": false,
1207
- "rstrip": false,
1208
- "single_word": false,
1209
- "special": true
1210
- },
1211
- "128151": {
1212
- "content": "<|reserved_special_token_143|>",
1213
- "lstrip": false,
1214
- "normalized": false,
1215
- "rstrip": false,
1216
- "single_word": false,
1217
- "special": true
1218
- },
1219
- "128152": {
1220
- "content": "<|reserved_special_token_144|>",
1221
- "lstrip": false,
1222
- "normalized": false,
1223
- "rstrip": false,
1224
- "single_word": false,
1225
- "special": true
1226
- },
1227
- "128153": {
1228
- "content": "<|reserved_special_token_145|>",
1229
- "lstrip": false,
1230
- "normalized": false,
1231
- "rstrip": false,
1232
- "single_word": false,
1233
- "special": true
1234
- },
1235
- "128154": {
1236
- "content": "<|reserved_special_token_146|>",
1237
- "lstrip": false,
1238
- "normalized": false,
1239
- "rstrip": false,
1240
- "single_word": false,
1241
- "special": true
1242
- },
1243
- "128155": {
1244
- "content": "<|reserved_special_token_147|>",
1245
- "lstrip": false,
1246
- "normalized": false,
1247
- "rstrip": false,
1248
- "single_word": false,
1249
- "special": true
1250
- },
1251
- "128156": {
1252
- "content": "<|reserved_special_token_148|>",
1253
- "lstrip": false,
1254
- "normalized": false,
1255
- "rstrip": false,
1256
- "single_word": false,
1257
- "special": true
1258
- },
1259
- "128157": {
1260
- "content": "<|reserved_special_token_149|>",
1261
- "lstrip": false,
1262
- "normalized": false,
1263
- "rstrip": false,
1264
- "single_word": false,
1265
- "special": true
1266
- },
1267
- "128158": {
1268
- "content": "<|reserved_special_token_150|>",
1269
- "lstrip": false,
1270
- "normalized": false,
1271
- "rstrip": false,
1272
- "single_word": false,
1273
- "special": true
1274
- },
1275
- "128159": {
1276
- "content": "<|reserved_special_token_151|>",
1277
- "lstrip": false,
1278
- "normalized": false,
1279
- "rstrip": false,
1280
- "single_word": false,
1281
- "special": true
1282
- },
1283
- "128160": {
1284
- "content": "<|reserved_special_token_152|>",
1285
- "lstrip": false,
1286
- "normalized": false,
1287
- "rstrip": false,
1288
- "single_word": false,
1289
- "special": true
1290
- },
1291
- "128161": {
1292
- "content": "<|reserved_special_token_153|>",
1293
- "lstrip": false,
1294
- "normalized": false,
1295
- "rstrip": false,
1296
- "single_word": false,
1297
- "special": true
1298
- },
1299
- "128162": {
1300
- "content": "<|reserved_special_token_154|>",
1301
- "lstrip": false,
1302
- "normalized": false,
1303
- "rstrip": false,
1304
- "single_word": false,
1305
- "special": true
1306
- },
1307
- "128163": {
1308
- "content": "<|reserved_special_token_155|>",
1309
- "lstrip": false,
1310
- "normalized": false,
1311
- "rstrip": false,
1312
- "single_word": false,
1313
- "special": true
1314
- },
1315
- "128164": {
1316
- "content": "<|reserved_special_token_156|>",
1317
- "lstrip": false,
1318
- "normalized": false,
1319
- "rstrip": false,
1320
- "single_word": false,
1321
- "special": true
1322
- },
1323
- "128165": {
1324
- "content": "<|reserved_special_token_157|>",
1325
- "lstrip": false,
1326
- "normalized": false,
1327
- "rstrip": false,
1328
- "single_word": false,
1329
- "special": true
1330
- },
1331
- "128166": {
1332
- "content": "<|reserved_special_token_158|>",
1333
- "lstrip": false,
1334
- "normalized": false,
1335
- "rstrip": false,
1336
- "single_word": false,
1337
- "special": true
1338
- },
1339
- "128167": {
1340
- "content": "<|reserved_special_token_159|>",
1341
- "lstrip": false,
1342
- "normalized": false,
1343
- "rstrip": false,
1344
- "single_word": false,
1345
- "special": true
1346
- },
1347
- "128168": {
1348
- "content": "<|reserved_special_token_160|>",
1349
- "lstrip": false,
1350
- "normalized": false,
1351
- "rstrip": false,
1352
- "single_word": false,
1353
- "special": true
1354
- },
1355
- "128169": {
1356
- "content": "<|reserved_special_token_161|>",
1357
- "lstrip": false,
1358
- "normalized": false,
1359
- "rstrip": false,
1360
- "single_word": false,
1361
- "special": true
1362
- },
1363
- "128170": {
1364
- "content": "<|reserved_special_token_162|>",
1365
- "lstrip": false,
1366
- "normalized": false,
1367
- "rstrip": false,
1368
- "single_word": false,
1369
- "special": true
1370
- },
1371
- "128171": {
1372
- "content": "<|reserved_special_token_163|>",
1373
- "lstrip": false,
1374
- "normalized": false,
1375
- "rstrip": false,
1376
- "single_word": false,
1377
- "special": true
1378
- },
1379
- "128172": {
1380
- "content": "<|reserved_special_token_164|>",
1381
- "lstrip": false,
1382
- "normalized": false,
1383
- "rstrip": false,
1384
- "single_word": false,
1385
- "special": true
1386
- },
1387
- "128173": {
1388
- "content": "<|reserved_special_token_165|>",
1389
- "lstrip": false,
1390
- "normalized": false,
1391
- "rstrip": false,
1392
- "single_word": false,
1393
- "special": true
1394
- },
1395
- "128174": {
1396
- "content": "<|reserved_special_token_166|>",
1397
- "lstrip": false,
1398
- "normalized": false,
1399
- "rstrip": false,
1400
- "single_word": false,
1401
- "special": true
1402
- },
1403
- "128175": {
1404
- "content": "<|reserved_special_token_167|>",
1405
- "lstrip": false,
1406
- "normalized": false,
1407
- "rstrip": false,
1408
- "single_word": false,
1409
- "special": true
1410
- },
1411
- "128176": {
1412
- "content": "<|reserved_special_token_168|>",
1413
- "lstrip": false,
1414
- "normalized": false,
1415
- "rstrip": false,
1416
- "single_word": false,
1417
- "special": true
1418
- },
1419
- "128177": {
1420
- "content": "<|reserved_special_token_169|>",
1421
- "lstrip": false,
1422
- "normalized": false,
1423
- "rstrip": false,
1424
- "single_word": false,
1425
- "special": true
1426
- },
1427
- "128178": {
1428
- "content": "<|reserved_special_token_170|>",
1429
- "lstrip": false,
1430
- "normalized": false,
1431
- "rstrip": false,
1432
- "single_word": false,
1433
- "special": true
1434
- },
1435
- "128179": {
1436
- "content": "<|reserved_special_token_171|>",
1437
- "lstrip": false,
1438
- "normalized": false,
1439
- "rstrip": false,
1440
- "single_word": false,
1441
- "special": true
1442
- },
1443
- "128180": {
1444
- "content": "<|reserved_special_token_172|>",
1445
- "lstrip": false,
1446
- "normalized": false,
1447
- "rstrip": false,
1448
- "single_word": false,
1449
- "special": true
1450
- },
1451
- "128181": {
1452
- "content": "<|reserved_special_token_173|>",
1453
- "lstrip": false,
1454
- "normalized": false,
1455
- "rstrip": false,
1456
- "single_word": false,
1457
- "special": true
1458
- },
1459
- "128182": {
1460
- "content": "<|reserved_special_token_174|>",
1461
- "lstrip": false,
1462
- "normalized": false,
1463
- "rstrip": false,
1464
- "single_word": false,
1465
- "special": true
1466
- },
1467
- "128183": {
1468
- "content": "<|reserved_special_token_175|>",
1469
- "lstrip": false,
1470
- "normalized": false,
1471
- "rstrip": false,
1472
- "single_word": false,
1473
- "special": true
1474
- },
1475
- "128184": {
1476
- "content": "<|reserved_special_token_176|>",
1477
- "lstrip": false,
1478
- "normalized": false,
1479
- "rstrip": false,
1480
- "single_word": false,
1481
- "special": true
1482
- },
1483
- "128185": {
1484
- "content": "<|reserved_special_token_177|>",
1485
- "lstrip": false,
1486
- "normalized": false,
1487
- "rstrip": false,
1488
- "single_word": false,
1489
- "special": true
1490
- },
1491
- "128186": {
1492
- "content": "<|reserved_special_token_178|>",
1493
- "lstrip": false,
1494
- "normalized": false,
1495
- "rstrip": false,
1496
- "single_word": false,
1497
- "special": true
1498
- },
1499
- "128187": {
1500
- "content": "<|reserved_special_token_179|>",
1501
- "lstrip": false,
1502
- "normalized": false,
1503
- "rstrip": false,
1504
- "single_word": false,
1505
- "special": true
1506
- },
1507
- "128188": {
1508
- "content": "<|reserved_special_token_180|>",
1509
- "lstrip": false,
1510
- "normalized": false,
1511
- "rstrip": false,
1512
- "single_word": false,
1513
- "special": true
1514
- },
1515
- "128189": {
1516
- "content": "<|reserved_special_token_181|>",
1517
- "lstrip": false,
1518
- "normalized": false,
1519
- "rstrip": false,
1520
- "single_word": false,
1521
- "special": true
1522
- },
1523
- "128190": {
1524
- "content": "<|reserved_special_token_182|>",
1525
- "lstrip": false,
1526
- "normalized": false,
1527
- "rstrip": false,
1528
- "single_word": false,
1529
- "special": true
1530
- },
1531
- "128191": {
1532
- "content": "<|reserved_special_token_183|>",
1533
- "lstrip": false,
1534
- "normalized": false,
1535
- "rstrip": false,
1536
- "single_word": false,
1537
- "special": true
1538
- },
1539
- "128192": {
1540
- "content": "<|reserved_special_token_184|>",
1541
- "lstrip": false,
1542
- "normalized": false,
1543
- "rstrip": false,
1544
- "single_word": false,
1545
- "special": true
1546
- },
1547
- "128193": {
1548
- "content": "<|reserved_special_token_185|>",
1549
- "lstrip": false,
1550
- "normalized": false,
1551
- "rstrip": false,
1552
- "single_word": false,
1553
- "special": true
1554
- },
1555
- "128194": {
1556
- "content": "<|reserved_special_token_186|>",
1557
- "lstrip": false,
1558
- "normalized": false,
1559
- "rstrip": false,
1560
- "single_word": false,
1561
- "special": true
1562
- },
1563
- "128195": {
1564
- "content": "<|reserved_special_token_187|>",
1565
- "lstrip": false,
1566
- "normalized": false,
1567
- "rstrip": false,
1568
- "single_word": false,
1569
- "special": true
1570
- },
1571
- "128196": {
1572
- "content": "<|reserved_special_token_188|>",
1573
- "lstrip": false,
1574
- "normalized": false,
1575
- "rstrip": false,
1576
- "single_word": false,
1577
- "special": true
1578
- },
1579
- "128197": {
1580
- "content": "<|reserved_special_token_189|>",
1581
- "lstrip": false,
1582
- "normalized": false,
1583
- "rstrip": false,
1584
- "single_word": false,
1585
- "special": true
1586
- },
1587
- "128198": {
1588
- "content": "<|reserved_special_token_190|>",
1589
- "lstrip": false,
1590
- "normalized": false,
1591
- "rstrip": false,
1592
- "single_word": false,
1593
- "special": true
1594
- },
1595
- "128199": {
1596
- "content": "<|reserved_special_token_191|>",
1597
- "lstrip": false,
1598
- "normalized": false,
1599
- "rstrip": false,
1600
- "single_word": false,
1601
- "special": true
1602
- },
1603
- "128200": {
1604
- "content": "<|reserved_special_token_192|>",
1605
- "lstrip": false,
1606
- "normalized": false,
1607
- "rstrip": false,
1608
- "single_word": false,
1609
- "special": true
1610
- },
1611
- "128201": {
1612
- "content": "<|reserved_special_token_193|>",
1613
- "lstrip": false,
1614
- "normalized": false,
1615
- "rstrip": false,
1616
- "single_word": false,
1617
- "special": true
1618
- },
1619
- "128202": {
1620
- "content": "<|reserved_special_token_194|>",
1621
- "lstrip": false,
1622
- "normalized": false,
1623
- "rstrip": false,
1624
- "single_word": false,
1625
- "special": true
1626
- },
1627
- "128203": {
1628
- "content": "<|reserved_special_token_195|>",
1629
- "lstrip": false,
1630
- "normalized": false,
1631
- "rstrip": false,
1632
- "single_word": false,
1633
- "special": true
1634
- },
1635
- "128204": {
1636
- "content": "<|reserved_special_token_196|>",
1637
- "lstrip": false,
1638
- "normalized": false,
1639
- "rstrip": false,
1640
- "single_word": false,
1641
- "special": true
1642
- },
1643
- "128205": {
1644
- "content": "<|reserved_special_token_197|>",
1645
- "lstrip": false,
1646
- "normalized": false,
1647
- "rstrip": false,
1648
- "single_word": false,
1649
- "special": true
1650
- },
1651
- "128206": {
1652
- "content": "<|reserved_special_token_198|>",
1653
- "lstrip": false,
1654
- "normalized": false,
1655
- "rstrip": false,
1656
- "single_word": false,
1657
- "special": true
1658
- },
1659
- "128207": {
1660
- "content": "<|reserved_special_token_199|>",
1661
- "lstrip": false,
1662
- "normalized": false,
1663
- "rstrip": false,
1664
- "single_word": false,
1665
- "special": true
1666
- },
1667
- "128208": {
1668
- "content": "<|reserved_special_token_200|>",
1669
- "lstrip": false,
1670
- "normalized": false,
1671
- "rstrip": false,
1672
- "single_word": false,
1673
- "special": true
1674
- },
1675
- "128209": {
1676
- "content": "<|reserved_special_token_201|>",
1677
- "lstrip": false,
1678
- "normalized": false,
1679
- "rstrip": false,
1680
- "single_word": false,
1681
- "special": true
1682
- },
1683
- "128210": {
1684
- "content": "<|reserved_special_token_202|>",
1685
- "lstrip": false,
1686
- "normalized": false,
1687
- "rstrip": false,
1688
- "single_word": false,
1689
- "special": true
1690
- },
1691
- "128211": {
1692
- "content": "<|reserved_special_token_203|>",
1693
- "lstrip": false,
1694
- "normalized": false,
1695
- "rstrip": false,
1696
- "single_word": false,
1697
- "special": true
1698
- },
1699
- "128212": {
1700
- "content": "<|reserved_special_token_204|>",
1701
- "lstrip": false,
1702
- "normalized": false,
1703
- "rstrip": false,
1704
- "single_word": false,
1705
- "special": true
1706
- },
1707
- "128213": {
1708
- "content": "<|reserved_special_token_205|>",
1709
- "lstrip": false,
1710
- "normalized": false,
1711
- "rstrip": false,
1712
- "single_word": false,
1713
- "special": true
1714
- },
1715
- "128214": {
1716
- "content": "<|reserved_special_token_206|>",
1717
- "lstrip": false,
1718
- "normalized": false,
1719
- "rstrip": false,
1720
- "single_word": false,
1721
- "special": true
1722
- },
1723
- "128215": {
1724
- "content": "<|reserved_special_token_207|>",
1725
- "lstrip": false,
1726
- "normalized": false,
1727
- "rstrip": false,
1728
- "single_word": false,
1729
- "special": true
1730
- },
1731
- "128216": {
1732
- "content": "<|reserved_special_token_208|>",
1733
- "lstrip": false,
1734
- "normalized": false,
1735
- "rstrip": false,
1736
- "single_word": false,
1737
- "special": true
1738
- },
1739
- "128217": {
1740
- "content": "<|reserved_special_token_209|>",
1741
- "lstrip": false,
1742
- "normalized": false,
1743
- "rstrip": false,
1744
- "single_word": false,
1745
- "special": true
1746
- },
1747
- "128218": {
1748
- "content": "<|reserved_special_token_210|>",
1749
- "lstrip": false,
1750
- "normalized": false,
1751
- "rstrip": false,
1752
- "single_word": false,
1753
- "special": true
1754
- },
1755
- "128219": {
1756
- "content": "<|reserved_special_token_211|>",
1757
- "lstrip": false,
1758
- "normalized": false,
1759
- "rstrip": false,
1760
- "single_word": false,
1761
- "special": true
1762
- },
1763
- "128220": {
1764
- "content": "<|reserved_special_token_212|>",
1765
- "lstrip": false,
1766
- "normalized": false,
1767
- "rstrip": false,
1768
- "single_word": false,
1769
- "special": true
1770
- },
1771
- "128221": {
1772
- "content": "<|reserved_special_token_213|>",
1773
- "lstrip": false,
1774
- "normalized": false,
1775
- "rstrip": false,
1776
- "single_word": false,
1777
- "special": true
1778
- },
1779
- "128222": {
1780
- "content": "<|reserved_special_token_214|>",
1781
- "lstrip": false,
1782
- "normalized": false,
1783
- "rstrip": false,
1784
- "single_word": false,
1785
- "special": true
1786
- },
1787
- "128223": {
1788
- "content": "<|reserved_special_token_215|>",
1789
- "lstrip": false,
1790
- "normalized": false,
1791
- "rstrip": false,
1792
- "single_word": false,
1793
- "special": true
1794
- },
1795
- "128224": {
1796
- "content": "<|reserved_special_token_216|>",
1797
- "lstrip": false,
1798
- "normalized": false,
1799
- "rstrip": false,
1800
- "single_word": false,
1801
- "special": true
1802
- },
1803
- "128225": {
1804
- "content": "<|reserved_special_token_217|>",
1805
- "lstrip": false,
1806
- "normalized": false,
1807
- "rstrip": false,
1808
- "single_word": false,
1809
- "special": true
1810
- },
1811
- "128226": {
1812
- "content": "<|reserved_special_token_218|>",
1813
- "lstrip": false,
1814
- "normalized": false,
1815
- "rstrip": false,
1816
- "single_word": false,
1817
- "special": true
1818
- },
1819
- "128227": {
1820
- "content": "<|reserved_special_token_219|>",
1821
- "lstrip": false,
1822
- "normalized": false,
1823
- "rstrip": false,
1824
- "single_word": false,
1825
- "special": true
1826
- },
1827
- "128228": {
1828
- "content": "<|reserved_special_token_220|>",
1829
- "lstrip": false,
1830
- "normalized": false,
1831
- "rstrip": false,
1832
- "single_word": false,
1833
- "special": true
1834
- },
1835
- "128229": {
1836
- "content": "<|reserved_special_token_221|>",
1837
- "lstrip": false,
1838
- "normalized": false,
1839
- "rstrip": false,
1840
- "single_word": false,
1841
- "special": true
1842
- },
1843
- "128230": {
1844
- "content": "<|reserved_special_token_222|>",
1845
- "lstrip": false,
1846
- "normalized": false,
1847
- "rstrip": false,
1848
- "single_word": false,
1849
- "special": true
1850
- },
1851
- "128231": {
1852
- "content": "<|reserved_special_token_223|>",
1853
- "lstrip": false,
1854
- "normalized": false,
1855
- "rstrip": false,
1856
- "single_word": false,
1857
- "special": true
1858
- },
1859
- "128232": {
1860
- "content": "<|reserved_special_token_224|>",
1861
- "lstrip": false,
1862
- "normalized": false,
1863
- "rstrip": false,
1864
- "single_word": false,
1865
- "special": true
1866
- },
1867
- "128233": {
1868
- "content": "<|reserved_special_token_225|>",
1869
- "lstrip": false,
1870
- "normalized": false,
1871
- "rstrip": false,
1872
- "single_word": false,
1873
- "special": true
1874
- },
1875
- "128234": {
1876
- "content": "<|reserved_special_token_226|>",
1877
- "lstrip": false,
1878
- "normalized": false,
1879
- "rstrip": false,
1880
- "single_word": false,
1881
- "special": true
1882
- },
1883
- "128235": {
1884
- "content": "<|reserved_special_token_227|>",
1885
- "lstrip": false,
1886
- "normalized": false,
1887
- "rstrip": false,
1888
- "single_word": false,
1889
- "special": true
1890
- },
1891
- "128236": {
1892
- "content": "<|reserved_special_token_228|>",
1893
- "lstrip": false,
1894
- "normalized": false,
1895
- "rstrip": false,
1896
- "single_word": false,
1897
- "special": true
1898
- },
1899
- "128237": {
1900
- "content": "<|reserved_special_token_229|>",
1901
- "lstrip": false,
1902
- "normalized": false,
1903
- "rstrip": false,
1904
- "single_word": false,
1905
- "special": true
1906
- },
1907
- "128238": {
1908
- "content": "<|reserved_special_token_230|>",
1909
- "lstrip": false,
1910
- "normalized": false,
1911
- "rstrip": false,
1912
- "single_word": false,
1913
- "special": true
1914
- },
1915
- "128239": {
1916
- "content": "<|reserved_special_token_231|>",
1917
- "lstrip": false,
1918
- "normalized": false,
1919
- "rstrip": false,
1920
- "single_word": false,
1921
- "special": true
1922
- },
1923
- "128240": {
1924
- "content": "<|reserved_special_token_232|>",
1925
- "lstrip": false,
1926
- "normalized": false,
1927
- "rstrip": false,
1928
- "single_word": false,
1929
- "special": true
1930
- },
1931
- "128241": {
1932
- "content": "<|reserved_special_token_233|>",
1933
- "lstrip": false,
1934
- "normalized": false,
1935
- "rstrip": false,
1936
- "single_word": false,
1937
- "special": true
1938
- },
1939
- "128242": {
1940
- "content": "<|reserved_special_token_234|>",
1941
- "lstrip": false,
1942
- "normalized": false,
1943
- "rstrip": false,
1944
- "single_word": false,
1945
- "special": true
1946
- },
1947
- "128243": {
1948
- "content": "<|reserved_special_token_235|>",
1949
- "lstrip": false,
1950
- "normalized": false,
1951
- "rstrip": false,
1952
- "single_word": false,
1953
- "special": true
1954
- },
1955
- "128244": {
1956
- "content": "<|reserved_special_token_236|>",
1957
- "lstrip": false,
1958
- "normalized": false,
1959
- "rstrip": false,
1960
- "single_word": false,
1961
- "special": true
1962
- },
1963
- "128245": {
1964
- "content": "<|reserved_special_token_237|>",
1965
- "lstrip": false,
1966
- "normalized": false,
1967
- "rstrip": false,
1968
- "single_word": false,
1969
- "special": true
1970
- },
1971
- "128246": {
1972
- "content": "<|reserved_special_token_238|>",
1973
- "lstrip": false,
1974
- "normalized": false,
1975
- "rstrip": false,
1976
- "single_word": false,
1977
- "special": true
1978
- },
1979
- "128247": {
1980
- "content": "<|reserved_special_token_239|>",
1981
- "lstrip": false,
1982
- "normalized": false,
1983
- "rstrip": false,
1984
- "single_word": false,
1985
- "special": true
1986
- },
1987
- "128248": {
1988
- "content": "<|reserved_special_token_240|>",
1989
- "lstrip": false,
1990
- "normalized": false,
1991
- "rstrip": false,
1992
- "single_word": false,
1993
- "special": true
1994
- },
1995
- "128249": {
1996
- "content": "<|reserved_special_token_241|>",
1997
- "lstrip": false,
1998
- "normalized": false,
1999
- "rstrip": false,
2000
- "single_word": false,
2001
- "special": true
2002
- },
2003
- "128250": {
2004
- "content": "<|reserved_special_token_242|>",
2005
- "lstrip": false,
2006
- "normalized": false,
2007
- "rstrip": false,
2008
- "single_word": false,
2009
- "special": true
2010
- },
2011
- "128251": {
2012
- "content": "<|reserved_special_token_243|>",
2013
- "lstrip": false,
2014
- "normalized": false,
2015
- "rstrip": false,
2016
- "single_word": false,
2017
- "special": true
2018
- },
2019
- "128252": {
2020
- "content": "<|reserved_special_token_244|>",
2021
- "lstrip": false,
2022
- "normalized": false,
2023
- "rstrip": false,
2024
- "single_word": false,
2025
- "special": true
2026
- },
2027
- "128253": {
2028
- "content": "<|reserved_special_token_245|>",
2029
- "lstrip": false,
2030
- "normalized": false,
2031
- "rstrip": false,
2032
- "single_word": false,
2033
- "special": true
2034
- },
2035
- "128254": {
2036
- "content": "<|reserved_special_token_246|>",
2037
- "lstrip": false,
2038
- "normalized": false,
2039
- "rstrip": false,
2040
- "single_word": false,
2041
- "special": true
2042
- },
2043
- "128255": {
2044
- "content": "<|reserved_special_token_247|>",
2045
- "lstrip": false,
2046
- "normalized": false,
2047
- "rstrip": false,
2048
- "single_word": false,
2049
- "special": true
2050
- }
2051
- },
2052
- "bos_token": "<|begin_of_text|>",
2053
- "clean_up_tokenization_spaces": true,
2054
- "eos_token": "<|eot_id|>",
2055
- "extra_special_tokens": {},
2056
- "model_input_names": [
2057
- "input_ids",
2058
- "attention_mask"
2059
- ],
2060
- "model_max_length": 131072,
2061
- "pad_token": "<|eot_id|>",
2062
- "tokenizer_class": "PreTrainedTokenizerFast"
2063
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw6.65_5-6-7-8bit/README.md DELETED
@@ -1,17 +0,0 @@
1
- # Quantized Model Checkpoint
2
-
3
- **Base model:** meta-llama/Llama-3.1-8B-Instruct
4
-
5
- **Average bitwidth:** 6.6454
6
-
7
- **Sensitivity method:** shapley
8
-
9
- **Constraints:**
10
- - max_kl: 0.01
11
- - min_eap: 0.99
12
-
13
- **Metrics:**
14
- - predicted_kl: 0.001530
15
- - predicted_eap: 0.990005
16
-
17
- See `quantization_config.txt` for full configuration details.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw6.65_5-6-7-8bit/chat_template.jinja DELETED
@@ -1,109 +0,0 @@
1
- {{- bos_token }}
2
- {%- if custom_tools is defined %}
3
- {%- set tools = custom_tools %}
4
- {%- endif %}
5
- {%- if not tools_in_user_message is defined %}
6
- {%- set tools_in_user_message = true %}
7
- {%- endif %}
8
- {%- if not date_string is defined %}
9
- {%- set date_string = "26 Jul 2024" %}
10
- {%- endif %}
11
- {%- if not tools is defined %}
12
- {%- set tools = none %}
13
- {%- endif %}
14
-
15
- {#- This block extracts the system message, so we can slot it into the right place. #}
16
- {%- if messages[0]['role'] == 'system' %}
17
- {%- set system_message = messages[0]['content']|trim %}
18
- {%- set messages = messages[1:] %}
19
- {%- else %}
20
- {%- set system_message = "" %}
21
- {%- endif %}
22
-
23
- {#- System message + builtin tools #}
24
- {{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
25
- {%- if builtin_tools is defined or tools is not none %}
26
- {{- "Environment: ipython\n" }}
27
- {%- endif %}
28
- {%- if builtin_tools is defined %}
29
- {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
30
- {%- endif %}
31
- {{- "Cutting Knowledge Date: December 2023\n" }}
32
- {{- "Today Date: " + date_string + "\n\n" }}
33
- {%- if tools is not none and not tools_in_user_message %}
34
- {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
35
- {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
36
- {{- "Do not use variables.\n\n" }}
37
- {%- for t in tools %}
38
- {{- t | tojson(indent=4) }}
39
- {{- "\n\n" }}
40
- {%- endfor %}
41
- {%- endif %}
42
- {{- system_message }}
43
- {{- "<|eot_id|>" }}
44
-
45
- {#- Custom tools are passed in a user message with some extra guidance #}
46
- {%- if tools_in_user_message and not tools is none %}
47
- {#- Extract the first user message so we can plug it in here #}
48
- {%- if messages | length != 0 %}
49
- {%- set first_user_message = messages[0]['content']|trim %}
50
- {%- set messages = messages[1:] %}
51
- {%- else %}
52
- {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
53
- {%- endif %}
54
- {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
55
- {{- "Given the following functions, please respond with a JSON for a function call " }}
56
- {{- "with its proper arguments that best answers the given prompt.\n\n" }}
57
- {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
58
- {{- "Do not use variables.\n\n" }}
59
- {%- for t in tools %}
60
- {{- t | tojson(indent=4) }}
61
- {{- "\n\n" }}
62
- {%- endfor %}
63
- {{- first_user_message + "<|eot_id|>"}}
64
- {%- endif %}
65
-
66
- {%- for message in messages %}
67
- {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
68
- {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
69
- {%- elif 'tool_calls' in message %}
70
- {%- if not message.tool_calls|length == 1 %}
71
- {{- raise_exception("This model only supports single tool-calls at once!") }}
72
- {%- endif %}
73
- {%- set tool_call = message.tool_calls[0].function %}
74
- {%- if builtin_tools is defined and tool_call.name in builtin_tools %}
75
- {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
76
- {{- "<|python_tag|>" + tool_call.name + ".call(" }}
77
- {%- for arg_name, arg_val in tool_call.arguments | items %}
78
- {{- arg_name + '="' + arg_val + '"' }}
79
- {%- if not loop.last %}
80
- {{- ", " }}
81
- {%- endif %}
82
- {%- endfor %}
83
- {{- ")" }}
84
- {%- else %}
85
- {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
86
- {{- '{"name": "' + tool_call.name + '", ' }}
87
- {{- '"parameters": ' }}
88
- {{- tool_call.arguments | tojson }}
89
- {{- "}" }}
90
- {%- endif %}
91
- {%- if builtin_tools is defined %}
92
- {#- This means we're in ipython mode #}
93
- {{- "<|eom_id|>" }}
94
- {%- else %}
95
- {{- "<|eot_id|>" }}
96
- {%- endif %}
97
- {%- elif message.role == "tool" or message.role == "ipython" %}
98
- {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
99
- {%- if message.content is mapping or message.content is iterable %}
100
- {{- message.content | tojson }}
101
- {%- else %}
102
- {{- message.content }}
103
- {%- endif %}
104
- {{- "<|eot_id|>" }}
105
- {%- endif %}
106
- {%- endfor %}
107
- {%- if add_generation_prompt %}
108
- {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
109
- {%- endif %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw6.65_5-6-7-8bit/config.json DELETED
@@ -1,39 +0,0 @@
1
- {
2
- "architectures": [
3
- "LlamaForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 128000,
8
- "dtype": "float16",
9
- "eos_token_id": [
10
- 128001,
11
- 128008,
12
- 128009
13
- ],
14
- "head_dim": 128,
15
- "hidden_act": "silu",
16
- "hidden_size": 4096,
17
- "initializer_range": 0.02,
18
- "intermediate_size": 14336,
19
- "max_position_embeddings": 131072,
20
- "mlp_bias": false,
21
- "model_type": "llama",
22
- "num_attention_heads": 32,
23
- "num_hidden_layers": 32,
24
- "num_key_value_heads": 8,
25
- "pretraining_tp": 1,
26
- "rms_norm_eps": 1e-05,
27
- "rope_scaling": {
28
- "factor": 8.0,
29
- "high_freq_factor": 4.0,
30
- "low_freq_factor": 1.0,
31
- "original_max_position_embeddings": 8192,
32
- "rope_type": "llama3"
33
- },
34
- "rope_theta": 500000.0,
35
- "tie_word_embeddings": false,
36
- "transformers_version": "4.57.3",
37
- "use_cache": false,
38
- "vocab_size": 128256
39
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw6.65_5-6-7-8bit/generation_config.json DELETED
@@ -1,12 +0,0 @@
1
- {
2
- "bos_token_id": 128000,
3
- "do_sample": true,
4
- "eos_token_id": [
5
- 128001,
6
- 128008,
7
- 128009
8
- ],
9
- "temperature": 0.6,
10
- "top_p": 0.9,
11
- "transformers_version": "4.57.3"
12
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw6.65_5-6-7-8bit/model-00001-of-00004.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:87a988f90d2be901de9c23896e8d909980ebf5e7f2ed2a0a5cddd9598caf5188
3
- size 4976698592
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw6.65_5-6-7-8bit/model-00002-of-00004.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:59e48041230a2cfe3f447d5d8fc881647a42e27bd910e8bfebebee50797814c8
3
- size 4999802616
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw6.65_5-6-7-8bit/model-00003-of-00004.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e4ea4b99fc0060c4cb60868a42fc01bb7f28d6138bc8746f00d0ef780541c36
3
- size 4915916080
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw6.65_5-6-7-8bit/model-00004-of-00004.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:44408391c116c33adf6e43ab53f84d75bee5e2956b293c34dc60509fb0fd825b
3
- size 1168138808
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw6.65_5-6-7-8bit/model.safetensors.index.json DELETED
@@ -1,299 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_parameters": 8030261248,
4
- "total_size": 16060522496
5
- },
6
- "weight_map": {
7
- "lm_head.weight": "model-00004-of-00004.safetensors",
8
- "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
- "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
17
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
18
- "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
19
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
20
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
21
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
22
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
23
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
24
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
25
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
26
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
27
- "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
28
- "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
29
- "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
30
- "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
31
- "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
32
- "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
33
- "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
34
- "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
35
- "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
36
- "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
37
- "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
38
- "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
39
- "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
40
- "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
41
- "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
42
- "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
43
- "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
44
- "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
45
- "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
46
- "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
47
- "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
48
- "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
49
- "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
50
- "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
- "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
- "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
53
- "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
54
- "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
55
- "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
56
- "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
57
- "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
58
- "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
59
- "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
60
- "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
61
- "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
62
- "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
63
- "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
64
- "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
65
- "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
66
- "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
67
- "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
68
- "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
69
- "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
70
- "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
71
- "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
72
- "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
73
- "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
74
- "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
75
- "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
76
- "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
77
- "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
78
- "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
79
- "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
80
- "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
81
- "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
82
- "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
83
- "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
84
- "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
85
- "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
86
- "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
- "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
- "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
89
- "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
90
- "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
91
- "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
92
- "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
93
- "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
94
- "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
95
- "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
96
- "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
97
- "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
98
- "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
99
- "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
100
- "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
101
- "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
102
- "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
103
- "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
104
- "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
105
- "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
106
- "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
107
- "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
108
- "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
109
- "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
110
- "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
111
- "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
112
- "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
113
- "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
114
- "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
115
- "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
116
- "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
117
- "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
118
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
119
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
120
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
121
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
122
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
123
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
124
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
125
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
126
- "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
127
- "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
128
- "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
129
- "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
130
- "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
131
- "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
132
- "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
133
- "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
134
- "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
135
- "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
136
- "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
137
- "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
138
- "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
139
- "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
140
- "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
141
- "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
142
- "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
143
- "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
144
- "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
145
- "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
146
- "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
147
- "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
148
- "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
149
- "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
150
- "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
151
- "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
152
- "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
153
- "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
154
- "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
155
- "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
156
- "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
157
- "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
158
- "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
159
- "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
160
- "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
161
- "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
162
- "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
163
- "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
164
- "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
165
- "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
166
- "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
167
- "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
168
- "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
169
- "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
170
- "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
171
- "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
172
- "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
173
- "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
174
- "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
175
- "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
176
- "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
177
- "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
178
- "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
179
- "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
180
- "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
181
- "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
182
- "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
183
- "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
184
- "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
185
- "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
186
- "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
187
- "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
188
- "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
189
- "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
190
- "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
191
- "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
192
- "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
193
- "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
194
- "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
- "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
- "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
197
- "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
198
- "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
199
- "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
200
- "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
201
- "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
202
- "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
203
- "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
204
- "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
205
- "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
206
- "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
207
- "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
208
- "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
209
- "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
210
- "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
211
- "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
212
- "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
213
- "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
214
- "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
215
- "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
216
- "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
217
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
218
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
219
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
220
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
221
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
222
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
223
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
224
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
225
- "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
226
- "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
227
- "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
228
- "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
229
- "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
230
- "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
- "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
- "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
233
- "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
234
- "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
235
- "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
236
- "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
237
- "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
238
- "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
239
- "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
240
- "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
241
- "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
242
- "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
243
- "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
244
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
245
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
246
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
247
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
248
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
249
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
250
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
251
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
252
- "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
253
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
254
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
255
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
256
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
257
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
258
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
259
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
260
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
261
- "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
262
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
263
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
264
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
265
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
266
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
269
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
270
- "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
271
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
272
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
273
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
274
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
275
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
276
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
277
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
278
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
279
- "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
280
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
281
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
282
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
283
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
284
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
285
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
286
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
287
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
288
- "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
289
- "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
290
- "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
291
- "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
292
- "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
293
- "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
294
- "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
295
- "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
296
- "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
297
- "model.norm.weight": "model-00004-of-00004.safetensors"
298
- }
299
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw6.65_5-6-7-8bit/quantization_config.txt DELETED
@@ -1,252 +0,0 @@
1
- # Model: meta-llama/Llama-3.1-8B-Instruct
2
- # Layer directory: /nfs/scistore19/alistgrp/mhelcig/local/data/search/4_5_6_7_8bit_asym_g128/Llama-3.1-8B-Instruct/6bit/
3
- # Sensitivity method: shapley
4
- # Estimation method: permutation_separate
5
- # Available bitwidths: [4, 5, 6, 7, 8]
6
- # Bitwidth map: {4: 4.3125, 5: 5.3125, 6: 6.3125, 7: 7.3125, 8: 8.3125}
7
- #
8
- # Mode: predicted_constraint_search
9
- # Constraint max_kl: 0.01
10
- # Constraint min_eap: 0.99
11
- # Weights: nll=0.0, kl=0.0, eap=1.0
12
- #
13
- # Average bitwidth: 6.6454
14
- # Total params: 6979321856
15
- # Total bits: 46380613632
16
- # Predicted KL: 0.001530
17
- # Predicted EAP: 0.990005
18
- # Predicted ETL: 0.009995
19
- # Satisfies constraints: True
20
- # Solver calls: 1
21
- # Evaluations: 0
22
- #
23
- # Bitwidth distribution:
24
- # 8-bit: 86 layers (38.4%)
25
- # 7-bit: 50 layers (22.3%)
26
- # 6-bit: 83 layers (37.1%)
27
- # 5-bit: 5 layers (2.2%)
28
- #
29
- model.layers.0.self_attn.q_proj: 7
30
- model.layers.0.self_attn.k_proj: 8
31
- model.layers.0.self_attn.v_proj: 8
32
- model.layers.0.self_attn.o_proj: 7
33
- model.layers.0.mlp.gate_proj: 6
34
- model.layers.0.mlp.up_proj: 6
35
- model.layers.0.mlp.down_proj: 6
36
- model.layers.1.self_attn.q_proj: 8
37
- model.layers.1.self_attn.k_proj: 8
38
- model.layers.1.self_attn.v_proj: 8
39
- model.layers.1.self_attn.o_proj: 7
40
- model.layers.1.mlp.gate_proj: 6
41
- model.layers.1.mlp.up_proj: 6
42
- model.layers.1.mlp.down_proj: 8
43
- model.layers.2.self_attn.q_proj: 8
44
- model.layers.2.self_attn.k_proj: 8
45
- model.layers.2.self_attn.v_proj: 8
46
- model.layers.2.self_attn.o_proj: 7
47
- model.layers.2.mlp.gate_proj: 6
48
- model.layers.2.mlp.up_proj: 6
49
- model.layers.2.mlp.down_proj: 6
50
- model.layers.3.self_attn.q_proj: 7
51
- model.layers.3.self_attn.k_proj: 8
52
- model.layers.3.self_attn.v_proj: 8
53
- model.layers.3.self_attn.o_proj: 7
54
- model.layers.3.mlp.gate_proj: 6
55
- model.layers.3.mlp.up_proj: 6
56
- model.layers.3.mlp.down_proj: 6
57
- model.layers.4.self_attn.q_proj: 7
58
- model.layers.4.self_attn.k_proj: 8
59
- model.layers.4.self_attn.v_proj: 8
60
- model.layers.4.self_attn.o_proj: 7
61
- model.layers.4.mlp.gate_proj: 6
62
- model.layers.4.mlp.up_proj: 6
63
- model.layers.4.mlp.down_proj: 6
64
- model.layers.5.self_attn.q_proj: 7
65
- model.layers.5.self_attn.k_proj: 8
66
- model.layers.5.self_attn.v_proj: 8
67
- model.layers.5.self_attn.o_proj: 7
68
- model.layers.5.mlp.gate_proj: 6
69
- model.layers.5.mlp.up_proj: 6
70
- model.layers.5.mlp.down_proj: 6
71
- model.layers.6.self_attn.q_proj: 7
72
- model.layers.6.self_attn.k_proj: 8
73
- model.layers.6.self_attn.v_proj: 8
74
- model.layers.6.self_attn.o_proj: 7
75
- model.layers.6.mlp.gate_proj: 7
76
- model.layers.6.mlp.up_proj: 7
77
- model.layers.6.mlp.down_proj: 6
78
- model.layers.7.self_attn.q_proj: 8
79
- model.layers.7.self_attn.k_proj: 8
80
- model.layers.7.self_attn.v_proj: 8
81
- model.layers.7.self_attn.o_proj: 7
82
- model.layers.7.mlp.gate_proj: 6
83
- model.layers.7.mlp.up_proj: 6
84
- model.layers.7.mlp.down_proj: 6
85
- model.layers.8.self_attn.q_proj: 8
86
- model.layers.8.self_attn.k_proj: 8
87
- model.layers.8.self_attn.v_proj: 8
88
- model.layers.8.self_attn.o_proj: 7
89
- model.layers.8.mlp.gate_proj: 6
90
- model.layers.8.mlp.up_proj: 6
91
- model.layers.8.mlp.down_proj: 6
92
- model.layers.9.self_attn.q_proj: 8
93
- model.layers.9.self_attn.k_proj: 8
94
- model.layers.9.self_attn.v_proj: 8
95
- model.layers.9.self_attn.o_proj: 7
96
- model.layers.9.mlp.gate_proj: 6
97
- model.layers.9.mlp.up_proj: 6
98
- model.layers.9.mlp.down_proj: 6
99
- model.layers.10.self_attn.q_proj: 8
100
- model.layers.10.self_attn.k_proj: 8
101
- model.layers.10.self_attn.v_proj: 8
102
- model.layers.10.self_attn.o_proj: 7
103
- model.layers.10.mlp.gate_proj: 6
104
- model.layers.10.mlp.up_proj: 6
105
- model.layers.10.mlp.down_proj: 6
106
- model.layers.11.self_attn.q_proj: 8
107
- model.layers.11.self_attn.k_proj: 8
108
- model.layers.11.self_attn.v_proj: 8
109
- model.layers.11.self_attn.o_proj: 7
110
- model.layers.11.mlp.gate_proj: 6
111
- model.layers.11.mlp.up_proj: 6
112
- model.layers.11.mlp.down_proj: 6
113
- model.layers.12.self_attn.q_proj: 8
114
- model.layers.12.self_attn.k_proj: 8
115
- model.layers.12.self_attn.v_proj: 8
116
- model.layers.12.self_attn.o_proj: 7
117
- model.layers.12.mlp.gate_proj: 6
118
- model.layers.12.mlp.up_proj: 6
119
- model.layers.12.mlp.down_proj: 6
120
- model.layers.13.self_attn.q_proj: 8
121
- model.layers.13.self_attn.k_proj: 8
122
- model.layers.13.self_attn.v_proj: 8
123
- model.layers.13.self_attn.o_proj: 7
124
- model.layers.13.mlp.gate_proj: 6
125
- model.layers.13.mlp.up_proj: 6
126
- model.layers.13.mlp.down_proj: 6
127
- model.layers.14.self_attn.q_proj: 8
128
- model.layers.14.self_attn.k_proj: 8
129
- model.layers.14.self_attn.v_proj: 8
130
- model.layers.14.self_attn.o_proj: 7
131
- model.layers.14.mlp.gate_proj: 6
132
- model.layers.14.mlp.up_proj: 6
133
- model.layers.14.mlp.down_proj: 6
134
- model.layers.15.self_attn.q_proj: 8
135
- model.layers.15.self_attn.k_proj: 8
136
- model.layers.15.self_attn.v_proj: 8
137
- model.layers.15.self_attn.o_proj: 7
138
- model.layers.15.mlp.gate_proj: 6
139
- model.layers.15.mlp.up_proj: 6
140
- model.layers.15.mlp.down_proj: 6
141
- model.layers.16.self_attn.q_proj: 8
142
- model.layers.16.self_attn.k_proj: 8
143
- model.layers.16.self_attn.v_proj: 8
144
- model.layers.16.self_attn.o_proj: 7
145
- model.layers.16.mlp.gate_proj: 6
146
- model.layers.16.mlp.up_proj: 6
147
- model.layers.16.mlp.down_proj: 6
148
- model.layers.17.self_attn.q_proj: 8
149
- model.layers.17.self_attn.k_proj: 8
150
- model.layers.17.self_attn.v_proj: 8
151
- model.layers.17.self_attn.o_proj: 7
152
- model.layers.17.mlp.gate_proj: 6
153
- model.layers.17.mlp.up_proj: 6
154
- model.layers.17.mlp.down_proj: 6
155
- model.layers.18.self_attn.q_proj: 8
156
- model.layers.18.self_attn.k_proj: 8
157
- model.layers.18.self_attn.v_proj: 8
158
- model.layers.18.self_attn.o_proj: 7
159
- model.layers.18.mlp.gate_proj: 6
160
- model.layers.18.mlp.up_proj: 6
161
- model.layers.18.mlp.down_proj: 6
162
- model.layers.19.self_attn.q_proj: 8
163
- model.layers.19.self_attn.k_proj: 8
164
- model.layers.19.self_attn.v_proj: 8
165
- model.layers.19.self_attn.o_proj: 7
166
- model.layers.19.mlp.gate_proj: 6
167
- model.layers.19.mlp.up_proj: 6
168
- model.layers.19.mlp.down_proj: 6
169
- model.layers.20.self_attn.q_proj: 7
170
- model.layers.20.self_attn.k_proj: 8
171
- model.layers.20.self_attn.v_proj: 8
172
- model.layers.20.self_attn.o_proj: 7
173
- model.layers.20.mlp.gate_proj: 6
174
- model.layers.20.mlp.up_proj: 6
175
- model.layers.20.mlp.down_proj: 6
176
- model.layers.21.self_attn.q_proj: 8
177
- model.layers.21.self_attn.k_proj: 8
178
- model.layers.21.self_attn.v_proj: 8
179
- model.layers.21.self_attn.o_proj: 7
180
- model.layers.21.mlp.gate_proj: 6
181
- model.layers.21.mlp.up_proj: 6
182
- model.layers.21.mlp.down_proj: 6
183
- model.layers.22.self_attn.q_proj: 7
184
- model.layers.22.self_attn.k_proj: 8
185
- model.layers.22.self_attn.v_proj: 8
186
- model.layers.22.self_attn.o_proj: 7
187
- model.layers.22.mlp.gate_proj: 6
188
- model.layers.22.mlp.up_proj: 6
189
- model.layers.22.mlp.down_proj: 6
190
- model.layers.23.self_attn.q_proj: 8
191
- model.layers.23.self_attn.k_proj: 8
192
- model.layers.23.self_attn.v_proj: 8
193
- model.layers.23.self_attn.o_proj: 7
194
- model.layers.23.mlp.gate_proj: 6
195
- model.layers.23.mlp.up_proj: 6
196
- model.layers.23.mlp.down_proj: 6
197
- model.layers.24.self_attn.q_proj: 7
198
- model.layers.24.self_attn.k_proj: 8
199
- model.layers.24.self_attn.v_proj: 8
200
- model.layers.24.self_attn.o_proj: 7
201
- model.layers.24.mlp.gate_proj: 5
202
- model.layers.24.mlp.up_proj: 5
203
- model.layers.24.mlp.down_proj: 5
204
- model.layers.25.self_attn.q_proj: 8
205
- model.layers.25.self_attn.k_proj: 8
206
- model.layers.25.self_attn.v_proj: 8
207
- model.layers.25.self_attn.o_proj: 7
208
- model.layers.25.mlp.gate_proj: 6
209
- model.layers.25.mlp.up_proj: 6
210
- model.layers.25.mlp.down_proj: 6
211
- model.layers.26.self_attn.q_proj: 7
212
- model.layers.26.self_attn.k_proj: 8
213
- model.layers.26.self_attn.v_proj: 8
214
- model.layers.26.self_attn.o_proj: 7
215
- model.layers.26.mlp.gate_proj: 6
216
- model.layers.26.mlp.up_proj: 6
217
- model.layers.26.mlp.down_proj: 5
218
- model.layers.27.self_attn.q_proj: 7
219
- model.layers.27.self_attn.k_proj: 8
220
- model.layers.27.self_attn.v_proj: 8
221
- model.layers.27.self_attn.o_proj: 7
222
- model.layers.27.mlp.gate_proj: 6
223
- model.layers.27.mlp.up_proj: 6
224
- model.layers.27.mlp.down_proj: 5
225
- model.layers.28.self_attn.q_proj: 7
226
- model.layers.28.self_attn.k_proj: 8
227
- model.layers.28.self_attn.v_proj: 8
228
- model.layers.28.self_attn.o_proj: 7
229
- model.layers.28.mlp.gate_proj: 6
230
- model.layers.28.mlp.up_proj: 6
231
- model.layers.28.mlp.down_proj: 6
232
- model.layers.29.self_attn.q_proj: 7
233
- model.layers.29.self_attn.k_proj: 8
234
- model.layers.29.self_attn.v_proj: 8
235
- model.layers.29.self_attn.o_proj: 7
236
- model.layers.29.mlp.gate_proj: 6
237
- model.layers.29.mlp.up_proj: 6
238
- model.layers.29.mlp.down_proj: 6
239
- model.layers.30.self_attn.q_proj: 7
240
- model.layers.30.self_attn.k_proj: 8
241
- model.layers.30.self_attn.v_proj: 8
242
- model.layers.30.self_attn.o_proj: 7
243
- model.layers.30.mlp.gate_proj: 7
244
- model.layers.30.mlp.up_proj: 7
245
- model.layers.30.mlp.down_proj: 6
246
- model.layers.31.self_attn.q_proj: 7
247
- model.layers.31.self_attn.k_proj: 8
248
- model.layers.31.self_attn.v_proj: 8
249
- model.layers.31.self_attn.o_proj: 7
250
- model.layers.31.mlp.gate_proj: 8
251
- model.layers.31.mlp.up_proj: 8
252
- model.layers.31.mlp.down_proj: 8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw6.65_5-6-7-8bit/special_tokens_map.json DELETED
@@ -1,17 +0,0 @@
1
- {
2
- "bos_token": {
3
- "content": "<|begin_of_text|>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "<|eot_id|>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": "<|eot_id|>"
17
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw6.65_5-6-7-8bit/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
- size 17209920
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw6.65_5-6-7-8bit/tokenizer_config.json DELETED
@@ -1,2063 +0,0 @@
1
- {
2
- "added_tokens_decoder": {
3
- "128000": {
4
- "content": "<|begin_of_text|>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "128001": {
12
- "content": "<|end_of_text|>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "128002": {
20
- "content": "<|reserved_special_token_0|>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "128003": {
28
- "content": "<|reserved_special_token_1|>",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "128004": {
36
- "content": "<|finetune_right_pad_id|>",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- },
43
- "128005": {
44
- "content": "<|reserved_special_token_2|>",
45
- "lstrip": false,
46
- "normalized": false,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": true
50
- },
51
- "128006": {
52
- "content": "<|start_header_id|>",
53
- "lstrip": false,
54
- "normalized": false,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": true
58
- },
59
- "128007": {
60
- "content": "<|end_header_id|>",
61
- "lstrip": false,
62
- "normalized": false,
63
- "rstrip": false,
64
- "single_word": false,
65
- "special": true
66
- },
67
- "128008": {
68
- "content": "<|eom_id|>",
69
- "lstrip": false,
70
- "normalized": false,
71
- "rstrip": false,
72
- "single_word": false,
73
- "special": true
74
- },
75
- "128009": {
76
- "content": "<|eot_id|>",
77
- "lstrip": false,
78
- "normalized": false,
79
- "rstrip": false,
80
- "single_word": false,
81
- "special": true
82
- },
83
- "128010": {
84
- "content": "<|python_tag|>",
85
- "lstrip": false,
86
- "normalized": false,
87
- "rstrip": false,
88
- "single_word": false,
89
- "special": true
90
- },
91
- "128011": {
92
- "content": "<|reserved_special_token_3|>",
93
- "lstrip": false,
94
- "normalized": false,
95
- "rstrip": false,
96
- "single_word": false,
97
- "special": true
98
- },
99
- "128012": {
100
- "content": "<|reserved_special_token_4|>",
101
- "lstrip": false,
102
- "normalized": false,
103
- "rstrip": false,
104
- "single_word": false,
105
- "special": true
106
- },
107
- "128013": {
108
- "content": "<|reserved_special_token_5|>",
109
- "lstrip": false,
110
- "normalized": false,
111
- "rstrip": false,
112
- "single_word": false,
113
- "special": true
114
- },
115
- "128014": {
116
- "content": "<|reserved_special_token_6|>",
117
- "lstrip": false,
118
- "normalized": false,
119
- "rstrip": false,
120
- "single_word": false,
121
- "special": true
122
- },
123
- "128015": {
124
- "content": "<|reserved_special_token_7|>",
125
- "lstrip": false,
126
- "normalized": false,
127
- "rstrip": false,
128
- "single_word": false,
129
- "special": true
130
- },
131
- "128016": {
132
- "content": "<|reserved_special_token_8|>",
133
- "lstrip": false,
134
- "normalized": false,
135
- "rstrip": false,
136
- "single_word": false,
137
- "special": true
138
- },
139
- "128017": {
140
- "content": "<|reserved_special_token_9|>",
141
- "lstrip": false,
142
- "normalized": false,
143
- "rstrip": false,
144
- "single_word": false,
145
- "special": true
146
- },
147
- "128018": {
148
- "content": "<|reserved_special_token_10|>",
149
- "lstrip": false,
150
- "normalized": false,
151
- "rstrip": false,
152
- "single_word": false,
153
- "special": true
154
- },
155
- "128019": {
156
- "content": "<|reserved_special_token_11|>",
157
- "lstrip": false,
158
- "normalized": false,
159
- "rstrip": false,
160
- "single_word": false,
161
- "special": true
162
- },
163
- "128020": {
164
- "content": "<|reserved_special_token_12|>",
165
- "lstrip": false,
166
- "normalized": false,
167
- "rstrip": false,
168
- "single_word": false,
169
- "special": true
170
- },
171
- "128021": {
172
- "content": "<|reserved_special_token_13|>",
173
- "lstrip": false,
174
- "normalized": false,
175
- "rstrip": false,
176
- "single_word": false,
177
- "special": true
178
- },
179
- "128022": {
180
- "content": "<|reserved_special_token_14|>",
181
- "lstrip": false,
182
- "normalized": false,
183
- "rstrip": false,
184
- "single_word": false,
185
- "special": true
186
- },
187
- "128023": {
188
- "content": "<|reserved_special_token_15|>",
189
- "lstrip": false,
190
- "normalized": false,
191
- "rstrip": false,
192
- "single_word": false,
193
- "special": true
194
- },
195
- "128024": {
196
- "content": "<|reserved_special_token_16|>",
197
- "lstrip": false,
198
- "normalized": false,
199
- "rstrip": false,
200
- "single_word": false,
201
- "special": true
202
- },
203
- "128025": {
204
- "content": "<|reserved_special_token_17|>",
205
- "lstrip": false,
206
- "normalized": false,
207
- "rstrip": false,
208
- "single_word": false,
209
- "special": true
210
- },
211
- "128026": {
212
- "content": "<|reserved_special_token_18|>",
213
- "lstrip": false,
214
- "normalized": false,
215
- "rstrip": false,
216
- "single_word": false,
217
- "special": true
218
- },
219
- "128027": {
220
- "content": "<|reserved_special_token_19|>",
221
- "lstrip": false,
222
- "normalized": false,
223
- "rstrip": false,
224
- "single_word": false,
225
- "special": true
226
- },
227
- "128028": {
228
- "content": "<|reserved_special_token_20|>",
229
- "lstrip": false,
230
- "normalized": false,
231
- "rstrip": false,
232
- "single_word": false,
233
- "special": true
234
- },
235
- "128029": {
236
- "content": "<|reserved_special_token_21|>",
237
- "lstrip": false,
238
- "normalized": false,
239
- "rstrip": false,
240
- "single_word": false,
241
- "special": true
242
- },
243
- "128030": {
244
- "content": "<|reserved_special_token_22|>",
245
- "lstrip": false,
246
- "normalized": false,
247
- "rstrip": false,
248
- "single_word": false,
249
- "special": true
250
- },
251
- "128031": {
252
- "content": "<|reserved_special_token_23|>",
253
- "lstrip": false,
254
- "normalized": false,
255
- "rstrip": false,
256
- "single_word": false,
257
- "special": true
258
- },
259
- "128032": {
260
- "content": "<|reserved_special_token_24|>",
261
- "lstrip": false,
262
- "normalized": false,
263
- "rstrip": false,
264
- "single_word": false,
265
- "special": true
266
- },
267
- "128033": {
268
- "content": "<|reserved_special_token_25|>",
269
- "lstrip": false,
270
- "normalized": false,
271
- "rstrip": false,
272
- "single_word": false,
273
- "special": true
274
- },
275
- "128034": {
276
- "content": "<|reserved_special_token_26|>",
277
- "lstrip": false,
278
- "normalized": false,
279
- "rstrip": false,
280
- "single_word": false,
281
- "special": true
282
- },
283
- "128035": {
284
- "content": "<|reserved_special_token_27|>",
285
- "lstrip": false,
286
- "normalized": false,
287
- "rstrip": false,
288
- "single_word": false,
289
- "special": true
290
- },
291
- "128036": {
292
- "content": "<|reserved_special_token_28|>",
293
- "lstrip": false,
294
- "normalized": false,
295
- "rstrip": false,
296
- "single_word": false,
297
- "special": true
298
- },
299
- "128037": {
300
- "content": "<|reserved_special_token_29|>",
301
- "lstrip": false,
302
- "normalized": false,
303
- "rstrip": false,
304
- "single_word": false,
305
- "special": true
306
- },
307
- "128038": {
308
- "content": "<|reserved_special_token_30|>",
309
- "lstrip": false,
310
- "normalized": false,
311
- "rstrip": false,
312
- "single_word": false,
313
- "special": true
314
- },
315
- "128039": {
316
- "content": "<|reserved_special_token_31|>",
317
- "lstrip": false,
318
- "normalized": false,
319
- "rstrip": false,
320
- "single_word": false,
321
- "special": true
322
- },
323
- "128040": {
324
- "content": "<|reserved_special_token_32|>",
325
- "lstrip": false,
326
- "normalized": false,
327
- "rstrip": false,
328
- "single_word": false,
329
- "special": true
330
- },
331
- "128041": {
332
- "content": "<|reserved_special_token_33|>",
333
- "lstrip": false,
334
- "normalized": false,
335
- "rstrip": false,
336
- "single_word": false,
337
- "special": true
338
- },
339
- "128042": {
340
- "content": "<|reserved_special_token_34|>",
341
- "lstrip": false,
342
- "normalized": false,
343
- "rstrip": false,
344
- "single_word": false,
345
- "special": true
346
- },
347
- "128043": {
348
- "content": "<|reserved_special_token_35|>",
349
- "lstrip": false,
350
- "normalized": false,
351
- "rstrip": false,
352
- "single_word": false,
353
- "special": true
354
- },
355
- "128044": {
356
- "content": "<|reserved_special_token_36|>",
357
- "lstrip": false,
358
- "normalized": false,
359
- "rstrip": false,
360
- "single_word": false,
361
- "special": true
362
- },
363
- "128045": {
364
- "content": "<|reserved_special_token_37|>",
365
- "lstrip": false,
366
- "normalized": false,
367
- "rstrip": false,
368
- "single_word": false,
369
- "special": true
370
- },
371
- "128046": {
372
- "content": "<|reserved_special_token_38|>",
373
- "lstrip": false,
374
- "normalized": false,
375
- "rstrip": false,
376
- "single_word": false,
377
- "special": true
378
- },
379
- "128047": {
380
- "content": "<|reserved_special_token_39|>",
381
- "lstrip": false,
382
- "normalized": false,
383
- "rstrip": false,
384
- "single_word": false,
385
- "special": true
386
- },
387
- "128048": {
388
- "content": "<|reserved_special_token_40|>",
389
- "lstrip": false,
390
- "normalized": false,
391
- "rstrip": false,
392
- "single_word": false,
393
- "special": true
394
- },
395
- "128049": {
396
- "content": "<|reserved_special_token_41|>",
397
- "lstrip": false,
398
- "normalized": false,
399
- "rstrip": false,
400
- "single_word": false,
401
- "special": true
402
- },
403
- "128050": {
404
- "content": "<|reserved_special_token_42|>",
405
- "lstrip": false,
406
- "normalized": false,
407
- "rstrip": false,
408
- "single_word": false,
409
- "special": true
410
- },
411
- "128051": {
412
- "content": "<|reserved_special_token_43|>",
413
- "lstrip": false,
414
- "normalized": false,
415
- "rstrip": false,
416
- "single_word": false,
417
- "special": true
418
- },
419
- "128052": {
420
- "content": "<|reserved_special_token_44|>",
421
- "lstrip": false,
422
- "normalized": false,
423
- "rstrip": false,
424
- "single_word": false,
425
- "special": true
426
- },
427
- "128053": {
428
- "content": "<|reserved_special_token_45|>",
429
- "lstrip": false,
430
- "normalized": false,
431
- "rstrip": false,
432
- "single_word": false,
433
- "special": true
434
- },
435
- "128054": {
436
- "content": "<|reserved_special_token_46|>",
437
- "lstrip": false,
438
- "normalized": false,
439
- "rstrip": false,
440
- "single_word": false,
441
- "special": true
442
- },
443
- "128055": {
444
- "content": "<|reserved_special_token_47|>",
445
- "lstrip": false,
446
- "normalized": false,
447
- "rstrip": false,
448
- "single_word": false,
449
- "special": true
450
- },
451
- "128056": {
452
- "content": "<|reserved_special_token_48|>",
453
- "lstrip": false,
454
- "normalized": false,
455
- "rstrip": false,
456
- "single_word": false,
457
- "special": true
458
- },
459
- "128057": {
460
- "content": "<|reserved_special_token_49|>",
461
- "lstrip": false,
462
- "normalized": false,
463
- "rstrip": false,
464
- "single_word": false,
465
- "special": true
466
- },
467
- "128058": {
468
- "content": "<|reserved_special_token_50|>",
469
- "lstrip": false,
470
- "normalized": false,
471
- "rstrip": false,
472
- "single_word": false,
473
- "special": true
474
- },
475
- "128059": {
476
- "content": "<|reserved_special_token_51|>",
477
- "lstrip": false,
478
- "normalized": false,
479
- "rstrip": false,
480
- "single_word": false,
481
- "special": true
482
- },
483
- "128060": {
484
- "content": "<|reserved_special_token_52|>",
485
- "lstrip": false,
486
- "normalized": false,
487
- "rstrip": false,
488
- "single_word": false,
489
- "special": true
490
- },
491
- "128061": {
492
- "content": "<|reserved_special_token_53|>",
493
- "lstrip": false,
494
- "normalized": false,
495
- "rstrip": false,
496
- "single_word": false,
497
- "special": true
498
- },
499
- "128062": {
500
- "content": "<|reserved_special_token_54|>",
501
- "lstrip": false,
502
- "normalized": false,
503
- "rstrip": false,
504
- "single_word": false,
505
- "special": true
506
- },
507
- "128063": {
508
- "content": "<|reserved_special_token_55|>",
509
- "lstrip": false,
510
- "normalized": false,
511
- "rstrip": false,
512
- "single_word": false,
513
- "special": true
514
- },
515
- "128064": {
516
- "content": "<|reserved_special_token_56|>",
517
- "lstrip": false,
518
- "normalized": false,
519
- "rstrip": false,
520
- "single_word": false,
521
- "special": true
522
- },
523
- "128065": {
524
- "content": "<|reserved_special_token_57|>",
525
- "lstrip": false,
526
- "normalized": false,
527
- "rstrip": false,
528
- "single_word": false,
529
- "special": true
530
- },
531
- "128066": {
532
- "content": "<|reserved_special_token_58|>",
533
- "lstrip": false,
534
- "normalized": false,
535
- "rstrip": false,
536
- "single_word": false,
537
- "special": true
538
- },
539
- "128067": {
540
- "content": "<|reserved_special_token_59|>",
541
- "lstrip": false,
542
- "normalized": false,
543
- "rstrip": false,
544
- "single_word": false,
545
- "special": true
546
- },
547
- "128068": {
548
- "content": "<|reserved_special_token_60|>",
549
- "lstrip": false,
550
- "normalized": false,
551
- "rstrip": false,
552
- "single_word": false,
553
- "special": true
554
- },
555
- "128069": {
556
- "content": "<|reserved_special_token_61|>",
557
- "lstrip": false,
558
- "normalized": false,
559
- "rstrip": false,
560
- "single_word": false,
561
- "special": true
562
- },
563
- "128070": {
564
- "content": "<|reserved_special_token_62|>",
565
- "lstrip": false,
566
- "normalized": false,
567
- "rstrip": false,
568
- "single_word": false,
569
- "special": true
570
- },
571
- "128071": {
572
- "content": "<|reserved_special_token_63|>",
573
- "lstrip": false,
574
- "normalized": false,
575
- "rstrip": false,
576
- "single_word": false,
577
- "special": true
578
- },
579
- "128072": {
580
- "content": "<|reserved_special_token_64|>",
581
- "lstrip": false,
582
- "normalized": false,
583
- "rstrip": false,
584
- "single_word": false,
585
- "special": true
586
- },
587
- "128073": {
588
- "content": "<|reserved_special_token_65|>",
589
- "lstrip": false,
590
- "normalized": false,
591
- "rstrip": false,
592
- "single_word": false,
593
- "special": true
594
- },
595
- "128074": {
596
- "content": "<|reserved_special_token_66|>",
597
- "lstrip": false,
598
- "normalized": false,
599
- "rstrip": false,
600
- "single_word": false,
601
- "special": true
602
- },
603
- "128075": {
604
- "content": "<|reserved_special_token_67|>",
605
- "lstrip": false,
606
- "normalized": false,
607
- "rstrip": false,
608
- "single_word": false,
609
- "special": true
610
- },
611
- "128076": {
612
- "content": "<|reserved_special_token_68|>",
613
- "lstrip": false,
614
- "normalized": false,
615
- "rstrip": false,
616
- "single_word": false,
617
- "special": true
618
- },
619
- "128077": {
620
- "content": "<|reserved_special_token_69|>",
621
- "lstrip": false,
622
- "normalized": false,
623
- "rstrip": false,
624
- "single_word": false,
625
- "special": true
626
- },
627
- "128078": {
628
- "content": "<|reserved_special_token_70|>",
629
- "lstrip": false,
630
- "normalized": false,
631
- "rstrip": false,
632
- "single_word": false,
633
- "special": true
634
- },
635
- "128079": {
636
- "content": "<|reserved_special_token_71|>",
637
- "lstrip": false,
638
- "normalized": false,
639
- "rstrip": false,
640
- "single_word": false,
641
- "special": true
642
- },
643
- "128080": {
644
- "content": "<|reserved_special_token_72|>",
645
- "lstrip": false,
646
- "normalized": false,
647
- "rstrip": false,
648
- "single_word": false,
649
- "special": true
650
- },
651
- "128081": {
652
- "content": "<|reserved_special_token_73|>",
653
- "lstrip": false,
654
- "normalized": false,
655
- "rstrip": false,
656
- "single_word": false,
657
- "special": true
658
- },
659
- "128082": {
660
- "content": "<|reserved_special_token_74|>",
661
- "lstrip": false,
662
- "normalized": false,
663
- "rstrip": false,
664
- "single_word": false,
665
- "special": true
666
- },
667
- "128083": {
668
- "content": "<|reserved_special_token_75|>",
669
- "lstrip": false,
670
- "normalized": false,
671
- "rstrip": false,
672
- "single_word": false,
673
- "special": true
674
- },
675
- "128084": {
676
- "content": "<|reserved_special_token_76|>",
677
- "lstrip": false,
678
- "normalized": false,
679
- "rstrip": false,
680
- "single_word": false,
681
- "special": true
682
- },
683
- "128085": {
684
- "content": "<|reserved_special_token_77|>",
685
- "lstrip": false,
686
- "normalized": false,
687
- "rstrip": false,
688
- "single_word": false,
689
- "special": true
690
- },
691
- "128086": {
692
- "content": "<|reserved_special_token_78|>",
693
- "lstrip": false,
694
- "normalized": false,
695
- "rstrip": false,
696
- "single_word": false,
697
- "special": true
698
- },
699
- "128087": {
700
- "content": "<|reserved_special_token_79|>",
701
- "lstrip": false,
702
- "normalized": false,
703
- "rstrip": false,
704
- "single_word": false,
705
- "special": true
706
- },
707
- "128088": {
708
- "content": "<|reserved_special_token_80|>",
709
- "lstrip": false,
710
- "normalized": false,
711
- "rstrip": false,
712
- "single_word": false,
713
- "special": true
714
- },
715
- "128089": {
716
- "content": "<|reserved_special_token_81|>",
717
- "lstrip": false,
718
- "normalized": false,
719
- "rstrip": false,
720
- "single_word": false,
721
- "special": true
722
- },
723
- "128090": {
724
- "content": "<|reserved_special_token_82|>",
725
- "lstrip": false,
726
- "normalized": false,
727
- "rstrip": false,
728
- "single_word": false,
729
- "special": true
730
- },
731
- "128091": {
732
- "content": "<|reserved_special_token_83|>",
733
- "lstrip": false,
734
- "normalized": false,
735
- "rstrip": false,
736
- "single_word": false,
737
- "special": true
738
- },
739
- "128092": {
740
- "content": "<|reserved_special_token_84|>",
741
- "lstrip": false,
742
- "normalized": false,
743
- "rstrip": false,
744
- "single_word": false,
745
- "special": true
746
- },
747
- "128093": {
748
- "content": "<|reserved_special_token_85|>",
749
- "lstrip": false,
750
- "normalized": false,
751
- "rstrip": false,
752
- "single_word": false,
753
- "special": true
754
- },
755
- "128094": {
756
- "content": "<|reserved_special_token_86|>",
757
- "lstrip": false,
758
- "normalized": false,
759
- "rstrip": false,
760
- "single_word": false,
761
- "special": true
762
- },
763
- "128095": {
764
- "content": "<|reserved_special_token_87|>",
765
- "lstrip": false,
766
- "normalized": false,
767
- "rstrip": false,
768
- "single_word": false,
769
- "special": true
770
- },
771
- "128096": {
772
- "content": "<|reserved_special_token_88|>",
773
- "lstrip": false,
774
- "normalized": false,
775
- "rstrip": false,
776
- "single_word": false,
777
- "special": true
778
- },
779
- "128097": {
780
- "content": "<|reserved_special_token_89|>",
781
- "lstrip": false,
782
- "normalized": false,
783
- "rstrip": false,
784
- "single_word": false,
785
- "special": true
786
- },
787
- "128098": {
788
- "content": "<|reserved_special_token_90|>",
789
- "lstrip": false,
790
- "normalized": false,
791
- "rstrip": false,
792
- "single_word": false,
793
- "special": true
794
- },
795
- "128099": {
796
- "content": "<|reserved_special_token_91|>",
797
- "lstrip": false,
798
- "normalized": false,
799
- "rstrip": false,
800
- "single_word": false,
801
- "special": true
802
- },
803
- "128100": {
804
- "content": "<|reserved_special_token_92|>",
805
- "lstrip": false,
806
- "normalized": false,
807
- "rstrip": false,
808
- "single_word": false,
809
- "special": true
810
- },
811
- "128101": {
812
- "content": "<|reserved_special_token_93|>",
813
- "lstrip": false,
814
- "normalized": false,
815
- "rstrip": false,
816
- "single_word": false,
817
- "special": true
818
- },
819
- "128102": {
820
- "content": "<|reserved_special_token_94|>",
821
- "lstrip": false,
822
- "normalized": false,
823
- "rstrip": false,
824
- "single_word": false,
825
- "special": true
826
- },
827
- "128103": {
828
- "content": "<|reserved_special_token_95|>",
829
- "lstrip": false,
830
- "normalized": false,
831
- "rstrip": false,
832
- "single_word": false,
833
- "special": true
834
- },
835
- "128104": {
836
- "content": "<|reserved_special_token_96|>",
837
- "lstrip": false,
838
- "normalized": false,
839
- "rstrip": false,
840
- "single_word": false,
841
- "special": true
842
- },
843
- "128105": {
844
- "content": "<|reserved_special_token_97|>",
845
- "lstrip": false,
846
- "normalized": false,
847
- "rstrip": false,
848
- "single_word": false,
849
- "special": true
850
- },
851
- "128106": {
852
- "content": "<|reserved_special_token_98|>",
853
- "lstrip": false,
854
- "normalized": false,
855
- "rstrip": false,
856
- "single_word": false,
857
- "special": true
858
- },
859
- "128107": {
860
- "content": "<|reserved_special_token_99|>",
861
- "lstrip": false,
862
- "normalized": false,
863
- "rstrip": false,
864
- "single_word": false,
865
- "special": true
866
- },
867
- "128108": {
868
- "content": "<|reserved_special_token_100|>",
869
- "lstrip": false,
870
- "normalized": false,
871
- "rstrip": false,
872
- "single_word": false,
873
- "special": true
874
- },
875
- "128109": {
876
- "content": "<|reserved_special_token_101|>",
877
- "lstrip": false,
878
- "normalized": false,
879
- "rstrip": false,
880
- "single_word": false,
881
- "special": true
882
- },
883
- "128110": {
884
- "content": "<|reserved_special_token_102|>",
885
- "lstrip": false,
886
- "normalized": false,
887
- "rstrip": false,
888
- "single_word": false,
889
- "special": true
890
- },
891
- "128111": {
892
- "content": "<|reserved_special_token_103|>",
893
- "lstrip": false,
894
- "normalized": false,
895
- "rstrip": false,
896
- "single_word": false,
897
- "special": true
898
- },
899
- "128112": {
900
- "content": "<|reserved_special_token_104|>",
901
- "lstrip": false,
902
- "normalized": false,
903
- "rstrip": false,
904
- "single_word": false,
905
- "special": true
906
- },
907
- "128113": {
908
- "content": "<|reserved_special_token_105|>",
909
- "lstrip": false,
910
- "normalized": false,
911
- "rstrip": false,
912
- "single_word": false,
913
- "special": true
914
- },
915
- "128114": {
916
- "content": "<|reserved_special_token_106|>",
917
- "lstrip": false,
918
- "normalized": false,
919
- "rstrip": false,
920
- "single_word": false,
921
- "special": true
922
- },
923
- "128115": {
924
- "content": "<|reserved_special_token_107|>",
925
- "lstrip": false,
926
- "normalized": false,
927
- "rstrip": false,
928
- "single_word": false,
929
- "special": true
930
- },
931
- "128116": {
932
- "content": "<|reserved_special_token_108|>",
933
- "lstrip": false,
934
- "normalized": false,
935
- "rstrip": false,
936
- "single_word": false,
937
- "special": true
938
- },
939
- "128117": {
940
- "content": "<|reserved_special_token_109|>",
941
- "lstrip": false,
942
- "normalized": false,
943
- "rstrip": false,
944
- "single_word": false,
945
- "special": true
946
- },
947
- "128118": {
948
- "content": "<|reserved_special_token_110|>",
949
- "lstrip": false,
950
- "normalized": false,
951
- "rstrip": false,
952
- "single_word": false,
953
- "special": true
954
- },
955
- "128119": {
956
- "content": "<|reserved_special_token_111|>",
957
- "lstrip": false,
958
- "normalized": false,
959
- "rstrip": false,
960
- "single_word": false,
961
- "special": true
962
- },
963
- "128120": {
964
- "content": "<|reserved_special_token_112|>",
965
- "lstrip": false,
966
- "normalized": false,
967
- "rstrip": false,
968
- "single_word": false,
969
- "special": true
970
- },
971
- "128121": {
972
- "content": "<|reserved_special_token_113|>",
973
- "lstrip": false,
974
- "normalized": false,
975
- "rstrip": false,
976
- "single_word": false,
977
- "special": true
978
- },
979
- "128122": {
980
- "content": "<|reserved_special_token_114|>",
981
- "lstrip": false,
982
- "normalized": false,
983
- "rstrip": false,
984
- "single_word": false,
985
- "special": true
986
- },
987
- "128123": {
988
- "content": "<|reserved_special_token_115|>",
989
- "lstrip": false,
990
- "normalized": false,
991
- "rstrip": false,
992
- "single_word": false,
993
- "special": true
994
- },
995
- "128124": {
996
- "content": "<|reserved_special_token_116|>",
997
- "lstrip": false,
998
- "normalized": false,
999
- "rstrip": false,
1000
- "single_word": false,
1001
- "special": true
1002
- },
1003
- "128125": {
1004
- "content": "<|reserved_special_token_117|>",
1005
- "lstrip": false,
1006
- "normalized": false,
1007
- "rstrip": false,
1008
- "single_word": false,
1009
- "special": true
1010
- },
1011
- "128126": {
1012
- "content": "<|reserved_special_token_118|>",
1013
- "lstrip": false,
1014
- "normalized": false,
1015
- "rstrip": false,
1016
- "single_word": false,
1017
- "special": true
1018
- },
1019
- "128127": {
1020
- "content": "<|reserved_special_token_119|>",
1021
- "lstrip": false,
1022
- "normalized": false,
1023
- "rstrip": false,
1024
- "single_word": false,
1025
- "special": true
1026
- },
1027
- "128128": {
1028
- "content": "<|reserved_special_token_120|>",
1029
- "lstrip": false,
1030
- "normalized": false,
1031
- "rstrip": false,
1032
- "single_word": false,
1033
- "special": true
1034
- },
1035
- "128129": {
1036
- "content": "<|reserved_special_token_121|>",
1037
- "lstrip": false,
1038
- "normalized": false,
1039
- "rstrip": false,
1040
- "single_word": false,
1041
- "special": true
1042
- },
1043
- "128130": {
1044
- "content": "<|reserved_special_token_122|>",
1045
- "lstrip": false,
1046
- "normalized": false,
1047
- "rstrip": false,
1048
- "single_word": false,
1049
- "special": true
1050
- },
1051
- "128131": {
1052
- "content": "<|reserved_special_token_123|>",
1053
- "lstrip": false,
1054
- "normalized": false,
1055
- "rstrip": false,
1056
- "single_word": false,
1057
- "special": true
1058
- },
1059
- "128132": {
1060
- "content": "<|reserved_special_token_124|>",
1061
- "lstrip": false,
1062
- "normalized": false,
1063
- "rstrip": false,
1064
- "single_word": false,
1065
- "special": true
1066
- },
1067
- "128133": {
1068
- "content": "<|reserved_special_token_125|>",
1069
- "lstrip": false,
1070
- "normalized": false,
1071
- "rstrip": false,
1072
- "single_word": false,
1073
- "special": true
1074
- },
1075
- "128134": {
1076
- "content": "<|reserved_special_token_126|>",
1077
- "lstrip": false,
1078
- "normalized": false,
1079
- "rstrip": false,
1080
- "single_word": false,
1081
- "special": true
1082
- },
1083
- "128135": {
1084
- "content": "<|reserved_special_token_127|>",
1085
- "lstrip": false,
1086
- "normalized": false,
1087
- "rstrip": false,
1088
- "single_word": false,
1089
- "special": true
1090
- },
1091
- "128136": {
1092
- "content": "<|reserved_special_token_128|>",
1093
- "lstrip": false,
1094
- "normalized": false,
1095
- "rstrip": false,
1096
- "single_word": false,
1097
- "special": true
1098
- },
1099
- "128137": {
1100
- "content": "<|reserved_special_token_129|>",
1101
- "lstrip": false,
1102
- "normalized": false,
1103
- "rstrip": false,
1104
- "single_word": false,
1105
- "special": true
1106
- },
1107
- "128138": {
1108
- "content": "<|reserved_special_token_130|>",
1109
- "lstrip": false,
1110
- "normalized": false,
1111
- "rstrip": false,
1112
- "single_word": false,
1113
- "special": true
1114
- },
1115
- "128139": {
1116
- "content": "<|reserved_special_token_131|>",
1117
- "lstrip": false,
1118
- "normalized": false,
1119
- "rstrip": false,
1120
- "single_word": false,
1121
- "special": true
1122
- },
1123
- "128140": {
1124
- "content": "<|reserved_special_token_132|>",
1125
- "lstrip": false,
1126
- "normalized": false,
1127
- "rstrip": false,
1128
- "single_word": false,
1129
- "special": true
1130
- },
1131
- "128141": {
1132
- "content": "<|reserved_special_token_133|>",
1133
- "lstrip": false,
1134
- "normalized": false,
1135
- "rstrip": false,
1136
- "single_word": false,
1137
- "special": true
1138
- },
1139
- "128142": {
1140
- "content": "<|reserved_special_token_134|>",
1141
- "lstrip": false,
1142
- "normalized": false,
1143
- "rstrip": false,
1144
- "single_word": false,
1145
- "special": true
1146
- },
1147
- "128143": {
1148
- "content": "<|reserved_special_token_135|>",
1149
- "lstrip": false,
1150
- "normalized": false,
1151
- "rstrip": false,
1152
- "single_word": false,
1153
- "special": true
1154
- },
1155
- "128144": {
1156
- "content": "<|reserved_special_token_136|>",
1157
- "lstrip": false,
1158
- "normalized": false,
1159
- "rstrip": false,
1160
- "single_word": false,
1161
- "special": true
1162
- },
1163
- "128145": {
1164
- "content": "<|reserved_special_token_137|>",
1165
- "lstrip": false,
1166
- "normalized": false,
1167
- "rstrip": false,
1168
- "single_word": false,
1169
- "special": true
1170
- },
1171
- "128146": {
1172
- "content": "<|reserved_special_token_138|>",
1173
- "lstrip": false,
1174
- "normalized": false,
1175
- "rstrip": false,
1176
- "single_word": false,
1177
- "special": true
1178
- },
1179
- "128147": {
1180
- "content": "<|reserved_special_token_139|>",
1181
- "lstrip": false,
1182
- "normalized": false,
1183
- "rstrip": false,
1184
- "single_word": false,
1185
- "special": true
1186
- },
1187
- "128148": {
1188
- "content": "<|reserved_special_token_140|>",
1189
- "lstrip": false,
1190
- "normalized": false,
1191
- "rstrip": false,
1192
- "single_word": false,
1193
- "special": true
1194
- },
1195
- "128149": {
1196
- "content": "<|reserved_special_token_141|>",
1197
- "lstrip": false,
1198
- "normalized": false,
1199
- "rstrip": false,
1200
- "single_word": false,
1201
- "special": true
1202
- },
1203
- "128150": {
1204
- "content": "<|reserved_special_token_142|>",
1205
- "lstrip": false,
1206
- "normalized": false,
1207
- "rstrip": false,
1208
- "single_word": false,
1209
- "special": true
1210
- },
1211
- "128151": {
1212
- "content": "<|reserved_special_token_143|>",
1213
- "lstrip": false,
1214
- "normalized": false,
1215
- "rstrip": false,
1216
- "single_word": false,
1217
- "special": true
1218
- },
1219
- "128152": {
1220
- "content": "<|reserved_special_token_144|>",
1221
- "lstrip": false,
1222
- "normalized": false,
1223
- "rstrip": false,
1224
- "single_word": false,
1225
- "special": true
1226
- },
1227
- "128153": {
1228
- "content": "<|reserved_special_token_145|>",
1229
- "lstrip": false,
1230
- "normalized": false,
1231
- "rstrip": false,
1232
- "single_word": false,
1233
- "special": true
1234
- },
1235
- "128154": {
1236
- "content": "<|reserved_special_token_146|>",
1237
- "lstrip": false,
1238
- "normalized": false,
1239
- "rstrip": false,
1240
- "single_word": false,
1241
- "special": true
1242
- },
1243
- "128155": {
1244
- "content": "<|reserved_special_token_147|>",
1245
- "lstrip": false,
1246
- "normalized": false,
1247
- "rstrip": false,
1248
- "single_word": false,
1249
- "special": true
1250
- },
1251
- "128156": {
1252
- "content": "<|reserved_special_token_148|>",
1253
- "lstrip": false,
1254
- "normalized": false,
1255
- "rstrip": false,
1256
- "single_word": false,
1257
- "special": true
1258
- },
1259
- "128157": {
1260
- "content": "<|reserved_special_token_149|>",
1261
- "lstrip": false,
1262
- "normalized": false,
1263
- "rstrip": false,
1264
- "single_word": false,
1265
- "special": true
1266
- },
1267
- "128158": {
1268
- "content": "<|reserved_special_token_150|>",
1269
- "lstrip": false,
1270
- "normalized": false,
1271
- "rstrip": false,
1272
- "single_word": false,
1273
- "special": true
1274
- },
1275
- "128159": {
1276
- "content": "<|reserved_special_token_151|>",
1277
- "lstrip": false,
1278
- "normalized": false,
1279
- "rstrip": false,
1280
- "single_word": false,
1281
- "special": true
1282
- },
1283
- "128160": {
1284
- "content": "<|reserved_special_token_152|>",
1285
- "lstrip": false,
1286
- "normalized": false,
1287
- "rstrip": false,
1288
- "single_word": false,
1289
- "special": true
1290
- },
1291
- "128161": {
1292
- "content": "<|reserved_special_token_153|>",
1293
- "lstrip": false,
1294
- "normalized": false,
1295
- "rstrip": false,
1296
- "single_word": false,
1297
- "special": true
1298
- },
1299
- "128162": {
1300
- "content": "<|reserved_special_token_154|>",
1301
- "lstrip": false,
1302
- "normalized": false,
1303
- "rstrip": false,
1304
- "single_word": false,
1305
- "special": true
1306
- },
1307
- "128163": {
1308
- "content": "<|reserved_special_token_155|>",
1309
- "lstrip": false,
1310
- "normalized": false,
1311
- "rstrip": false,
1312
- "single_word": false,
1313
- "special": true
1314
- },
1315
- "128164": {
1316
- "content": "<|reserved_special_token_156|>",
1317
- "lstrip": false,
1318
- "normalized": false,
1319
- "rstrip": false,
1320
- "single_word": false,
1321
- "special": true
1322
- },
1323
- "128165": {
1324
- "content": "<|reserved_special_token_157|>",
1325
- "lstrip": false,
1326
- "normalized": false,
1327
- "rstrip": false,
1328
- "single_word": false,
1329
- "special": true
1330
- },
1331
- "128166": {
1332
- "content": "<|reserved_special_token_158|>",
1333
- "lstrip": false,
1334
- "normalized": false,
1335
- "rstrip": false,
1336
- "single_word": false,
1337
- "special": true
1338
- },
1339
- "128167": {
1340
- "content": "<|reserved_special_token_159|>",
1341
- "lstrip": false,
1342
- "normalized": false,
1343
- "rstrip": false,
1344
- "single_word": false,
1345
- "special": true
1346
- },
1347
- "128168": {
1348
- "content": "<|reserved_special_token_160|>",
1349
- "lstrip": false,
1350
- "normalized": false,
1351
- "rstrip": false,
1352
- "single_word": false,
1353
- "special": true
1354
- },
1355
- "128169": {
1356
- "content": "<|reserved_special_token_161|>",
1357
- "lstrip": false,
1358
- "normalized": false,
1359
- "rstrip": false,
1360
- "single_word": false,
1361
- "special": true
1362
- },
1363
- "128170": {
1364
- "content": "<|reserved_special_token_162|>",
1365
- "lstrip": false,
1366
- "normalized": false,
1367
- "rstrip": false,
1368
- "single_word": false,
1369
- "special": true
1370
- },
1371
- "128171": {
1372
- "content": "<|reserved_special_token_163|>",
1373
- "lstrip": false,
1374
- "normalized": false,
1375
- "rstrip": false,
1376
- "single_word": false,
1377
- "special": true
1378
- },
1379
- "128172": {
1380
- "content": "<|reserved_special_token_164|>",
1381
- "lstrip": false,
1382
- "normalized": false,
1383
- "rstrip": false,
1384
- "single_word": false,
1385
- "special": true
1386
- },
1387
- "128173": {
1388
- "content": "<|reserved_special_token_165|>",
1389
- "lstrip": false,
1390
- "normalized": false,
1391
- "rstrip": false,
1392
- "single_word": false,
1393
- "special": true
1394
- },
1395
- "128174": {
1396
- "content": "<|reserved_special_token_166|>",
1397
- "lstrip": false,
1398
- "normalized": false,
1399
- "rstrip": false,
1400
- "single_word": false,
1401
- "special": true
1402
- },
1403
- "128175": {
1404
- "content": "<|reserved_special_token_167|>",
1405
- "lstrip": false,
1406
- "normalized": false,
1407
- "rstrip": false,
1408
- "single_word": false,
1409
- "special": true
1410
- },
1411
- "128176": {
1412
- "content": "<|reserved_special_token_168|>",
1413
- "lstrip": false,
1414
- "normalized": false,
1415
- "rstrip": false,
1416
- "single_word": false,
1417
- "special": true
1418
- },
1419
- "128177": {
1420
- "content": "<|reserved_special_token_169|>",
1421
- "lstrip": false,
1422
- "normalized": false,
1423
- "rstrip": false,
1424
- "single_word": false,
1425
- "special": true
1426
- },
1427
- "128178": {
1428
- "content": "<|reserved_special_token_170|>",
1429
- "lstrip": false,
1430
- "normalized": false,
1431
- "rstrip": false,
1432
- "single_word": false,
1433
- "special": true
1434
- },
1435
- "128179": {
1436
- "content": "<|reserved_special_token_171|>",
1437
- "lstrip": false,
1438
- "normalized": false,
1439
- "rstrip": false,
1440
- "single_word": false,
1441
- "special": true
1442
- },
1443
- "128180": {
1444
- "content": "<|reserved_special_token_172|>",
1445
- "lstrip": false,
1446
- "normalized": false,
1447
- "rstrip": false,
1448
- "single_word": false,
1449
- "special": true
1450
- },
1451
- "128181": {
1452
- "content": "<|reserved_special_token_173|>",
1453
- "lstrip": false,
1454
- "normalized": false,
1455
- "rstrip": false,
1456
- "single_word": false,
1457
- "special": true
1458
- },
1459
- "128182": {
1460
- "content": "<|reserved_special_token_174|>",
1461
- "lstrip": false,
1462
- "normalized": false,
1463
- "rstrip": false,
1464
- "single_word": false,
1465
- "special": true
1466
- },
1467
- "128183": {
1468
- "content": "<|reserved_special_token_175|>",
1469
- "lstrip": false,
1470
- "normalized": false,
1471
- "rstrip": false,
1472
- "single_word": false,
1473
- "special": true
1474
- },
1475
- "128184": {
1476
- "content": "<|reserved_special_token_176|>",
1477
- "lstrip": false,
1478
- "normalized": false,
1479
- "rstrip": false,
1480
- "single_word": false,
1481
- "special": true
1482
- },
1483
- "128185": {
1484
- "content": "<|reserved_special_token_177|>",
1485
- "lstrip": false,
1486
- "normalized": false,
1487
- "rstrip": false,
1488
- "single_word": false,
1489
- "special": true
1490
- },
1491
- "128186": {
1492
- "content": "<|reserved_special_token_178|>",
1493
- "lstrip": false,
1494
- "normalized": false,
1495
- "rstrip": false,
1496
- "single_word": false,
1497
- "special": true
1498
- },
1499
- "128187": {
1500
- "content": "<|reserved_special_token_179|>",
1501
- "lstrip": false,
1502
- "normalized": false,
1503
- "rstrip": false,
1504
- "single_word": false,
1505
- "special": true
1506
- },
1507
- "128188": {
1508
- "content": "<|reserved_special_token_180|>",
1509
- "lstrip": false,
1510
- "normalized": false,
1511
- "rstrip": false,
1512
- "single_word": false,
1513
- "special": true
1514
- },
1515
- "128189": {
1516
- "content": "<|reserved_special_token_181|>",
1517
- "lstrip": false,
1518
- "normalized": false,
1519
- "rstrip": false,
1520
- "single_word": false,
1521
- "special": true
1522
- },
1523
- "128190": {
1524
- "content": "<|reserved_special_token_182|>",
1525
- "lstrip": false,
1526
- "normalized": false,
1527
- "rstrip": false,
1528
- "single_word": false,
1529
- "special": true
1530
- },
1531
- "128191": {
1532
- "content": "<|reserved_special_token_183|>",
1533
- "lstrip": false,
1534
- "normalized": false,
1535
- "rstrip": false,
1536
- "single_word": false,
1537
- "special": true
1538
- },
1539
- "128192": {
1540
- "content": "<|reserved_special_token_184|>",
1541
- "lstrip": false,
1542
- "normalized": false,
1543
- "rstrip": false,
1544
- "single_word": false,
1545
- "special": true
1546
- },
1547
- "128193": {
1548
- "content": "<|reserved_special_token_185|>",
1549
- "lstrip": false,
1550
- "normalized": false,
1551
- "rstrip": false,
1552
- "single_word": false,
1553
- "special": true
1554
- },
1555
- "128194": {
1556
- "content": "<|reserved_special_token_186|>",
1557
- "lstrip": false,
1558
- "normalized": false,
1559
- "rstrip": false,
1560
- "single_word": false,
1561
- "special": true
1562
- },
1563
- "128195": {
1564
- "content": "<|reserved_special_token_187|>",
1565
- "lstrip": false,
1566
- "normalized": false,
1567
- "rstrip": false,
1568
- "single_word": false,
1569
- "special": true
1570
- },
1571
- "128196": {
1572
- "content": "<|reserved_special_token_188|>",
1573
- "lstrip": false,
1574
- "normalized": false,
1575
- "rstrip": false,
1576
- "single_word": false,
1577
- "special": true
1578
- },
1579
- "128197": {
1580
- "content": "<|reserved_special_token_189|>",
1581
- "lstrip": false,
1582
- "normalized": false,
1583
- "rstrip": false,
1584
- "single_word": false,
1585
- "special": true
1586
- },
1587
- "128198": {
1588
- "content": "<|reserved_special_token_190|>",
1589
- "lstrip": false,
1590
- "normalized": false,
1591
- "rstrip": false,
1592
- "single_word": false,
1593
- "special": true
1594
- },
1595
- "128199": {
1596
- "content": "<|reserved_special_token_191|>",
1597
- "lstrip": false,
1598
- "normalized": false,
1599
- "rstrip": false,
1600
- "single_word": false,
1601
- "special": true
1602
- },
1603
- "128200": {
1604
- "content": "<|reserved_special_token_192|>",
1605
- "lstrip": false,
1606
- "normalized": false,
1607
- "rstrip": false,
1608
- "single_word": false,
1609
- "special": true
1610
- },
1611
- "128201": {
1612
- "content": "<|reserved_special_token_193|>",
1613
- "lstrip": false,
1614
- "normalized": false,
1615
- "rstrip": false,
1616
- "single_word": false,
1617
- "special": true
1618
- },
1619
- "128202": {
1620
- "content": "<|reserved_special_token_194|>",
1621
- "lstrip": false,
1622
- "normalized": false,
1623
- "rstrip": false,
1624
- "single_word": false,
1625
- "special": true
1626
- },
1627
- "128203": {
1628
- "content": "<|reserved_special_token_195|>",
1629
- "lstrip": false,
1630
- "normalized": false,
1631
- "rstrip": false,
1632
- "single_word": false,
1633
- "special": true
1634
- },
1635
- "128204": {
1636
- "content": "<|reserved_special_token_196|>",
1637
- "lstrip": false,
1638
- "normalized": false,
1639
- "rstrip": false,
1640
- "single_word": false,
1641
- "special": true
1642
- },
1643
- "128205": {
1644
- "content": "<|reserved_special_token_197|>",
1645
- "lstrip": false,
1646
- "normalized": false,
1647
- "rstrip": false,
1648
- "single_word": false,
1649
- "special": true
1650
- },
1651
- "128206": {
1652
- "content": "<|reserved_special_token_198|>",
1653
- "lstrip": false,
1654
- "normalized": false,
1655
- "rstrip": false,
1656
- "single_word": false,
1657
- "special": true
1658
- },
1659
- "128207": {
1660
- "content": "<|reserved_special_token_199|>",
1661
- "lstrip": false,
1662
- "normalized": false,
1663
- "rstrip": false,
1664
- "single_word": false,
1665
- "special": true
1666
- },
1667
- "128208": {
1668
- "content": "<|reserved_special_token_200|>",
1669
- "lstrip": false,
1670
- "normalized": false,
1671
- "rstrip": false,
1672
- "single_word": false,
1673
- "special": true
1674
- },
1675
- "128209": {
1676
- "content": "<|reserved_special_token_201|>",
1677
- "lstrip": false,
1678
- "normalized": false,
1679
- "rstrip": false,
1680
- "single_word": false,
1681
- "special": true
1682
- },
1683
- "128210": {
1684
- "content": "<|reserved_special_token_202|>",
1685
- "lstrip": false,
1686
- "normalized": false,
1687
- "rstrip": false,
1688
- "single_word": false,
1689
- "special": true
1690
- },
1691
- "128211": {
1692
- "content": "<|reserved_special_token_203|>",
1693
- "lstrip": false,
1694
- "normalized": false,
1695
- "rstrip": false,
1696
- "single_word": false,
1697
- "special": true
1698
- },
1699
- "128212": {
1700
- "content": "<|reserved_special_token_204|>",
1701
- "lstrip": false,
1702
- "normalized": false,
1703
- "rstrip": false,
1704
- "single_word": false,
1705
- "special": true
1706
- },
1707
- "128213": {
1708
- "content": "<|reserved_special_token_205|>",
1709
- "lstrip": false,
1710
- "normalized": false,
1711
- "rstrip": false,
1712
- "single_word": false,
1713
- "special": true
1714
- },
1715
- "128214": {
1716
- "content": "<|reserved_special_token_206|>",
1717
- "lstrip": false,
1718
- "normalized": false,
1719
- "rstrip": false,
1720
- "single_word": false,
1721
- "special": true
1722
- },
1723
- "128215": {
1724
- "content": "<|reserved_special_token_207|>",
1725
- "lstrip": false,
1726
- "normalized": false,
1727
- "rstrip": false,
1728
- "single_word": false,
1729
- "special": true
1730
- },
1731
- "128216": {
1732
- "content": "<|reserved_special_token_208|>",
1733
- "lstrip": false,
1734
- "normalized": false,
1735
- "rstrip": false,
1736
- "single_word": false,
1737
- "special": true
1738
- },
1739
- "128217": {
1740
- "content": "<|reserved_special_token_209|>",
1741
- "lstrip": false,
1742
- "normalized": false,
1743
- "rstrip": false,
1744
- "single_word": false,
1745
- "special": true
1746
- },
1747
- "128218": {
1748
- "content": "<|reserved_special_token_210|>",
1749
- "lstrip": false,
1750
- "normalized": false,
1751
- "rstrip": false,
1752
- "single_word": false,
1753
- "special": true
1754
- },
1755
- "128219": {
1756
- "content": "<|reserved_special_token_211|>",
1757
- "lstrip": false,
1758
- "normalized": false,
1759
- "rstrip": false,
1760
- "single_word": false,
1761
- "special": true
1762
- },
1763
- "128220": {
1764
- "content": "<|reserved_special_token_212|>",
1765
- "lstrip": false,
1766
- "normalized": false,
1767
- "rstrip": false,
1768
- "single_word": false,
1769
- "special": true
1770
- },
1771
- "128221": {
1772
- "content": "<|reserved_special_token_213|>",
1773
- "lstrip": false,
1774
- "normalized": false,
1775
- "rstrip": false,
1776
- "single_word": false,
1777
- "special": true
1778
- },
1779
- "128222": {
1780
- "content": "<|reserved_special_token_214|>",
1781
- "lstrip": false,
1782
- "normalized": false,
1783
- "rstrip": false,
1784
- "single_word": false,
1785
- "special": true
1786
- },
1787
- "128223": {
1788
- "content": "<|reserved_special_token_215|>",
1789
- "lstrip": false,
1790
- "normalized": false,
1791
- "rstrip": false,
1792
- "single_word": false,
1793
- "special": true
1794
- },
1795
- "128224": {
1796
- "content": "<|reserved_special_token_216|>",
1797
- "lstrip": false,
1798
- "normalized": false,
1799
- "rstrip": false,
1800
- "single_word": false,
1801
- "special": true
1802
- },
1803
- "128225": {
1804
- "content": "<|reserved_special_token_217|>",
1805
- "lstrip": false,
1806
- "normalized": false,
1807
- "rstrip": false,
1808
- "single_word": false,
1809
- "special": true
1810
- },
1811
- "128226": {
1812
- "content": "<|reserved_special_token_218|>",
1813
- "lstrip": false,
1814
- "normalized": false,
1815
- "rstrip": false,
1816
- "single_word": false,
1817
- "special": true
1818
- },
1819
- "128227": {
1820
- "content": "<|reserved_special_token_219|>",
1821
- "lstrip": false,
1822
- "normalized": false,
1823
- "rstrip": false,
1824
- "single_word": false,
1825
- "special": true
1826
- },
1827
- "128228": {
1828
- "content": "<|reserved_special_token_220|>",
1829
- "lstrip": false,
1830
- "normalized": false,
1831
- "rstrip": false,
1832
- "single_word": false,
1833
- "special": true
1834
- },
1835
- "128229": {
1836
- "content": "<|reserved_special_token_221|>",
1837
- "lstrip": false,
1838
- "normalized": false,
1839
- "rstrip": false,
1840
- "single_word": false,
1841
- "special": true
1842
- },
1843
- "128230": {
1844
- "content": "<|reserved_special_token_222|>",
1845
- "lstrip": false,
1846
- "normalized": false,
1847
- "rstrip": false,
1848
- "single_word": false,
1849
- "special": true
1850
- },
1851
- "128231": {
1852
- "content": "<|reserved_special_token_223|>",
1853
- "lstrip": false,
1854
- "normalized": false,
1855
- "rstrip": false,
1856
- "single_word": false,
1857
- "special": true
1858
- },
1859
- "128232": {
1860
- "content": "<|reserved_special_token_224|>",
1861
- "lstrip": false,
1862
- "normalized": false,
1863
- "rstrip": false,
1864
- "single_word": false,
1865
- "special": true
1866
- },
1867
- "128233": {
1868
- "content": "<|reserved_special_token_225|>",
1869
- "lstrip": false,
1870
- "normalized": false,
1871
- "rstrip": false,
1872
- "single_word": false,
1873
- "special": true
1874
- },
1875
- "128234": {
1876
- "content": "<|reserved_special_token_226|>",
1877
- "lstrip": false,
1878
- "normalized": false,
1879
- "rstrip": false,
1880
- "single_word": false,
1881
- "special": true
1882
- },
1883
- "128235": {
1884
- "content": "<|reserved_special_token_227|>",
1885
- "lstrip": false,
1886
- "normalized": false,
1887
- "rstrip": false,
1888
- "single_word": false,
1889
- "special": true
1890
- },
1891
- "128236": {
1892
- "content": "<|reserved_special_token_228|>",
1893
- "lstrip": false,
1894
- "normalized": false,
1895
- "rstrip": false,
1896
- "single_word": false,
1897
- "special": true
1898
- },
1899
- "128237": {
1900
- "content": "<|reserved_special_token_229|>",
1901
- "lstrip": false,
1902
- "normalized": false,
1903
- "rstrip": false,
1904
- "single_word": false,
1905
- "special": true
1906
- },
1907
- "128238": {
1908
- "content": "<|reserved_special_token_230|>",
1909
- "lstrip": false,
1910
- "normalized": false,
1911
- "rstrip": false,
1912
- "single_word": false,
1913
- "special": true
1914
- },
1915
- "128239": {
1916
- "content": "<|reserved_special_token_231|>",
1917
- "lstrip": false,
1918
- "normalized": false,
1919
- "rstrip": false,
1920
- "single_word": false,
1921
- "special": true
1922
- },
1923
- "128240": {
1924
- "content": "<|reserved_special_token_232|>",
1925
- "lstrip": false,
1926
- "normalized": false,
1927
- "rstrip": false,
1928
- "single_word": false,
1929
- "special": true
1930
- },
1931
- "128241": {
1932
- "content": "<|reserved_special_token_233|>",
1933
- "lstrip": false,
1934
- "normalized": false,
1935
- "rstrip": false,
1936
- "single_word": false,
1937
- "special": true
1938
- },
1939
- "128242": {
1940
- "content": "<|reserved_special_token_234|>",
1941
- "lstrip": false,
1942
- "normalized": false,
1943
- "rstrip": false,
1944
- "single_word": false,
1945
- "special": true
1946
- },
1947
- "128243": {
1948
- "content": "<|reserved_special_token_235|>",
1949
- "lstrip": false,
1950
- "normalized": false,
1951
- "rstrip": false,
1952
- "single_word": false,
1953
- "special": true
1954
- },
1955
- "128244": {
1956
- "content": "<|reserved_special_token_236|>",
1957
- "lstrip": false,
1958
- "normalized": false,
1959
- "rstrip": false,
1960
- "single_word": false,
1961
- "special": true
1962
- },
1963
- "128245": {
1964
- "content": "<|reserved_special_token_237|>",
1965
- "lstrip": false,
1966
- "normalized": false,
1967
- "rstrip": false,
1968
- "single_word": false,
1969
- "special": true
1970
- },
1971
- "128246": {
1972
- "content": "<|reserved_special_token_238|>",
1973
- "lstrip": false,
1974
- "normalized": false,
1975
- "rstrip": false,
1976
- "single_word": false,
1977
- "special": true
1978
- },
1979
- "128247": {
1980
- "content": "<|reserved_special_token_239|>",
1981
- "lstrip": false,
1982
- "normalized": false,
1983
- "rstrip": false,
1984
- "single_word": false,
1985
- "special": true
1986
- },
1987
- "128248": {
1988
- "content": "<|reserved_special_token_240|>",
1989
- "lstrip": false,
1990
- "normalized": false,
1991
- "rstrip": false,
1992
- "single_word": false,
1993
- "special": true
1994
- },
1995
- "128249": {
1996
- "content": "<|reserved_special_token_241|>",
1997
- "lstrip": false,
1998
- "normalized": false,
1999
- "rstrip": false,
2000
- "single_word": false,
2001
- "special": true
2002
- },
2003
- "128250": {
2004
- "content": "<|reserved_special_token_242|>",
2005
- "lstrip": false,
2006
- "normalized": false,
2007
- "rstrip": false,
2008
- "single_word": false,
2009
- "special": true
2010
- },
2011
- "128251": {
2012
- "content": "<|reserved_special_token_243|>",
2013
- "lstrip": false,
2014
- "normalized": false,
2015
- "rstrip": false,
2016
- "single_word": false,
2017
- "special": true
2018
- },
2019
- "128252": {
2020
- "content": "<|reserved_special_token_244|>",
2021
- "lstrip": false,
2022
- "normalized": false,
2023
- "rstrip": false,
2024
- "single_word": false,
2025
- "special": true
2026
- },
2027
- "128253": {
2028
- "content": "<|reserved_special_token_245|>",
2029
- "lstrip": false,
2030
- "normalized": false,
2031
- "rstrip": false,
2032
- "single_word": false,
2033
- "special": true
2034
- },
2035
- "128254": {
2036
- "content": "<|reserved_special_token_246|>",
2037
- "lstrip": false,
2038
- "normalized": false,
2039
- "rstrip": false,
2040
- "single_word": false,
2041
- "special": true
2042
- },
2043
- "128255": {
2044
- "content": "<|reserved_special_token_247|>",
2045
- "lstrip": false,
2046
- "normalized": false,
2047
- "rstrip": false,
2048
- "single_word": false,
2049
- "special": true
2050
- }
2051
- },
2052
- "bos_token": "<|begin_of_text|>",
2053
- "clean_up_tokenization_spaces": true,
2054
- "eos_token": "<|eot_id|>",
2055
- "extra_special_tokens": {},
2056
- "model_input_names": [
2057
- "input_ids",
2058
- "attention_mask"
2059
- ],
2060
- "model_max_length": 131072,
2061
- "pad_token": "<|eot_id|>",
2062
- "tokenizer_class": "PreTrainedTokenizerFast"
2063
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw7.54_4-8bit/README.md DELETED
@@ -1,17 +0,0 @@
1
- # Quantized Model Checkpoint
2
-
3
- **Base model:** meta-llama/Llama-3.1-8B-Instruct
4
-
5
- **Average bitwidth:** 7.5385
6
-
7
- **Sensitivity method:** shapley
8
-
9
- **Constraints:**
10
- - max_kl: 0.01
11
- - min_eap: 0.99
12
-
13
- **Metrics:**
14
- - predicted_kl: 0.005405
15
- - predicted_eap: 0.990085
16
-
17
- See `quantization_config.txt` for full configuration details.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw7.54_4-8bit/chat_template.jinja DELETED
@@ -1,109 +0,0 @@
1
- {{- bos_token }}
2
- {%- if custom_tools is defined %}
3
- {%- set tools = custom_tools %}
4
- {%- endif %}
5
- {%- if not tools_in_user_message is defined %}
6
- {%- set tools_in_user_message = true %}
7
- {%- endif %}
8
- {%- if not date_string is defined %}
9
- {%- set date_string = "26 Jul 2024" %}
10
- {%- endif %}
11
- {%- if not tools is defined %}
12
- {%- set tools = none %}
13
- {%- endif %}
14
-
15
- {#- This block extracts the system message, so we can slot it into the right place. #}
16
- {%- if messages[0]['role'] == 'system' %}
17
- {%- set system_message = messages[0]['content']|trim %}
18
- {%- set messages = messages[1:] %}
19
- {%- else %}
20
- {%- set system_message = "" %}
21
- {%- endif %}
22
-
23
- {#- System message + builtin tools #}
24
- {{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
25
- {%- if builtin_tools is defined or tools is not none %}
26
- {{- "Environment: ipython\n" }}
27
- {%- endif %}
28
- {%- if builtin_tools is defined %}
29
- {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
30
- {%- endif %}
31
- {{- "Cutting Knowledge Date: December 2023\n" }}
32
- {{- "Today Date: " + date_string + "\n\n" }}
33
- {%- if tools is not none and not tools_in_user_message %}
34
- {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
35
- {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
36
- {{- "Do not use variables.\n\n" }}
37
- {%- for t in tools %}
38
- {{- t | tojson(indent=4) }}
39
- {{- "\n\n" }}
40
- {%- endfor %}
41
- {%- endif %}
42
- {{- system_message }}
43
- {{- "<|eot_id|>" }}
44
-
45
- {#- Custom tools are passed in a user message with some extra guidance #}
46
- {%- if tools_in_user_message and not tools is none %}
47
- {#- Extract the first user message so we can plug it in here #}
48
- {%- if messages | length != 0 %}
49
- {%- set first_user_message = messages[0]['content']|trim %}
50
- {%- set messages = messages[1:] %}
51
- {%- else %}
52
- {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
53
- {%- endif %}
54
- {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
55
- {{- "Given the following functions, please respond with a JSON for a function call " }}
56
- {{- "with its proper arguments that best answers the given prompt.\n\n" }}
57
- {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
58
- {{- "Do not use variables.\n\n" }}
59
- {%- for t in tools %}
60
- {{- t | tojson(indent=4) }}
61
- {{- "\n\n" }}
62
- {%- endfor %}
63
- {{- first_user_message + "<|eot_id|>"}}
64
- {%- endif %}
65
-
66
- {%- for message in messages %}
67
- {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
68
- {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
69
- {%- elif 'tool_calls' in message %}
70
- {%- if not message.tool_calls|length == 1 %}
71
- {{- raise_exception("This model only supports single tool-calls at once!") }}
72
- {%- endif %}
73
- {%- set tool_call = message.tool_calls[0].function %}
74
- {%- if builtin_tools is defined and tool_call.name in builtin_tools %}
75
- {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
76
- {{- "<|python_tag|>" + tool_call.name + ".call(" }}
77
- {%- for arg_name, arg_val in tool_call.arguments | items %}
78
- {{- arg_name + '="' + arg_val + '"' }}
79
- {%- if not loop.last %}
80
- {{- ", " }}
81
- {%- endif %}
82
- {%- endfor %}
83
- {{- ")" }}
84
- {%- else %}
85
- {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
86
- {{- '{"name": "' + tool_call.name + '", ' }}
87
- {{- '"parameters": ' }}
88
- {{- tool_call.arguments | tojson }}
89
- {{- "}" }}
90
- {%- endif %}
91
- {%- if builtin_tools is defined %}
92
- {#- This means we're in ipython mode #}
93
- {{- "<|eom_id|>" }}
94
- {%- else %}
95
- {{- "<|eot_id|>" }}
96
- {%- endif %}
97
- {%- elif message.role == "tool" or message.role == "ipython" %}
98
- {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
99
- {%- if message.content is mapping or message.content is iterable %}
100
- {{- message.content | tojson }}
101
- {%- else %}
102
- {{- message.content }}
103
- {%- endif %}
104
- {{- "<|eot_id|>" }}
105
- {%- endif %}
106
- {%- endfor %}
107
- {%- if add_generation_prompt %}
108
- {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
109
- {%- endif %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw7.54_4-8bit/config.json DELETED
@@ -1,39 +0,0 @@
1
- {
2
- "architectures": [
3
- "LlamaForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 128000,
8
- "dtype": "float16",
9
- "eos_token_id": [
10
- 128001,
11
- 128008,
12
- 128009
13
- ],
14
- "head_dim": 128,
15
- "hidden_act": "silu",
16
- "hidden_size": 4096,
17
- "initializer_range": 0.02,
18
- "intermediate_size": 14336,
19
- "max_position_embeddings": 131072,
20
- "mlp_bias": false,
21
- "model_type": "llama",
22
- "num_attention_heads": 32,
23
- "num_hidden_layers": 32,
24
- "num_key_value_heads": 8,
25
- "pretraining_tp": 1,
26
- "rms_norm_eps": 1e-05,
27
- "rope_scaling": {
28
- "factor": 8.0,
29
- "high_freq_factor": 4.0,
30
- "low_freq_factor": 1.0,
31
- "original_max_position_embeddings": 8192,
32
- "rope_type": "llama3"
33
- },
34
- "rope_theta": 500000.0,
35
- "tie_word_embeddings": false,
36
- "transformers_version": "4.57.3",
37
- "use_cache": false,
38
- "vocab_size": 128256
39
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw7.54_4-8bit/generation_config.json DELETED
@@ -1,12 +0,0 @@
1
- {
2
- "bos_token_id": 128000,
3
- "do_sample": true,
4
- "eos_token_id": [
5
- 128001,
6
- 128008,
7
- 128009
8
- ],
9
- "temperature": 0.6,
10
- "top_p": 0.9,
11
- "transformers_version": "4.57.3"
12
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw7.54_4-8bit/model-00001-of-00004.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:949a717376d70bd7c14cb9f0a04ef3e48fa6c9571a0959dbad1d7816052530b1
3
- size 4976698592
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw7.54_4-8bit/model-00002-of-00004.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f33b8cada7e12ac207e90dafa27ee6b859f29d88c40984da826204a1091e5b3
3
- size 4999802616
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw7.54_4-8bit/model-00003-of-00004.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7e16163743bc24257c0d41837eeea6ce95d243cfb00ffe7bf0f30f63dc0e6d4
3
- size 4915916080
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw7.54_4-8bit/model-00004-of-00004.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:44408391c116c33adf6e43ab53f84d75bee5e2956b293c34dc60509fb0fd825b
3
- size 1168138808
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw7.54_4-8bit/model.safetensors.index.json DELETED
@@ -1,299 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_parameters": 8030261248,
4
- "total_size": 16060522496
5
- },
6
- "weight_map": {
7
- "lm_head.weight": "model-00004-of-00004.safetensors",
8
- "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
- "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
17
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
18
- "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
19
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
20
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
21
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
22
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
23
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
24
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
25
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
26
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
27
- "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
28
- "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
29
- "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
30
- "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
31
- "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
32
- "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
33
- "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
34
- "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
35
- "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
36
- "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
37
- "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
38
- "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
39
- "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
40
- "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
41
- "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
42
- "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
43
- "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
44
- "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
45
- "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
46
- "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
47
- "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
48
- "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
49
- "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
50
- "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
- "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
- "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
53
- "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
54
- "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
55
- "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
56
- "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
57
- "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
58
- "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
59
- "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
60
- "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
61
- "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
62
- "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
63
- "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
64
- "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
65
- "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
66
- "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
67
- "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
68
- "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
69
- "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
70
- "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
71
- "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
72
- "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
73
- "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
74
- "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
75
- "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
76
- "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
77
- "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
78
- "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
79
- "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
80
- "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
81
- "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
82
- "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
83
- "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
84
- "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
85
- "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
86
- "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
- "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
- "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
89
- "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
90
- "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
91
- "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
92
- "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
93
- "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
94
- "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
95
- "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
96
- "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
97
- "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
98
- "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
99
- "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
100
- "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
101
- "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
102
- "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
103
- "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
104
- "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
105
- "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
106
- "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
107
- "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
108
- "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
109
- "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
110
- "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
111
- "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
112
- "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
113
- "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
114
- "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
115
- "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
116
- "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
117
- "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
118
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
119
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
120
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
121
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
122
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
123
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
124
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
125
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
126
- "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
127
- "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
128
- "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
129
- "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
130
- "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
131
- "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
132
- "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
133
- "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
134
- "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
135
- "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
136
- "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
137
- "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
138
- "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
139
- "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
140
- "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
141
- "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
142
- "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
143
- "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
144
- "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
145
- "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
146
- "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
147
- "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
148
- "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
149
- "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
150
- "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
151
- "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
152
- "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
153
- "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
154
- "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
155
- "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
156
- "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
157
- "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
158
- "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
159
- "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
160
- "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
161
- "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
162
- "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
163
- "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
164
- "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
165
- "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
166
- "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
167
- "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
168
- "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
169
- "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
170
- "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
171
- "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
172
- "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
173
- "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
174
- "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
175
- "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
176
- "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
177
- "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
178
- "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
179
- "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
180
- "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
181
- "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
182
- "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
183
- "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
184
- "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
185
- "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
186
- "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
187
- "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
188
- "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
189
- "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
190
- "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
191
- "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
192
- "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
193
- "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
194
- "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
- "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
- "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
197
- "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
198
- "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
199
- "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
200
- "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
201
- "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
202
- "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
203
- "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
204
- "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
205
- "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
206
- "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
207
- "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
208
- "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
209
- "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
210
- "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
211
- "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
212
- "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
213
- "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
214
- "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
215
- "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
216
- "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
217
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
218
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
219
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
220
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
221
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
222
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
223
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
224
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
225
- "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
226
- "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
227
- "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
228
- "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
229
- "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
230
- "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
- "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
- "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
233
- "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
234
- "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
235
- "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
236
- "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
237
- "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
238
- "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
239
- "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
240
- "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
241
- "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
242
- "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
243
- "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
244
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
245
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
246
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
247
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
248
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
249
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
250
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
251
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
252
- "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
253
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
254
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
255
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
256
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
257
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
258
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
259
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
260
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
261
- "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
262
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
263
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
264
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
265
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
266
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
269
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
270
- "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
271
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
272
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
273
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
274
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
275
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
276
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
277
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
278
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
279
- "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
280
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
281
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
282
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
283
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
284
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
285
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
286
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
287
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
288
- "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
289
- "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
290
- "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
291
- "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
292
- "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
293
- "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
294
- "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
295
- "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
296
- "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
297
- "model.norm.weight": "model-00004-of-00004.safetensors"
298
- }
299
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw7.54_4-8bit/quantization_config.txt DELETED
@@ -1,250 +0,0 @@
1
- # Model: meta-llama/Llama-3.1-8B-Instruct
2
- # Layer directory: /nfs/scistore19/alistgrp/mhelcig/local/data/search/4_5_6_7_8bit_asym_g128/Llama-3.1-8B-Instruct/6bit/
3
- # Sensitivity method: shapley
4
- # Estimation method: permutation_separate
5
- # Available bitwidths: [4, 8]
6
- # Bitwidth map: {4: 4.3125, 5: 5.3125, 6: 6.3125, 7: 7.3125, 8: 8.3125}
7
- #
8
- # Mode: predicted_constraint_search
9
- # Constraint max_kl: 0.01
10
- # Constraint min_eap: 0.99
11
- # Weights: nll=0.0, kl=0.0, eap=1.0
12
- #
13
- # Average bitwidth: 7.5385
14
- # Total params: 6979321856
15
- # Total bits: 52613349376
16
- # Predicted KL: 0.005405
17
- # Predicted EAP: 0.990085
18
- # Predicted ETL: 0.009915
19
- # Satisfies constraints: True
20
- # Solver calls: 1
21
- # Evaluations: 0
22
- #
23
- # Bitwidth distribution:
24
- # 8-bit: 201 layers (89.7%)
25
- # 4-bit: 23 layers (10.3%)
26
- #
27
- model.layers.0.self_attn.q_proj: 8
28
- model.layers.0.self_attn.k_proj: 8
29
- model.layers.0.self_attn.v_proj: 8
30
- model.layers.0.self_attn.o_proj: 8
31
- model.layers.0.mlp.gate_proj: 4
32
- model.layers.0.mlp.up_proj: 4
33
- model.layers.0.mlp.down_proj: 8
34
- model.layers.1.self_attn.q_proj: 8
35
- model.layers.1.self_attn.k_proj: 8
36
- model.layers.1.self_attn.v_proj: 8
37
- model.layers.1.self_attn.o_proj: 8
38
- model.layers.1.mlp.gate_proj: 8
39
- model.layers.1.mlp.up_proj: 8
40
- model.layers.1.mlp.down_proj: 8
41
- model.layers.2.self_attn.q_proj: 8
42
- model.layers.2.self_attn.k_proj: 8
43
- model.layers.2.self_attn.v_proj: 8
44
- model.layers.2.self_attn.o_proj: 8
45
- model.layers.2.mlp.gate_proj: 8
46
- model.layers.2.mlp.up_proj: 8
47
- model.layers.2.mlp.down_proj: 4
48
- model.layers.3.self_attn.q_proj: 8
49
- model.layers.3.self_attn.k_proj: 8
50
- model.layers.3.self_attn.v_proj: 8
51
- model.layers.3.self_attn.o_proj: 8
52
- model.layers.3.mlp.gate_proj: 8
53
- model.layers.3.mlp.up_proj: 8
54
- model.layers.3.mlp.down_proj: 8
55
- model.layers.4.self_attn.q_proj: 8
56
- model.layers.4.self_attn.k_proj: 8
57
- model.layers.4.self_attn.v_proj: 8
58
- model.layers.4.self_attn.o_proj: 8
59
- model.layers.4.mlp.gate_proj: 8
60
- model.layers.4.mlp.up_proj: 8
61
- model.layers.4.mlp.down_proj: 8
62
- model.layers.5.self_attn.q_proj: 8
63
- model.layers.5.self_attn.k_proj: 8
64
- model.layers.5.self_attn.v_proj: 8
65
- model.layers.5.self_attn.o_proj: 8
66
- model.layers.5.mlp.gate_proj: 8
67
- model.layers.5.mlp.up_proj: 8
68
- model.layers.5.mlp.down_proj: 8
69
- model.layers.6.self_attn.q_proj: 8
70
- model.layers.6.self_attn.k_proj: 8
71
- model.layers.6.self_attn.v_proj: 8
72
- model.layers.6.self_attn.o_proj: 8
73
- model.layers.6.mlp.gate_proj: 8
74
- model.layers.6.mlp.up_proj: 8
75
- model.layers.6.mlp.down_proj: 8
76
- model.layers.7.self_attn.q_proj: 8
77
- model.layers.7.self_attn.k_proj: 8
78
- model.layers.7.self_attn.v_proj: 8
79
- model.layers.7.self_attn.o_proj: 8
80
- model.layers.7.mlp.gate_proj: 8
81
- model.layers.7.mlp.up_proj: 8
82
- model.layers.7.mlp.down_proj: 4
83
- model.layers.8.self_attn.q_proj: 8
84
- model.layers.8.self_attn.k_proj: 8
85
- model.layers.8.self_attn.v_proj: 8
86
- model.layers.8.self_attn.o_proj: 8
87
- model.layers.8.mlp.gate_proj: 8
88
- model.layers.8.mlp.up_proj: 8
89
- model.layers.8.mlp.down_proj: 4
90
- model.layers.9.self_attn.q_proj: 8
91
- model.layers.9.self_attn.k_proj: 8
92
- model.layers.9.self_attn.v_proj: 8
93
- model.layers.9.self_attn.o_proj: 8
94
- model.layers.9.mlp.gate_proj: 8
95
- model.layers.9.mlp.up_proj: 8
96
- model.layers.9.mlp.down_proj: 4
97
- model.layers.10.self_attn.q_proj: 8
98
- model.layers.10.self_attn.k_proj: 8
99
- model.layers.10.self_attn.v_proj: 8
100
- model.layers.10.self_attn.o_proj: 8
101
- model.layers.10.mlp.gate_proj: 8
102
- model.layers.10.mlp.up_proj: 8
103
- model.layers.10.mlp.down_proj: 4
104
- model.layers.11.self_attn.q_proj: 8
105
- model.layers.11.self_attn.k_proj: 8
106
- model.layers.11.self_attn.v_proj: 8
107
- model.layers.11.self_attn.o_proj: 8
108
- model.layers.11.mlp.gate_proj: 8
109
- model.layers.11.mlp.up_proj: 8
110
- model.layers.11.mlp.down_proj: 4
111
- model.layers.12.self_attn.q_proj: 8
112
- model.layers.12.self_attn.k_proj: 8
113
- model.layers.12.self_attn.v_proj: 8
114
- model.layers.12.self_attn.o_proj: 8
115
- model.layers.12.mlp.gate_proj: 8
116
- model.layers.12.mlp.up_proj: 8
117
- model.layers.12.mlp.down_proj: 4
118
- model.layers.13.self_attn.q_proj: 8
119
- model.layers.13.self_attn.k_proj: 8
120
- model.layers.13.self_attn.v_proj: 8
121
- model.layers.13.self_attn.o_proj: 8
122
- model.layers.13.mlp.gate_proj: 8
123
- model.layers.13.mlp.up_proj: 8
124
- model.layers.13.mlp.down_proj: 8
125
- model.layers.14.self_attn.q_proj: 8
126
- model.layers.14.self_attn.k_proj: 8
127
- model.layers.14.self_attn.v_proj: 8
128
- model.layers.14.self_attn.o_proj: 8
129
- model.layers.14.mlp.gate_proj: 8
130
- model.layers.14.mlp.up_proj: 8
131
- model.layers.14.mlp.down_proj: 8
132
- model.layers.15.self_attn.q_proj: 8
133
- model.layers.15.self_attn.k_proj: 8
134
- model.layers.15.self_attn.v_proj: 8
135
- model.layers.15.self_attn.o_proj: 8
136
- model.layers.15.mlp.gate_proj: 8
137
- model.layers.15.mlp.up_proj: 8
138
- model.layers.15.mlp.down_proj: 8
139
- model.layers.16.self_attn.q_proj: 8
140
- model.layers.16.self_attn.k_proj: 8
141
- model.layers.16.self_attn.v_proj: 8
142
- model.layers.16.self_attn.o_proj: 8
143
- model.layers.16.mlp.gate_proj: 8
144
- model.layers.16.mlp.up_proj: 8
145
- model.layers.16.mlp.down_proj: 8
146
- model.layers.17.self_attn.q_proj: 8
147
- model.layers.17.self_attn.k_proj: 8
148
- model.layers.17.self_attn.v_proj: 8
149
- model.layers.17.self_attn.o_proj: 8
150
- model.layers.17.mlp.gate_proj: 8
151
- model.layers.17.mlp.up_proj: 8
152
- model.layers.17.mlp.down_proj: 8
153
- model.layers.18.self_attn.q_proj: 8
154
- model.layers.18.self_attn.k_proj: 8
155
- model.layers.18.self_attn.v_proj: 8
156
- model.layers.18.self_attn.o_proj: 8
157
- model.layers.18.mlp.gate_proj: 8
158
- model.layers.18.mlp.up_proj: 8
159
- model.layers.18.mlp.down_proj: 8
160
- model.layers.19.self_attn.q_proj: 8
161
- model.layers.19.self_attn.k_proj: 8
162
- model.layers.19.self_attn.v_proj: 8
163
- model.layers.19.self_attn.o_proj: 8
164
- model.layers.19.mlp.gate_proj: 8
165
- model.layers.19.mlp.up_proj: 8
166
- model.layers.19.mlp.down_proj: 4
167
- model.layers.20.self_attn.q_proj: 8
168
- model.layers.20.self_attn.k_proj: 8
169
- model.layers.20.self_attn.v_proj: 8
170
- model.layers.20.self_attn.o_proj: 8
171
- model.layers.20.mlp.gate_proj: 8
172
- model.layers.20.mlp.up_proj: 8
173
- model.layers.20.mlp.down_proj: 8
174
- model.layers.21.self_attn.q_proj: 8
175
- model.layers.21.self_attn.k_proj: 8
176
- model.layers.21.self_attn.v_proj: 8
177
- model.layers.21.self_attn.o_proj: 8
178
- model.layers.21.mlp.gate_proj: 4
179
- model.layers.21.mlp.up_proj: 4
180
- model.layers.21.mlp.down_proj: 8
181
- model.layers.22.self_attn.q_proj: 8
182
- model.layers.22.self_attn.k_proj: 8
183
- model.layers.22.self_attn.v_proj: 8
184
- model.layers.22.self_attn.o_proj: 8
185
- model.layers.22.mlp.gate_proj: 8
186
- model.layers.22.mlp.up_proj: 8
187
- model.layers.22.mlp.down_proj: 4
188
- model.layers.23.self_attn.q_proj: 8
189
- model.layers.23.self_attn.k_proj: 8
190
- model.layers.23.self_attn.v_proj: 8
191
- model.layers.23.self_attn.o_proj: 8
192
- model.layers.23.mlp.gate_proj: 8
193
- model.layers.23.mlp.up_proj: 8
194
- model.layers.23.mlp.down_proj: 4
195
- model.layers.24.self_attn.q_proj: 8
196
- model.layers.24.self_attn.k_proj: 8
197
- model.layers.24.self_attn.v_proj: 8
198
- model.layers.24.self_attn.o_proj: 8
199
- model.layers.24.mlp.gate_proj: 8
200
- model.layers.24.mlp.up_proj: 8
201
- model.layers.24.mlp.down_proj: 4
202
- model.layers.25.self_attn.q_proj: 8
203
- model.layers.25.self_attn.k_proj: 8
204
- model.layers.25.self_attn.v_proj: 8
205
- model.layers.25.self_attn.o_proj: 8
206
- model.layers.25.mlp.gate_proj: 8
207
- model.layers.25.mlp.up_proj: 8
208
- model.layers.25.mlp.down_proj: 4
209
- model.layers.26.self_attn.q_proj: 8
210
- model.layers.26.self_attn.k_proj: 8
211
- model.layers.26.self_attn.v_proj: 8
212
- model.layers.26.self_attn.o_proj: 8
213
- model.layers.26.mlp.gate_proj: 8
214
- model.layers.26.mlp.up_proj: 4
215
- model.layers.26.mlp.down_proj: 4
216
- model.layers.27.self_attn.q_proj: 8
217
- model.layers.27.self_attn.k_proj: 8
218
- model.layers.27.self_attn.v_proj: 8
219
- model.layers.27.self_attn.o_proj: 8
220
- model.layers.27.mlp.gate_proj: 8
221
- model.layers.27.mlp.up_proj: 8
222
- model.layers.27.mlp.down_proj: 4
223
- model.layers.28.self_attn.q_proj: 8
224
- model.layers.28.self_attn.k_proj: 8
225
- model.layers.28.self_attn.v_proj: 8
226
- model.layers.28.self_attn.o_proj: 8
227
- model.layers.28.mlp.gate_proj: 4
228
- model.layers.28.mlp.up_proj: 4
229
- model.layers.28.mlp.down_proj: 4
230
- model.layers.29.self_attn.q_proj: 8
231
- model.layers.29.self_attn.k_proj: 8
232
- model.layers.29.self_attn.v_proj: 8
233
- model.layers.29.self_attn.o_proj: 8
234
- model.layers.29.mlp.gate_proj: 8
235
- model.layers.29.mlp.up_proj: 8
236
- model.layers.29.mlp.down_proj: 4
237
- model.layers.30.self_attn.q_proj: 8
238
- model.layers.30.self_attn.k_proj: 8
239
- model.layers.30.self_attn.v_proj: 8
240
- model.layers.30.self_attn.o_proj: 8
241
- model.layers.30.mlp.gate_proj: 8
242
- model.layers.30.mlp.up_proj: 8
243
- model.layers.30.mlp.down_proj: 8
244
- model.layers.31.self_attn.q_proj: 8
245
- model.layers.31.self_attn.k_proj: 8
246
- model.layers.31.self_attn.v_proj: 8
247
- model.layers.31.self_attn.o_proj: 8
248
- model.layers.31.mlp.gate_proj: 8
249
- model.layers.31.mlp.up_proj: 8
250
- model.layers.31.mlp.down_proj: 8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw7.54_4-8bit/special_tokens_map.json DELETED
@@ -1,17 +0,0 @@
1
- {
2
- "bos_token": {
3
- "content": "<|begin_of_text|>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "<|eot_id|>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": "<|eot_id|>"
17
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw7.54_4-8bit/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
- size 17209920
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_eap0.99_sha_bw7.54_4-8bit/tokenizer_config.json DELETED
@@ -1,2063 +0,0 @@
1
- {
2
- "added_tokens_decoder": {
3
- "128000": {
4
- "content": "<|begin_of_text|>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "128001": {
12
- "content": "<|end_of_text|>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "128002": {
20
- "content": "<|reserved_special_token_0|>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "128003": {
28
- "content": "<|reserved_special_token_1|>",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "128004": {
36
- "content": "<|finetune_right_pad_id|>",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- },
43
- "128005": {
44
- "content": "<|reserved_special_token_2|>",
45
- "lstrip": false,
46
- "normalized": false,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": true
50
- },
51
- "128006": {
52
- "content": "<|start_header_id|>",
53
- "lstrip": false,
54
- "normalized": false,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": true
58
- },
59
- "128007": {
60
- "content": "<|end_header_id|>",
61
- "lstrip": false,
62
- "normalized": false,
63
- "rstrip": false,
64
- "single_word": false,
65
- "special": true
66
- },
67
- "128008": {
68
- "content": "<|eom_id|>",
69
- "lstrip": false,
70
- "normalized": false,
71
- "rstrip": false,
72
- "single_word": false,
73
- "special": true
74
- },
75
- "128009": {
76
- "content": "<|eot_id|>",
77
- "lstrip": false,
78
- "normalized": false,
79
- "rstrip": false,
80
- "single_word": false,
81
- "special": true
82
- },
83
- "128010": {
84
- "content": "<|python_tag|>",
85
- "lstrip": false,
86
- "normalized": false,
87
- "rstrip": false,
88
- "single_word": false,
89
- "special": true
90
- },
91
- "128011": {
92
- "content": "<|reserved_special_token_3|>",
93
- "lstrip": false,
94
- "normalized": false,
95
- "rstrip": false,
96
- "single_word": false,
97
- "special": true
98
- },
99
- "128012": {
100
- "content": "<|reserved_special_token_4|>",
101
- "lstrip": false,
102
- "normalized": false,
103
- "rstrip": false,
104
- "single_word": false,
105
- "special": true
106
- },
107
- "128013": {
108
- "content": "<|reserved_special_token_5|>",
109
- "lstrip": false,
110
- "normalized": false,
111
- "rstrip": false,
112
- "single_word": false,
113
- "special": true
114
- },
115
- "128014": {
116
- "content": "<|reserved_special_token_6|>",
117
- "lstrip": false,
118
- "normalized": false,
119
- "rstrip": false,
120
- "single_word": false,
121
- "special": true
122
- },
123
- "128015": {
124
- "content": "<|reserved_special_token_7|>",
125
- "lstrip": false,
126
- "normalized": false,
127
- "rstrip": false,
128
- "single_word": false,
129
- "special": true
130
- },
131
- "128016": {
132
- "content": "<|reserved_special_token_8|>",
133
- "lstrip": false,
134
- "normalized": false,
135
- "rstrip": false,
136
- "single_word": false,
137
- "special": true
138
- },
139
- "128017": {
140
- "content": "<|reserved_special_token_9|>",
141
- "lstrip": false,
142
- "normalized": false,
143
- "rstrip": false,
144
- "single_word": false,
145
- "special": true
146
- },
147
- "128018": {
148
- "content": "<|reserved_special_token_10|>",
149
- "lstrip": false,
150
- "normalized": false,
151
- "rstrip": false,
152
- "single_word": false,
153
- "special": true
154
- },
155
- "128019": {
156
- "content": "<|reserved_special_token_11|>",
157
- "lstrip": false,
158
- "normalized": false,
159
- "rstrip": false,
160
- "single_word": false,
161
- "special": true
162
- },
163
- "128020": {
164
- "content": "<|reserved_special_token_12|>",
165
- "lstrip": false,
166
- "normalized": false,
167
- "rstrip": false,
168
- "single_word": false,
169
- "special": true
170
- },
171
- "128021": {
172
- "content": "<|reserved_special_token_13|>",
173
- "lstrip": false,
174
- "normalized": false,
175
- "rstrip": false,
176
- "single_word": false,
177
- "special": true
178
- },
179
- "128022": {
180
- "content": "<|reserved_special_token_14|>",
181
- "lstrip": false,
182
- "normalized": false,
183
- "rstrip": false,
184
- "single_word": false,
185
- "special": true
186
- },
187
- "128023": {
188
- "content": "<|reserved_special_token_15|>",
189
- "lstrip": false,
190
- "normalized": false,
191
- "rstrip": false,
192
- "single_word": false,
193
- "special": true
194
- },
195
- "128024": {
196
- "content": "<|reserved_special_token_16|>",
197
- "lstrip": false,
198
- "normalized": false,
199
- "rstrip": false,
200
- "single_word": false,
201
- "special": true
202
- },
203
- "128025": {
204
- "content": "<|reserved_special_token_17|>",
205
- "lstrip": false,
206
- "normalized": false,
207
- "rstrip": false,
208
- "single_word": false,
209
- "special": true
210
- },
211
- "128026": {
212
- "content": "<|reserved_special_token_18|>",
213
- "lstrip": false,
214
- "normalized": false,
215
- "rstrip": false,
216
- "single_word": false,
217
- "special": true
218
- },
219
- "128027": {
220
- "content": "<|reserved_special_token_19|>",
221
- "lstrip": false,
222
- "normalized": false,
223
- "rstrip": false,
224
- "single_word": false,
225
- "special": true
226
- },
227
- "128028": {
228
- "content": "<|reserved_special_token_20|>",
229
- "lstrip": false,
230
- "normalized": false,
231
- "rstrip": false,
232
- "single_word": false,
233
- "special": true
234
- },
235
- "128029": {
236
- "content": "<|reserved_special_token_21|>",
237
- "lstrip": false,
238
- "normalized": false,
239
- "rstrip": false,
240
- "single_word": false,
241
- "special": true
242
- },
243
- "128030": {
244
- "content": "<|reserved_special_token_22|>",
245
- "lstrip": false,
246
- "normalized": false,
247
- "rstrip": false,
248
- "single_word": false,
249
- "special": true
250
- },
251
- "128031": {
252
- "content": "<|reserved_special_token_23|>",
253
- "lstrip": false,
254
- "normalized": false,
255
- "rstrip": false,
256
- "single_word": false,
257
- "special": true
258
- },
259
- "128032": {
260
- "content": "<|reserved_special_token_24|>",
261
- "lstrip": false,
262
- "normalized": false,
263
- "rstrip": false,
264
- "single_word": false,
265
- "special": true
266
- },
267
- "128033": {
268
- "content": "<|reserved_special_token_25|>",
269
- "lstrip": false,
270
- "normalized": false,
271
- "rstrip": false,
272
- "single_word": false,
273
- "special": true
274
- },
275
- "128034": {
276
- "content": "<|reserved_special_token_26|>",
277
- "lstrip": false,
278
- "normalized": false,
279
- "rstrip": false,
280
- "single_word": false,
281
- "special": true
282
- },
283
- "128035": {
284
- "content": "<|reserved_special_token_27|>",
285
- "lstrip": false,
286
- "normalized": false,
287
- "rstrip": false,
288
- "single_word": false,
289
- "special": true
290
- },
291
- "128036": {
292
- "content": "<|reserved_special_token_28|>",
293
- "lstrip": false,
294
- "normalized": false,
295
- "rstrip": false,
296
- "single_word": false,
297
- "special": true
298
- },
299
- "128037": {
300
- "content": "<|reserved_special_token_29|>",
301
- "lstrip": false,
302
- "normalized": false,
303
- "rstrip": false,
304
- "single_word": false,
305
- "special": true
306
- },
307
- "128038": {
308
- "content": "<|reserved_special_token_30|>",
309
- "lstrip": false,
310
- "normalized": false,
311
- "rstrip": false,
312
- "single_word": false,
313
- "special": true
314
- },
315
- "128039": {
316
- "content": "<|reserved_special_token_31|>",
317
- "lstrip": false,
318
- "normalized": false,
319
- "rstrip": false,
320
- "single_word": false,
321
- "special": true
322
- },
323
- "128040": {
324
- "content": "<|reserved_special_token_32|>",
325
- "lstrip": false,
326
- "normalized": false,
327
- "rstrip": false,
328
- "single_word": false,
329
- "special": true
330
- },
331
- "128041": {
332
- "content": "<|reserved_special_token_33|>",
333
- "lstrip": false,
334
- "normalized": false,
335
- "rstrip": false,
336
- "single_word": false,
337
- "special": true
338
- },
339
- "128042": {
340
- "content": "<|reserved_special_token_34|>",
341
- "lstrip": false,
342
- "normalized": false,
343
- "rstrip": false,
344
- "single_word": false,
345
- "special": true
346
- },
347
- "128043": {
348
- "content": "<|reserved_special_token_35|>",
349
- "lstrip": false,
350
- "normalized": false,
351
- "rstrip": false,
352
- "single_word": false,
353
- "special": true
354
- },
355
- "128044": {
356
- "content": "<|reserved_special_token_36|>",
357
- "lstrip": false,
358
- "normalized": false,
359
- "rstrip": false,
360
- "single_word": false,
361
- "special": true
362
- },
363
- "128045": {
364
- "content": "<|reserved_special_token_37|>",
365
- "lstrip": false,
366
- "normalized": false,
367
- "rstrip": false,
368
- "single_word": false,
369
- "special": true
370
- },
371
- "128046": {
372
- "content": "<|reserved_special_token_38|>",
373
- "lstrip": false,
374
- "normalized": false,
375
- "rstrip": false,
376
- "single_word": false,
377
- "special": true
378
- },
379
- "128047": {
380
- "content": "<|reserved_special_token_39|>",
381
- "lstrip": false,
382
- "normalized": false,
383
- "rstrip": false,
384
- "single_word": false,
385
- "special": true
386
- },
387
- "128048": {
388
- "content": "<|reserved_special_token_40|>",
389
- "lstrip": false,
390
- "normalized": false,
391
- "rstrip": false,
392
- "single_word": false,
393
- "special": true
394
- },
395
- "128049": {
396
- "content": "<|reserved_special_token_41|>",
397
- "lstrip": false,
398
- "normalized": false,
399
- "rstrip": false,
400
- "single_word": false,
401
- "special": true
402
- },
403
- "128050": {
404
- "content": "<|reserved_special_token_42|>",
405
- "lstrip": false,
406
- "normalized": false,
407
- "rstrip": false,
408
- "single_word": false,
409
- "special": true
410
- },
411
- "128051": {
412
- "content": "<|reserved_special_token_43|>",
413
- "lstrip": false,
414
- "normalized": false,
415
- "rstrip": false,
416
- "single_word": false,
417
- "special": true
418
- },
419
- "128052": {
420
- "content": "<|reserved_special_token_44|>",
421
- "lstrip": false,
422
- "normalized": false,
423
- "rstrip": false,
424
- "single_word": false,
425
- "special": true
426
- },
427
- "128053": {
428
- "content": "<|reserved_special_token_45|>",
429
- "lstrip": false,
430
- "normalized": false,
431
- "rstrip": false,
432
- "single_word": false,
433
- "special": true
434
- },
435
- "128054": {
436
- "content": "<|reserved_special_token_46|>",
437
- "lstrip": false,
438
- "normalized": false,
439
- "rstrip": false,
440
- "single_word": false,
441
- "special": true
442
- },
443
- "128055": {
444
- "content": "<|reserved_special_token_47|>",
445
- "lstrip": false,
446
- "normalized": false,
447
- "rstrip": false,
448
- "single_word": false,
449
- "special": true
450
- },
451
- "128056": {
452
- "content": "<|reserved_special_token_48|>",
453
- "lstrip": false,
454
- "normalized": false,
455
- "rstrip": false,
456
- "single_word": false,
457
- "special": true
458
- },
459
- "128057": {
460
- "content": "<|reserved_special_token_49|>",
461
- "lstrip": false,
462
- "normalized": false,
463
- "rstrip": false,
464
- "single_word": false,
465
- "special": true
466
- },
467
- "128058": {
468
- "content": "<|reserved_special_token_50|>",
469
- "lstrip": false,
470
- "normalized": false,
471
- "rstrip": false,
472
- "single_word": false,
473
- "special": true
474
- },
475
- "128059": {
476
- "content": "<|reserved_special_token_51|>",
477
- "lstrip": false,
478
- "normalized": false,
479
- "rstrip": false,
480
- "single_word": false,
481
- "special": true
482
- },
483
- "128060": {
484
- "content": "<|reserved_special_token_52|>",
485
- "lstrip": false,
486
- "normalized": false,
487
- "rstrip": false,
488
- "single_word": false,
489
- "special": true
490
- },
491
- "128061": {
492
- "content": "<|reserved_special_token_53|>",
493
- "lstrip": false,
494
- "normalized": false,
495
- "rstrip": false,
496
- "single_word": false,
497
- "special": true
498
- },
499
- "128062": {
500
- "content": "<|reserved_special_token_54|>",
501
- "lstrip": false,
502
- "normalized": false,
503
- "rstrip": false,
504
- "single_word": false,
505
- "special": true
506
- },
507
- "128063": {
508
- "content": "<|reserved_special_token_55|>",
509
- "lstrip": false,
510
- "normalized": false,
511
- "rstrip": false,
512
- "single_word": false,
513
- "special": true
514
- },
515
- "128064": {
516
- "content": "<|reserved_special_token_56|>",
517
- "lstrip": false,
518
- "normalized": false,
519
- "rstrip": false,
520
- "single_word": false,
521
- "special": true
522
- },
523
- "128065": {
524
- "content": "<|reserved_special_token_57|>",
525
- "lstrip": false,
526
- "normalized": false,
527
- "rstrip": false,
528
- "single_word": false,
529
- "special": true
530
- },
531
- "128066": {
532
- "content": "<|reserved_special_token_58|>",
533
- "lstrip": false,
534
- "normalized": false,
535
- "rstrip": false,
536
- "single_word": false,
537
- "special": true
538
- },
539
- "128067": {
540
- "content": "<|reserved_special_token_59|>",
541
- "lstrip": false,
542
- "normalized": false,
543
- "rstrip": false,
544
- "single_word": false,
545
- "special": true
546
- },
547
- "128068": {
548
- "content": "<|reserved_special_token_60|>",
549
- "lstrip": false,
550
- "normalized": false,
551
- "rstrip": false,
552
- "single_word": false,
553
- "special": true
554
- },
555
- "128069": {
556
- "content": "<|reserved_special_token_61|>",
557
- "lstrip": false,
558
- "normalized": false,
559
- "rstrip": false,
560
- "single_word": false,
561
- "special": true
562
- },
563
- "128070": {
564
- "content": "<|reserved_special_token_62|>",
565
- "lstrip": false,
566
- "normalized": false,
567
- "rstrip": false,
568
- "single_word": false,
569
- "special": true
570
- },
571
- "128071": {
572
- "content": "<|reserved_special_token_63|>",
573
- "lstrip": false,
574
- "normalized": false,
575
- "rstrip": false,
576
- "single_word": false,
577
- "special": true
578
- },
579
- "128072": {
580
- "content": "<|reserved_special_token_64|>",
581
- "lstrip": false,
582
- "normalized": false,
583
- "rstrip": false,
584
- "single_word": false,
585
- "special": true
586
- },
587
- "128073": {
588
- "content": "<|reserved_special_token_65|>",
589
- "lstrip": false,
590
- "normalized": false,
591
- "rstrip": false,
592
- "single_word": false,
593
- "special": true
594
- },
595
- "128074": {
596
- "content": "<|reserved_special_token_66|>",
597
- "lstrip": false,
598
- "normalized": false,
599
- "rstrip": false,
600
- "single_word": false,
601
- "special": true
602
- },
603
- "128075": {
604
- "content": "<|reserved_special_token_67|>",
605
- "lstrip": false,
606
- "normalized": false,
607
- "rstrip": false,
608
- "single_word": false,
609
- "special": true
610
- },
611
- "128076": {
612
- "content": "<|reserved_special_token_68|>",
613
- "lstrip": false,
614
- "normalized": false,
615
- "rstrip": false,
616
- "single_word": false,
617
- "special": true
618
- },
619
- "128077": {
620
- "content": "<|reserved_special_token_69|>",
621
- "lstrip": false,
622
- "normalized": false,
623
- "rstrip": false,
624
- "single_word": false,
625
- "special": true
626
- },
627
- "128078": {
628
- "content": "<|reserved_special_token_70|>",
629
- "lstrip": false,
630
- "normalized": false,
631
- "rstrip": false,
632
- "single_word": false,
633
- "special": true
634
- },
635
- "128079": {
636
- "content": "<|reserved_special_token_71|>",
637
- "lstrip": false,
638
- "normalized": false,
639
- "rstrip": false,
640
- "single_word": false,
641
- "special": true
642
- },
643
- "128080": {
644
- "content": "<|reserved_special_token_72|>",
645
- "lstrip": false,
646
- "normalized": false,
647
- "rstrip": false,
648
- "single_word": false,
649
- "special": true
650
- },
651
- "128081": {
652
- "content": "<|reserved_special_token_73|>",
653
- "lstrip": false,
654
- "normalized": false,
655
- "rstrip": false,
656
- "single_word": false,
657
- "special": true
658
- },
659
- "128082": {
660
- "content": "<|reserved_special_token_74|>",
661
- "lstrip": false,
662
- "normalized": false,
663
- "rstrip": false,
664
- "single_word": false,
665
- "special": true
666
- },
667
- "128083": {
668
- "content": "<|reserved_special_token_75|>",
669
- "lstrip": false,
670
- "normalized": false,
671
- "rstrip": false,
672
- "single_word": false,
673
- "special": true
674
- },
675
- "128084": {
676
- "content": "<|reserved_special_token_76|>",
677
- "lstrip": false,
678
- "normalized": false,
679
- "rstrip": false,
680
- "single_word": false,
681
- "special": true
682
- },
683
- "128085": {
684
- "content": "<|reserved_special_token_77|>",
685
- "lstrip": false,
686
- "normalized": false,
687
- "rstrip": false,
688
- "single_word": false,
689
- "special": true
690
- },
691
- "128086": {
692
- "content": "<|reserved_special_token_78|>",
693
- "lstrip": false,
694
- "normalized": false,
695
- "rstrip": false,
696
- "single_word": false,
697
- "special": true
698
- },
699
- "128087": {
700
- "content": "<|reserved_special_token_79|>",
701
- "lstrip": false,
702
- "normalized": false,
703
- "rstrip": false,
704
- "single_word": false,
705
- "special": true
706
- },
707
- "128088": {
708
- "content": "<|reserved_special_token_80|>",
709
- "lstrip": false,
710
- "normalized": false,
711
- "rstrip": false,
712
- "single_word": false,
713
- "special": true
714
- },
715
- "128089": {
716
- "content": "<|reserved_special_token_81|>",
717
- "lstrip": false,
718
- "normalized": false,
719
- "rstrip": false,
720
- "single_word": false,
721
- "special": true
722
- },
723
- "128090": {
724
- "content": "<|reserved_special_token_82|>",
725
- "lstrip": false,
726
- "normalized": false,
727
- "rstrip": false,
728
- "single_word": false,
729
- "special": true
730
- },
731
- "128091": {
732
- "content": "<|reserved_special_token_83|>",
733
- "lstrip": false,
734
- "normalized": false,
735
- "rstrip": false,
736
- "single_word": false,
737
- "special": true
738
- },
739
- "128092": {
740
- "content": "<|reserved_special_token_84|>",
741
- "lstrip": false,
742
- "normalized": false,
743
- "rstrip": false,
744
- "single_word": false,
745
- "special": true
746
- },
747
- "128093": {
748
- "content": "<|reserved_special_token_85|>",
749
- "lstrip": false,
750
- "normalized": false,
751
- "rstrip": false,
752
- "single_word": false,
753
- "special": true
754
- },
755
- "128094": {
756
- "content": "<|reserved_special_token_86|>",
757
- "lstrip": false,
758
- "normalized": false,
759
- "rstrip": false,
760
- "single_word": false,
761
- "special": true
762
- },
763
- "128095": {
764
- "content": "<|reserved_special_token_87|>",
765
- "lstrip": false,
766
- "normalized": false,
767
- "rstrip": false,
768
- "single_word": false,
769
- "special": true
770
- },
771
- "128096": {
772
- "content": "<|reserved_special_token_88|>",
773
- "lstrip": false,
774
- "normalized": false,
775
- "rstrip": false,
776
- "single_word": false,
777
- "special": true
778
- },
779
- "128097": {
780
- "content": "<|reserved_special_token_89|>",
781
- "lstrip": false,
782
- "normalized": false,
783
- "rstrip": false,
784
- "single_word": false,
785
- "special": true
786
- },
787
- "128098": {
788
- "content": "<|reserved_special_token_90|>",
789
- "lstrip": false,
790
- "normalized": false,
791
- "rstrip": false,
792
- "single_word": false,
793
- "special": true
794
- },
795
- "128099": {
796
- "content": "<|reserved_special_token_91|>",
797
- "lstrip": false,
798
- "normalized": false,
799
- "rstrip": false,
800
- "single_word": false,
801
- "special": true
802
- },
803
- "128100": {
804
- "content": "<|reserved_special_token_92|>",
805
- "lstrip": false,
806
- "normalized": false,
807
- "rstrip": false,
808
- "single_word": false,
809
- "special": true
810
- },
811
- "128101": {
812
- "content": "<|reserved_special_token_93|>",
813
- "lstrip": false,
814
- "normalized": false,
815
- "rstrip": false,
816
- "single_word": false,
817
- "special": true
818
- },
819
- "128102": {
820
- "content": "<|reserved_special_token_94|>",
821
- "lstrip": false,
822
- "normalized": false,
823
- "rstrip": false,
824
- "single_word": false,
825
- "special": true
826
- },
827
- "128103": {
828
- "content": "<|reserved_special_token_95|>",
829
- "lstrip": false,
830
- "normalized": false,
831
- "rstrip": false,
832
- "single_word": false,
833
- "special": true
834
- },
835
- "128104": {
836
- "content": "<|reserved_special_token_96|>",
837
- "lstrip": false,
838
- "normalized": false,
839
- "rstrip": false,
840
- "single_word": false,
841
- "special": true
842
- },
843
- "128105": {
844
- "content": "<|reserved_special_token_97|>",
845
- "lstrip": false,
846
- "normalized": false,
847
- "rstrip": false,
848
- "single_word": false,
849
- "special": true
850
- },
851
- "128106": {
852
- "content": "<|reserved_special_token_98|>",
853
- "lstrip": false,
854
- "normalized": false,
855
- "rstrip": false,
856
- "single_word": false,
857
- "special": true
858
- },
859
- "128107": {
860
- "content": "<|reserved_special_token_99|>",
861
- "lstrip": false,
862
- "normalized": false,
863
- "rstrip": false,
864
- "single_word": false,
865
- "special": true
866
- },
867
- "128108": {
868
- "content": "<|reserved_special_token_100|>",
869
- "lstrip": false,
870
- "normalized": false,
871
- "rstrip": false,
872
- "single_word": false,
873
- "special": true
874
- },
875
- "128109": {
876
- "content": "<|reserved_special_token_101|>",
877
- "lstrip": false,
878
- "normalized": false,
879
- "rstrip": false,
880
- "single_word": false,
881
- "special": true
882
- },
883
- "128110": {
884
- "content": "<|reserved_special_token_102|>",
885
- "lstrip": false,
886
- "normalized": false,
887
- "rstrip": false,
888
- "single_word": false,
889
- "special": true
890
- },
891
- "128111": {
892
- "content": "<|reserved_special_token_103|>",
893
- "lstrip": false,
894
- "normalized": false,
895
- "rstrip": false,
896
- "single_word": false,
897
- "special": true
898
- },
899
- "128112": {
900
- "content": "<|reserved_special_token_104|>",
901
- "lstrip": false,
902
- "normalized": false,
903
- "rstrip": false,
904
- "single_word": false,
905
- "special": true
906
- },
907
- "128113": {
908
- "content": "<|reserved_special_token_105|>",
909
- "lstrip": false,
910
- "normalized": false,
911
- "rstrip": false,
912
- "single_word": false,
913
- "special": true
914
- },
915
- "128114": {
916
- "content": "<|reserved_special_token_106|>",
917
- "lstrip": false,
918
- "normalized": false,
919
- "rstrip": false,
920
- "single_word": false,
921
- "special": true
922
- },
923
- "128115": {
924
- "content": "<|reserved_special_token_107|>",
925
- "lstrip": false,
926
- "normalized": false,
927
- "rstrip": false,
928
- "single_word": false,
929
- "special": true
930
- },
931
- "128116": {
932
- "content": "<|reserved_special_token_108|>",
933
- "lstrip": false,
934
- "normalized": false,
935
- "rstrip": false,
936
- "single_word": false,
937
- "special": true
938
- },
939
- "128117": {
940
- "content": "<|reserved_special_token_109|>",
941
- "lstrip": false,
942
- "normalized": false,
943
- "rstrip": false,
944
- "single_word": false,
945
- "special": true
946
- },
947
- "128118": {
948
- "content": "<|reserved_special_token_110|>",
949
- "lstrip": false,
950
- "normalized": false,
951
- "rstrip": false,
952
- "single_word": false,
953
- "special": true
954
- },
955
- "128119": {
956
- "content": "<|reserved_special_token_111|>",
957
- "lstrip": false,
958
- "normalized": false,
959
- "rstrip": false,
960
- "single_word": false,
961
- "special": true
962
- },
963
- "128120": {
964
- "content": "<|reserved_special_token_112|>",
965
- "lstrip": false,
966
- "normalized": false,
967
- "rstrip": false,
968
- "single_word": false,
969
- "special": true
970
- },
971
- "128121": {
972
- "content": "<|reserved_special_token_113|>",
973
- "lstrip": false,
974
- "normalized": false,
975
- "rstrip": false,
976
- "single_word": false,
977
- "special": true
978
- },
979
- "128122": {
980
- "content": "<|reserved_special_token_114|>",
981
- "lstrip": false,
982
- "normalized": false,
983
- "rstrip": false,
984
- "single_word": false,
985
- "special": true
986
- },
987
- "128123": {
988
- "content": "<|reserved_special_token_115|>",
989
- "lstrip": false,
990
- "normalized": false,
991
- "rstrip": false,
992
- "single_word": false,
993
- "special": true
994
- },
995
- "128124": {
996
- "content": "<|reserved_special_token_116|>",
997
- "lstrip": false,
998
- "normalized": false,
999
- "rstrip": false,
1000
- "single_word": false,
1001
- "special": true
1002
- },
1003
- "128125": {
1004
- "content": "<|reserved_special_token_117|>",
1005
- "lstrip": false,
1006
- "normalized": false,
1007
- "rstrip": false,
1008
- "single_word": false,
1009
- "special": true
1010
- },
1011
- "128126": {
1012
- "content": "<|reserved_special_token_118|>",
1013
- "lstrip": false,
1014
- "normalized": false,
1015
- "rstrip": false,
1016
- "single_word": false,
1017
- "special": true
1018
- },
1019
- "128127": {
1020
- "content": "<|reserved_special_token_119|>",
1021
- "lstrip": false,
1022
- "normalized": false,
1023
- "rstrip": false,
1024
- "single_word": false,
1025
- "special": true
1026
- },
1027
- "128128": {
1028
- "content": "<|reserved_special_token_120|>",
1029
- "lstrip": false,
1030
- "normalized": false,
1031
- "rstrip": false,
1032
- "single_word": false,
1033
- "special": true
1034
- },
1035
- "128129": {
1036
- "content": "<|reserved_special_token_121|>",
1037
- "lstrip": false,
1038
- "normalized": false,
1039
- "rstrip": false,
1040
- "single_word": false,
1041
- "special": true
1042
- },
1043
- "128130": {
1044
- "content": "<|reserved_special_token_122|>",
1045
- "lstrip": false,
1046
- "normalized": false,
1047
- "rstrip": false,
1048
- "single_word": false,
1049
- "special": true
1050
- },
1051
- "128131": {
1052
- "content": "<|reserved_special_token_123|>",
1053
- "lstrip": false,
1054
- "normalized": false,
1055
- "rstrip": false,
1056
- "single_word": false,
1057
- "special": true
1058
- },
1059
- "128132": {
1060
- "content": "<|reserved_special_token_124|>",
1061
- "lstrip": false,
1062
- "normalized": false,
1063
- "rstrip": false,
1064
- "single_word": false,
1065
- "special": true
1066
- },
1067
- "128133": {
1068
- "content": "<|reserved_special_token_125|>",
1069
- "lstrip": false,
1070
- "normalized": false,
1071
- "rstrip": false,
1072
- "single_word": false,
1073
- "special": true
1074
- },
1075
- "128134": {
1076
- "content": "<|reserved_special_token_126|>",
1077
- "lstrip": false,
1078
- "normalized": false,
1079
- "rstrip": false,
1080
- "single_word": false,
1081
- "special": true
1082
- },
1083
- "128135": {
1084
- "content": "<|reserved_special_token_127|>",
1085
- "lstrip": false,
1086
- "normalized": false,
1087
- "rstrip": false,
1088
- "single_word": false,
1089
- "special": true
1090
- },
1091
- "128136": {
1092
- "content": "<|reserved_special_token_128|>",
1093
- "lstrip": false,
1094
- "normalized": false,
1095
- "rstrip": false,
1096
- "single_word": false,
1097
- "special": true
1098
- },
1099
- "128137": {
1100
- "content": "<|reserved_special_token_129|>",
1101
- "lstrip": false,
1102
- "normalized": false,
1103
- "rstrip": false,
1104
- "single_word": false,
1105
- "special": true
1106
- },
1107
- "128138": {
1108
- "content": "<|reserved_special_token_130|>",
1109
- "lstrip": false,
1110
- "normalized": false,
1111
- "rstrip": false,
1112
- "single_word": false,
1113
- "special": true
1114
- },
1115
- "128139": {
1116
- "content": "<|reserved_special_token_131|>",
1117
- "lstrip": false,
1118
- "normalized": false,
1119
- "rstrip": false,
1120
- "single_word": false,
1121
- "special": true
1122
- },
1123
- "128140": {
1124
- "content": "<|reserved_special_token_132|>",
1125
- "lstrip": false,
1126
- "normalized": false,
1127
- "rstrip": false,
1128
- "single_word": false,
1129
- "special": true
1130
- },
1131
- "128141": {
1132
- "content": "<|reserved_special_token_133|>",
1133
- "lstrip": false,
1134
- "normalized": false,
1135
- "rstrip": false,
1136
- "single_word": false,
1137
- "special": true
1138
- },
1139
- "128142": {
1140
- "content": "<|reserved_special_token_134|>",
1141
- "lstrip": false,
1142
- "normalized": false,
1143
- "rstrip": false,
1144
- "single_word": false,
1145
- "special": true
1146
- },
1147
- "128143": {
1148
- "content": "<|reserved_special_token_135|>",
1149
- "lstrip": false,
1150
- "normalized": false,
1151
- "rstrip": false,
1152
- "single_word": false,
1153
- "special": true
1154
- },
1155
- "128144": {
1156
- "content": "<|reserved_special_token_136|>",
1157
- "lstrip": false,
1158
- "normalized": false,
1159
- "rstrip": false,
1160
- "single_word": false,
1161
- "special": true
1162
- },
1163
- "128145": {
1164
- "content": "<|reserved_special_token_137|>",
1165
- "lstrip": false,
1166
- "normalized": false,
1167
- "rstrip": false,
1168
- "single_word": false,
1169
- "special": true
1170
- },
1171
- "128146": {
1172
- "content": "<|reserved_special_token_138|>",
1173
- "lstrip": false,
1174
- "normalized": false,
1175
- "rstrip": false,
1176
- "single_word": false,
1177
- "special": true
1178
- },
1179
- "128147": {
1180
- "content": "<|reserved_special_token_139|>",
1181
- "lstrip": false,
1182
- "normalized": false,
1183
- "rstrip": false,
1184
- "single_word": false,
1185
- "special": true
1186
- },
1187
- "128148": {
1188
- "content": "<|reserved_special_token_140|>",
1189
- "lstrip": false,
1190
- "normalized": false,
1191
- "rstrip": false,
1192
- "single_word": false,
1193
- "special": true
1194
- },
1195
- "128149": {
1196
- "content": "<|reserved_special_token_141|>",
1197
- "lstrip": false,
1198
- "normalized": false,
1199
- "rstrip": false,
1200
- "single_word": false,
1201
- "special": true
1202
- },
1203
- "128150": {
1204
- "content": "<|reserved_special_token_142|>",
1205
- "lstrip": false,
1206
- "normalized": false,
1207
- "rstrip": false,
1208
- "single_word": false,
1209
- "special": true
1210
- },
1211
- "128151": {
1212
- "content": "<|reserved_special_token_143|>",
1213
- "lstrip": false,
1214
- "normalized": false,
1215
- "rstrip": false,
1216
- "single_word": false,
1217
- "special": true
1218
- },
1219
- "128152": {
1220
- "content": "<|reserved_special_token_144|>",
1221
- "lstrip": false,
1222
- "normalized": false,
1223
- "rstrip": false,
1224
- "single_word": false,
1225
- "special": true
1226
- },
1227
- "128153": {
1228
- "content": "<|reserved_special_token_145|>",
1229
- "lstrip": false,
1230
- "normalized": false,
1231
- "rstrip": false,
1232
- "single_word": false,
1233
- "special": true
1234
- },
1235
- "128154": {
1236
- "content": "<|reserved_special_token_146|>",
1237
- "lstrip": false,
1238
- "normalized": false,
1239
- "rstrip": false,
1240
- "single_word": false,
1241
- "special": true
1242
- },
1243
- "128155": {
1244
- "content": "<|reserved_special_token_147|>",
1245
- "lstrip": false,
1246
- "normalized": false,
1247
- "rstrip": false,
1248
- "single_word": false,
1249
- "special": true
1250
- },
1251
- "128156": {
1252
- "content": "<|reserved_special_token_148|>",
1253
- "lstrip": false,
1254
- "normalized": false,
1255
- "rstrip": false,
1256
- "single_word": false,
1257
- "special": true
1258
- },
1259
- "128157": {
1260
- "content": "<|reserved_special_token_149|>",
1261
- "lstrip": false,
1262
- "normalized": false,
1263
- "rstrip": false,
1264
- "single_word": false,
1265
- "special": true
1266
- },
1267
- "128158": {
1268
- "content": "<|reserved_special_token_150|>",
1269
- "lstrip": false,
1270
- "normalized": false,
1271
- "rstrip": false,
1272
- "single_word": false,
1273
- "special": true
1274
- },
1275
- "128159": {
1276
- "content": "<|reserved_special_token_151|>",
1277
- "lstrip": false,
1278
- "normalized": false,
1279
- "rstrip": false,
1280
- "single_word": false,
1281
- "special": true
1282
- },
1283
- "128160": {
1284
- "content": "<|reserved_special_token_152|>",
1285
- "lstrip": false,
1286
- "normalized": false,
1287
- "rstrip": false,
1288
- "single_word": false,
1289
- "special": true
1290
- },
1291
- "128161": {
1292
- "content": "<|reserved_special_token_153|>",
1293
- "lstrip": false,
1294
- "normalized": false,
1295
- "rstrip": false,
1296
- "single_word": false,
1297
- "special": true
1298
- },
1299
- "128162": {
1300
- "content": "<|reserved_special_token_154|>",
1301
- "lstrip": false,
1302
- "normalized": false,
1303
- "rstrip": false,
1304
- "single_word": false,
1305
- "special": true
1306
- },
1307
- "128163": {
1308
- "content": "<|reserved_special_token_155|>",
1309
- "lstrip": false,
1310
- "normalized": false,
1311
- "rstrip": false,
1312
- "single_word": false,
1313
- "special": true
1314
- },
1315
- "128164": {
1316
- "content": "<|reserved_special_token_156|>",
1317
- "lstrip": false,
1318
- "normalized": false,
1319
- "rstrip": false,
1320
- "single_word": false,
1321
- "special": true
1322
- },
1323
- "128165": {
1324
- "content": "<|reserved_special_token_157|>",
1325
- "lstrip": false,
1326
- "normalized": false,
1327
- "rstrip": false,
1328
- "single_word": false,
1329
- "special": true
1330
- },
1331
- "128166": {
1332
- "content": "<|reserved_special_token_158|>",
1333
- "lstrip": false,
1334
- "normalized": false,
1335
- "rstrip": false,
1336
- "single_word": false,
1337
- "special": true
1338
- },
1339
- "128167": {
1340
- "content": "<|reserved_special_token_159|>",
1341
- "lstrip": false,
1342
- "normalized": false,
1343
- "rstrip": false,
1344
- "single_word": false,
1345
- "special": true
1346
- },
1347
- "128168": {
1348
- "content": "<|reserved_special_token_160|>",
1349
- "lstrip": false,
1350
- "normalized": false,
1351
- "rstrip": false,
1352
- "single_word": false,
1353
- "special": true
1354
- },
1355
- "128169": {
1356
- "content": "<|reserved_special_token_161|>",
1357
- "lstrip": false,
1358
- "normalized": false,
1359
- "rstrip": false,
1360
- "single_word": false,
1361
- "special": true
1362
- },
1363
- "128170": {
1364
- "content": "<|reserved_special_token_162|>",
1365
- "lstrip": false,
1366
- "normalized": false,
1367
- "rstrip": false,
1368
- "single_word": false,
1369
- "special": true
1370
- },
1371
- "128171": {
1372
- "content": "<|reserved_special_token_163|>",
1373
- "lstrip": false,
1374
- "normalized": false,
1375
- "rstrip": false,
1376
- "single_word": false,
1377
- "special": true
1378
- },
1379
- "128172": {
1380
- "content": "<|reserved_special_token_164|>",
1381
- "lstrip": false,
1382
- "normalized": false,
1383
- "rstrip": false,
1384
- "single_word": false,
1385
- "special": true
1386
- },
1387
- "128173": {
1388
- "content": "<|reserved_special_token_165|>",
1389
- "lstrip": false,
1390
- "normalized": false,
1391
- "rstrip": false,
1392
- "single_word": false,
1393
- "special": true
1394
- },
1395
- "128174": {
1396
- "content": "<|reserved_special_token_166|>",
1397
- "lstrip": false,
1398
- "normalized": false,
1399
- "rstrip": false,
1400
- "single_word": false,
1401
- "special": true
1402
- },
1403
- "128175": {
1404
- "content": "<|reserved_special_token_167|>",
1405
- "lstrip": false,
1406
- "normalized": false,
1407
- "rstrip": false,
1408
- "single_word": false,
1409
- "special": true
1410
- },
1411
- "128176": {
1412
- "content": "<|reserved_special_token_168|>",
1413
- "lstrip": false,
1414
- "normalized": false,
1415
- "rstrip": false,
1416
- "single_word": false,
1417
- "special": true
1418
- },
1419
- "128177": {
1420
- "content": "<|reserved_special_token_169|>",
1421
- "lstrip": false,
1422
- "normalized": false,
1423
- "rstrip": false,
1424
- "single_word": false,
1425
- "special": true
1426
- },
1427
- "128178": {
1428
- "content": "<|reserved_special_token_170|>",
1429
- "lstrip": false,
1430
- "normalized": false,
1431
- "rstrip": false,
1432
- "single_word": false,
1433
- "special": true
1434
- },
1435
- "128179": {
1436
- "content": "<|reserved_special_token_171|>",
1437
- "lstrip": false,
1438
- "normalized": false,
1439
- "rstrip": false,
1440
- "single_word": false,
1441
- "special": true
1442
- },
1443
- "128180": {
1444
- "content": "<|reserved_special_token_172|>",
1445
- "lstrip": false,
1446
- "normalized": false,
1447
- "rstrip": false,
1448
- "single_word": false,
1449
- "special": true
1450
- },
1451
- "128181": {
1452
- "content": "<|reserved_special_token_173|>",
1453
- "lstrip": false,
1454
- "normalized": false,
1455
- "rstrip": false,
1456
- "single_word": false,
1457
- "special": true
1458
- },
1459
- "128182": {
1460
- "content": "<|reserved_special_token_174|>",
1461
- "lstrip": false,
1462
- "normalized": false,
1463
- "rstrip": false,
1464
- "single_word": false,
1465
- "special": true
1466
- },
1467
- "128183": {
1468
- "content": "<|reserved_special_token_175|>",
1469
- "lstrip": false,
1470
- "normalized": false,
1471
- "rstrip": false,
1472
- "single_word": false,
1473
- "special": true
1474
- },
1475
- "128184": {
1476
- "content": "<|reserved_special_token_176|>",
1477
- "lstrip": false,
1478
- "normalized": false,
1479
- "rstrip": false,
1480
- "single_word": false,
1481
- "special": true
1482
- },
1483
- "128185": {
1484
- "content": "<|reserved_special_token_177|>",
1485
- "lstrip": false,
1486
- "normalized": false,
1487
- "rstrip": false,
1488
- "single_word": false,
1489
- "special": true
1490
- },
1491
- "128186": {
1492
- "content": "<|reserved_special_token_178|>",
1493
- "lstrip": false,
1494
- "normalized": false,
1495
- "rstrip": false,
1496
- "single_word": false,
1497
- "special": true
1498
- },
1499
- "128187": {
1500
- "content": "<|reserved_special_token_179|>",
1501
- "lstrip": false,
1502
- "normalized": false,
1503
- "rstrip": false,
1504
- "single_word": false,
1505
- "special": true
1506
- },
1507
- "128188": {
1508
- "content": "<|reserved_special_token_180|>",
1509
- "lstrip": false,
1510
- "normalized": false,
1511
- "rstrip": false,
1512
- "single_word": false,
1513
- "special": true
1514
- },
1515
- "128189": {
1516
- "content": "<|reserved_special_token_181|>",
1517
- "lstrip": false,
1518
- "normalized": false,
1519
- "rstrip": false,
1520
- "single_word": false,
1521
- "special": true
1522
- },
1523
- "128190": {
1524
- "content": "<|reserved_special_token_182|>",
1525
- "lstrip": false,
1526
- "normalized": false,
1527
- "rstrip": false,
1528
- "single_word": false,
1529
- "special": true
1530
- },
1531
- "128191": {
1532
- "content": "<|reserved_special_token_183|>",
1533
- "lstrip": false,
1534
- "normalized": false,
1535
- "rstrip": false,
1536
- "single_word": false,
1537
- "special": true
1538
- },
1539
- "128192": {
1540
- "content": "<|reserved_special_token_184|>",
1541
- "lstrip": false,
1542
- "normalized": false,
1543
- "rstrip": false,
1544
- "single_word": false,
1545
- "special": true
1546
- },
1547
- "128193": {
1548
- "content": "<|reserved_special_token_185|>",
1549
- "lstrip": false,
1550
- "normalized": false,
1551
- "rstrip": false,
1552
- "single_word": false,
1553
- "special": true
1554
- },
1555
- "128194": {
1556
- "content": "<|reserved_special_token_186|>",
1557
- "lstrip": false,
1558
- "normalized": false,
1559
- "rstrip": false,
1560
- "single_word": false,
1561
- "special": true
1562
- },
1563
- "128195": {
1564
- "content": "<|reserved_special_token_187|>",
1565
- "lstrip": false,
1566
- "normalized": false,
1567
- "rstrip": false,
1568
- "single_word": false,
1569
- "special": true
1570
- },
1571
- "128196": {
1572
- "content": "<|reserved_special_token_188|>",
1573
- "lstrip": false,
1574
- "normalized": false,
1575
- "rstrip": false,
1576
- "single_word": false,
1577
- "special": true
1578
- },
1579
- "128197": {
1580
- "content": "<|reserved_special_token_189|>",
1581
- "lstrip": false,
1582
- "normalized": false,
1583
- "rstrip": false,
1584
- "single_word": false,
1585
- "special": true
1586
- },
1587
- "128198": {
1588
- "content": "<|reserved_special_token_190|>",
1589
- "lstrip": false,
1590
- "normalized": false,
1591
- "rstrip": false,
1592
- "single_word": false,
1593
- "special": true
1594
- },
1595
- "128199": {
1596
- "content": "<|reserved_special_token_191|>",
1597
- "lstrip": false,
1598
- "normalized": false,
1599
- "rstrip": false,
1600
- "single_word": false,
1601
- "special": true
1602
- },
1603
- "128200": {
1604
- "content": "<|reserved_special_token_192|>",
1605
- "lstrip": false,
1606
- "normalized": false,
1607
- "rstrip": false,
1608
- "single_word": false,
1609
- "special": true
1610
- },
1611
- "128201": {
1612
- "content": "<|reserved_special_token_193|>",
1613
- "lstrip": false,
1614
- "normalized": false,
1615
- "rstrip": false,
1616
- "single_word": false,
1617
- "special": true
1618
- },
1619
- "128202": {
1620
- "content": "<|reserved_special_token_194|>",
1621
- "lstrip": false,
1622
- "normalized": false,
1623
- "rstrip": false,
1624
- "single_word": false,
1625
- "special": true
1626
- },
1627
- "128203": {
1628
- "content": "<|reserved_special_token_195|>",
1629
- "lstrip": false,
1630
- "normalized": false,
1631
- "rstrip": false,
1632
- "single_word": false,
1633
- "special": true
1634
- },
1635
- "128204": {
1636
- "content": "<|reserved_special_token_196|>",
1637
- "lstrip": false,
1638
- "normalized": false,
1639
- "rstrip": false,
1640
- "single_word": false,
1641
- "special": true
1642
- },
1643
- "128205": {
1644
- "content": "<|reserved_special_token_197|>",
1645
- "lstrip": false,
1646
- "normalized": false,
1647
- "rstrip": false,
1648
- "single_word": false,
1649
- "special": true
1650
- },
1651
- "128206": {
1652
- "content": "<|reserved_special_token_198|>",
1653
- "lstrip": false,
1654
- "normalized": false,
1655
- "rstrip": false,
1656
- "single_word": false,
1657
- "special": true
1658
- },
1659
- "128207": {
1660
- "content": "<|reserved_special_token_199|>",
1661
- "lstrip": false,
1662
- "normalized": false,
1663
- "rstrip": false,
1664
- "single_word": false,
1665
- "special": true
1666
- },
1667
- "128208": {
1668
- "content": "<|reserved_special_token_200|>",
1669
- "lstrip": false,
1670
- "normalized": false,
1671
- "rstrip": false,
1672
- "single_word": false,
1673
- "special": true
1674
- },
1675
- "128209": {
1676
- "content": "<|reserved_special_token_201|>",
1677
- "lstrip": false,
1678
- "normalized": false,
1679
- "rstrip": false,
1680
- "single_word": false,
1681
- "special": true
1682
- },
1683
- "128210": {
1684
- "content": "<|reserved_special_token_202|>",
1685
- "lstrip": false,
1686
- "normalized": false,
1687
- "rstrip": false,
1688
- "single_word": false,
1689
- "special": true
1690
- },
1691
- "128211": {
1692
- "content": "<|reserved_special_token_203|>",
1693
- "lstrip": false,
1694
- "normalized": false,
1695
- "rstrip": false,
1696
- "single_word": false,
1697
- "special": true
1698
- },
1699
- "128212": {
1700
- "content": "<|reserved_special_token_204|>",
1701
- "lstrip": false,
1702
- "normalized": false,
1703
- "rstrip": false,
1704
- "single_word": false,
1705
- "special": true
1706
- },
1707
- "128213": {
1708
- "content": "<|reserved_special_token_205|>",
1709
- "lstrip": false,
1710
- "normalized": false,
1711
- "rstrip": false,
1712
- "single_word": false,
1713
- "special": true
1714
- },
1715
- "128214": {
1716
- "content": "<|reserved_special_token_206|>",
1717
- "lstrip": false,
1718
- "normalized": false,
1719
- "rstrip": false,
1720
- "single_word": false,
1721
- "special": true
1722
- },
1723
- "128215": {
1724
- "content": "<|reserved_special_token_207|>",
1725
- "lstrip": false,
1726
- "normalized": false,
1727
- "rstrip": false,
1728
- "single_word": false,
1729
- "special": true
1730
- },
1731
- "128216": {
1732
- "content": "<|reserved_special_token_208|>",
1733
- "lstrip": false,
1734
- "normalized": false,
1735
- "rstrip": false,
1736
- "single_word": false,
1737
- "special": true
1738
- },
1739
- "128217": {
1740
- "content": "<|reserved_special_token_209|>",
1741
- "lstrip": false,
1742
- "normalized": false,
1743
- "rstrip": false,
1744
- "single_word": false,
1745
- "special": true
1746
- },
1747
- "128218": {
1748
- "content": "<|reserved_special_token_210|>",
1749
- "lstrip": false,
1750
- "normalized": false,
1751
- "rstrip": false,
1752
- "single_word": false,
1753
- "special": true
1754
- },
1755
- "128219": {
1756
- "content": "<|reserved_special_token_211|>",
1757
- "lstrip": false,
1758
- "normalized": false,
1759
- "rstrip": false,
1760
- "single_word": false,
1761
- "special": true
1762
- },
1763
- "128220": {
1764
- "content": "<|reserved_special_token_212|>",
1765
- "lstrip": false,
1766
- "normalized": false,
1767
- "rstrip": false,
1768
- "single_word": false,
1769
- "special": true
1770
- },
1771
- "128221": {
1772
- "content": "<|reserved_special_token_213|>",
1773
- "lstrip": false,
1774
- "normalized": false,
1775
- "rstrip": false,
1776
- "single_word": false,
1777
- "special": true
1778
- },
1779
- "128222": {
1780
- "content": "<|reserved_special_token_214|>",
1781
- "lstrip": false,
1782
- "normalized": false,
1783
- "rstrip": false,
1784
- "single_word": false,
1785
- "special": true
1786
- },
1787
- "128223": {
1788
- "content": "<|reserved_special_token_215|>",
1789
- "lstrip": false,
1790
- "normalized": false,
1791
- "rstrip": false,
1792
- "single_word": false,
1793
- "special": true
1794
- },
1795
- "128224": {
1796
- "content": "<|reserved_special_token_216|>",
1797
- "lstrip": false,
1798
- "normalized": false,
1799
- "rstrip": false,
1800
- "single_word": false,
1801
- "special": true
1802
- },
1803
- "128225": {
1804
- "content": "<|reserved_special_token_217|>",
1805
- "lstrip": false,
1806
- "normalized": false,
1807
- "rstrip": false,
1808
- "single_word": false,
1809
- "special": true
1810
- },
1811
- "128226": {
1812
- "content": "<|reserved_special_token_218|>",
1813
- "lstrip": false,
1814
- "normalized": false,
1815
- "rstrip": false,
1816
- "single_word": false,
1817
- "special": true
1818
- },
1819
- "128227": {
1820
- "content": "<|reserved_special_token_219|>",
1821
- "lstrip": false,
1822
- "normalized": false,
1823
- "rstrip": false,
1824
- "single_word": false,
1825
- "special": true
1826
- },
1827
- "128228": {
1828
- "content": "<|reserved_special_token_220|>",
1829
- "lstrip": false,
1830
- "normalized": false,
1831
- "rstrip": false,
1832
- "single_word": false,
1833
- "special": true
1834
- },
1835
- "128229": {
1836
- "content": "<|reserved_special_token_221|>",
1837
- "lstrip": false,
1838
- "normalized": false,
1839
- "rstrip": false,
1840
- "single_word": false,
1841
- "special": true
1842
- },
1843
- "128230": {
1844
- "content": "<|reserved_special_token_222|>",
1845
- "lstrip": false,
1846
- "normalized": false,
1847
- "rstrip": false,
1848
- "single_word": false,
1849
- "special": true
1850
- },
1851
- "128231": {
1852
- "content": "<|reserved_special_token_223|>",
1853
- "lstrip": false,
1854
- "normalized": false,
1855
- "rstrip": false,
1856
- "single_word": false,
1857
- "special": true
1858
- },
1859
- "128232": {
1860
- "content": "<|reserved_special_token_224|>",
1861
- "lstrip": false,
1862
- "normalized": false,
1863
- "rstrip": false,
1864
- "single_word": false,
1865
- "special": true
1866
- },
1867
- "128233": {
1868
- "content": "<|reserved_special_token_225|>",
1869
- "lstrip": false,
1870
- "normalized": false,
1871
- "rstrip": false,
1872
- "single_word": false,
1873
- "special": true
1874
- },
1875
- "128234": {
1876
- "content": "<|reserved_special_token_226|>",
1877
- "lstrip": false,
1878
- "normalized": false,
1879
- "rstrip": false,
1880
- "single_word": false,
1881
- "special": true
1882
- },
1883
- "128235": {
1884
- "content": "<|reserved_special_token_227|>",
1885
- "lstrip": false,
1886
- "normalized": false,
1887
- "rstrip": false,
1888
- "single_word": false,
1889
- "special": true
1890
- },
1891
- "128236": {
1892
- "content": "<|reserved_special_token_228|>",
1893
- "lstrip": false,
1894
- "normalized": false,
1895
- "rstrip": false,
1896
- "single_word": false,
1897
- "special": true
1898
- },
1899
- "128237": {
1900
- "content": "<|reserved_special_token_229|>",
1901
- "lstrip": false,
1902
- "normalized": false,
1903
- "rstrip": false,
1904
- "single_word": false,
1905
- "special": true
1906
- },
1907
- "128238": {
1908
- "content": "<|reserved_special_token_230|>",
1909
- "lstrip": false,
1910
- "normalized": false,
1911
- "rstrip": false,
1912
- "single_word": false,
1913
- "special": true
1914
- },
1915
- "128239": {
1916
- "content": "<|reserved_special_token_231|>",
1917
- "lstrip": false,
1918
- "normalized": false,
1919
- "rstrip": false,
1920
- "single_word": false,
1921
- "special": true
1922
- },
1923
- "128240": {
1924
- "content": "<|reserved_special_token_232|>",
1925
- "lstrip": false,
1926
- "normalized": false,
1927
- "rstrip": false,
1928
- "single_word": false,
1929
- "special": true
1930
- },
1931
- "128241": {
1932
- "content": "<|reserved_special_token_233|>",
1933
- "lstrip": false,
1934
- "normalized": false,
1935
- "rstrip": false,
1936
- "single_word": false,
1937
- "special": true
1938
- },
1939
- "128242": {
1940
- "content": "<|reserved_special_token_234|>",
1941
- "lstrip": false,
1942
- "normalized": false,
1943
- "rstrip": false,
1944
- "single_word": false,
1945
- "special": true
1946
- },
1947
- "128243": {
1948
- "content": "<|reserved_special_token_235|>",
1949
- "lstrip": false,
1950
- "normalized": false,
1951
- "rstrip": false,
1952
- "single_word": false,
1953
- "special": true
1954
- },
1955
- "128244": {
1956
- "content": "<|reserved_special_token_236|>",
1957
- "lstrip": false,
1958
- "normalized": false,
1959
- "rstrip": false,
1960
- "single_word": false,
1961
- "special": true
1962
- },
1963
- "128245": {
1964
- "content": "<|reserved_special_token_237|>",
1965
- "lstrip": false,
1966
- "normalized": false,
1967
- "rstrip": false,
1968
- "single_word": false,
1969
- "special": true
1970
- },
1971
- "128246": {
1972
- "content": "<|reserved_special_token_238|>",
1973
- "lstrip": false,
1974
- "normalized": false,
1975
- "rstrip": false,
1976
- "single_word": false,
1977
- "special": true
1978
- },
1979
- "128247": {
1980
- "content": "<|reserved_special_token_239|>",
1981
- "lstrip": false,
1982
- "normalized": false,
1983
- "rstrip": false,
1984
- "single_word": false,
1985
- "special": true
1986
- },
1987
- "128248": {
1988
- "content": "<|reserved_special_token_240|>",
1989
- "lstrip": false,
1990
- "normalized": false,
1991
- "rstrip": false,
1992
- "single_word": false,
1993
- "special": true
1994
- },
1995
- "128249": {
1996
- "content": "<|reserved_special_token_241|>",
1997
- "lstrip": false,
1998
- "normalized": false,
1999
- "rstrip": false,
2000
- "single_word": false,
2001
- "special": true
2002
- },
2003
- "128250": {
2004
- "content": "<|reserved_special_token_242|>",
2005
- "lstrip": false,
2006
- "normalized": false,
2007
- "rstrip": false,
2008
- "single_word": false,
2009
- "special": true
2010
- },
2011
- "128251": {
2012
- "content": "<|reserved_special_token_243|>",
2013
- "lstrip": false,
2014
- "normalized": false,
2015
- "rstrip": false,
2016
- "single_word": false,
2017
- "special": true
2018
- },
2019
- "128252": {
2020
- "content": "<|reserved_special_token_244|>",
2021
- "lstrip": false,
2022
- "normalized": false,
2023
- "rstrip": false,
2024
- "single_word": false,
2025
- "special": true
2026
- },
2027
- "128253": {
2028
- "content": "<|reserved_special_token_245|>",
2029
- "lstrip": false,
2030
- "normalized": false,
2031
- "rstrip": false,
2032
- "single_word": false,
2033
- "special": true
2034
- },
2035
- "128254": {
2036
- "content": "<|reserved_special_token_246|>",
2037
- "lstrip": false,
2038
- "normalized": false,
2039
- "rstrip": false,
2040
- "single_word": false,
2041
- "special": true
2042
- },
2043
- "128255": {
2044
- "content": "<|reserved_special_token_247|>",
2045
- "lstrip": false,
2046
- "normalized": false,
2047
- "rstrip": false,
2048
- "single_word": false,
2049
- "special": true
2050
- }
2051
- },
2052
- "bos_token": "<|begin_of_text|>",
2053
- "clean_up_tokenization_spaces": true,
2054
- "eos_token": "<|eot_id|>",
2055
- "extra_special_tokens": {},
2056
- "model_input_names": [
2057
- "input_ids",
2058
- "attention_mask"
2059
- ],
2060
- "model_max_length": 131072,
2061
- "pad_token": "<|eot_id|>",
2062
- "tokenizer_class": "PreTrainedTokenizerFast"
2063
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw6.00_5-6-7-8bit/README.md DELETED
@@ -1,16 +0,0 @@
1
- # Quantized Model Checkpoint
2
-
3
- **Base model:** meta-llama/Llama-3.1-8B-Instruct
4
-
5
- **Average bitwidth:** 6.0048
6
-
7
- **Sensitivity method:** linear
8
-
9
- **Constraints:**
10
- - max_kl: 0.01
11
-
12
- **Metrics:**
13
- - predicted_kl: 0.009996
14
- - predicted_eap: 0.610965
15
-
16
- See `quantization_config.txt` for full configuration details.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw6.00_5-6-7-8bit/chat_template.jinja DELETED
@@ -1,109 +0,0 @@
1
- {{- bos_token }}
2
- {%- if custom_tools is defined %}
3
- {%- set tools = custom_tools %}
4
- {%- endif %}
5
- {%- if not tools_in_user_message is defined %}
6
- {%- set tools_in_user_message = true %}
7
- {%- endif %}
8
- {%- if not date_string is defined %}
9
- {%- set date_string = "26 Jul 2024" %}
10
- {%- endif %}
11
- {%- if not tools is defined %}
12
- {%- set tools = none %}
13
- {%- endif %}
14
-
15
- {#- This block extracts the system message, so we can slot it into the right place. #}
16
- {%- if messages[0]['role'] == 'system' %}
17
- {%- set system_message = messages[0]['content']|trim %}
18
- {%- set messages = messages[1:] %}
19
- {%- else %}
20
- {%- set system_message = "" %}
21
- {%- endif %}
22
-
23
- {#- System message + builtin tools #}
24
- {{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
25
- {%- if builtin_tools is defined or tools is not none %}
26
- {{- "Environment: ipython\n" }}
27
- {%- endif %}
28
- {%- if builtin_tools is defined %}
29
- {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
30
- {%- endif %}
31
- {{- "Cutting Knowledge Date: December 2023\n" }}
32
- {{- "Today Date: " + date_string + "\n\n" }}
33
- {%- if tools is not none and not tools_in_user_message %}
34
- {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
35
- {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
36
- {{- "Do not use variables.\n\n" }}
37
- {%- for t in tools %}
38
- {{- t | tojson(indent=4) }}
39
- {{- "\n\n" }}
40
- {%- endfor %}
41
- {%- endif %}
42
- {{- system_message }}
43
- {{- "<|eot_id|>" }}
44
-
45
- {#- Custom tools are passed in a user message with some extra guidance #}
46
- {%- if tools_in_user_message and not tools is none %}
47
- {#- Extract the first user message so we can plug it in here #}
48
- {%- if messages | length != 0 %}
49
- {%- set first_user_message = messages[0]['content']|trim %}
50
- {%- set messages = messages[1:] %}
51
- {%- else %}
52
- {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
53
- {%- endif %}
54
- {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
55
- {{- "Given the following functions, please respond with a JSON for a function call " }}
56
- {{- "with its proper arguments that best answers the given prompt.\n\n" }}
57
- {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
58
- {{- "Do not use variables.\n\n" }}
59
- {%- for t in tools %}
60
- {{- t | tojson(indent=4) }}
61
- {{- "\n\n" }}
62
- {%- endfor %}
63
- {{- first_user_message + "<|eot_id|>"}}
64
- {%- endif %}
65
-
66
- {%- for message in messages %}
67
- {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
68
- {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
69
- {%- elif 'tool_calls' in message %}
70
- {%- if not message.tool_calls|length == 1 %}
71
- {{- raise_exception("This model only supports single tool-calls at once!") }}
72
- {%- endif %}
73
- {%- set tool_call = message.tool_calls[0].function %}
74
- {%- if builtin_tools is defined and tool_call.name in builtin_tools %}
75
- {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
76
- {{- "<|python_tag|>" + tool_call.name + ".call(" }}
77
- {%- for arg_name, arg_val in tool_call.arguments | items %}
78
- {{- arg_name + '="' + arg_val + '"' }}
79
- {%- if not loop.last %}
80
- {{- ", " }}
81
- {%- endif %}
82
- {%- endfor %}
83
- {{- ")" }}
84
- {%- else %}
85
- {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
86
- {{- '{"name": "' + tool_call.name + '", ' }}
87
- {{- '"parameters": ' }}
88
- {{- tool_call.arguments | tojson }}
89
- {{- "}" }}
90
- {%- endif %}
91
- {%- if builtin_tools is defined %}
92
- {#- This means we're in ipython mode #}
93
- {{- "<|eom_id|>" }}
94
- {%- else %}
95
- {{- "<|eot_id|>" }}
96
- {%- endif %}
97
- {%- elif message.role == "tool" or message.role == "ipython" %}
98
- {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
99
- {%- if message.content is mapping or message.content is iterable %}
100
- {{- message.content | tojson }}
101
- {%- else %}
102
- {{- message.content }}
103
- {%- endif %}
104
- {{- "<|eot_id|>" }}
105
- {%- endif %}
106
- {%- endfor %}
107
- {%- if add_generation_prompt %}
108
- {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
109
- {%- endif %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw6.00_5-6-7-8bit/config.json DELETED
@@ -1,39 +0,0 @@
1
- {
2
- "architectures": [
3
- "LlamaForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 128000,
8
- "dtype": "float16",
9
- "eos_token_id": [
10
- 128001,
11
- 128008,
12
- 128009
13
- ],
14
- "head_dim": 128,
15
- "hidden_act": "silu",
16
- "hidden_size": 4096,
17
- "initializer_range": 0.02,
18
- "intermediate_size": 14336,
19
- "max_position_embeddings": 131072,
20
- "mlp_bias": false,
21
- "model_type": "llama",
22
- "num_attention_heads": 32,
23
- "num_hidden_layers": 32,
24
- "num_key_value_heads": 8,
25
- "pretraining_tp": 1,
26
- "rms_norm_eps": 1e-05,
27
- "rope_scaling": {
28
- "factor": 8.0,
29
- "high_freq_factor": 4.0,
30
- "low_freq_factor": 1.0,
31
- "original_max_position_embeddings": 8192,
32
- "rope_type": "llama3"
33
- },
34
- "rope_theta": 500000.0,
35
- "tie_word_embeddings": false,
36
- "transformers_version": "4.57.3",
37
- "use_cache": false,
38
- "vocab_size": 128256
39
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw6.00_5-6-7-8bit/generation_config.json DELETED
@@ -1,12 +0,0 @@
1
- {
2
- "bos_token_id": 128000,
3
- "do_sample": true,
4
- "eos_token_id": [
5
- 128001,
6
- 128008,
7
- 128009
8
- ],
9
- "temperature": 0.6,
10
- "top_p": 0.9,
11
- "transformers_version": "4.57.3"
12
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw6.00_5-6-7-8bit/model-00001-of-00004.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3985a3e4bcb7e75b508abfc96ecc9115048de1eb13af2279677ffd6668e624da
3
- size 4976698592
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw6.00_5-6-7-8bit/model-00002-of-00004.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:daeb897ec2af846c6773c09df9b8620424cb10617f1b7a6df335c61b85b97be1
3
- size 4999802616
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw6.00_5-6-7-8bit/model-00003-of-00004.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff8bc5257342fd73a5926861e1964b59e0953d898180078409bb3dd1ac53ba61
3
- size 4915916080
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw6.00_5-6-7-8bit/model-00004-of-00004.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:41b6804c14c14e5bc8c6d95f57bc69272bacb1000108ec3d76ccdf601f1b08f8
3
- size 1168138808
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw6.00_5-6-7-8bit/model.safetensors.index.json DELETED
@@ -1,299 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_parameters": 8030261248,
4
- "total_size": 16060522496
5
- },
6
- "weight_map": {
7
- "lm_head.weight": "model-00004-of-00004.safetensors",
8
- "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
- "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
17
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
18
- "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
19
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
20
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
21
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
22
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
23
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
24
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
25
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
26
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
27
- "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
28
- "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
29
- "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
30
- "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
31
- "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
32
- "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
33
- "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
34
- "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
35
- "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
36
- "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
37
- "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
38
- "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
39
- "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
40
- "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
41
- "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
42
- "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
43
- "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
44
- "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
45
- "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
46
- "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
47
- "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
48
- "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
49
- "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
50
- "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
- "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
- "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
53
- "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
54
- "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
55
- "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
56
- "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
57
- "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
58
- "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
59
- "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
60
- "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
61
- "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
62
- "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
63
- "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
64
- "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
65
- "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
66
- "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
67
- "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
68
- "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
69
- "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
70
- "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
71
- "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
72
- "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
73
- "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
74
- "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
75
- "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
76
- "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
77
- "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
78
- "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
79
- "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
80
- "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
81
- "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
82
- "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
83
- "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
84
- "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
85
- "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
86
- "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
- "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
- "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
89
- "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
90
- "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
91
- "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
92
- "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
93
- "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
94
- "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
95
- "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
96
- "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
97
- "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
98
- "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
99
- "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
100
- "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
101
- "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
102
- "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
103
- "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
104
- "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
105
- "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
106
- "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
107
- "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
108
- "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
109
- "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
110
- "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
111
- "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
112
- "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
113
- "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
114
- "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
115
- "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
116
- "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
117
- "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
118
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
119
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
120
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
121
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
122
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
123
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
124
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
125
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
126
- "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
127
- "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
128
- "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
129
- "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
130
- "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
131
- "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
132
- "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
133
- "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
134
- "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
135
- "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
136
- "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
137
- "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
138
- "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
139
- "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
140
- "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
141
- "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
142
- "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
143
- "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
144
- "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
145
- "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
146
- "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
147
- "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
148
- "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
149
- "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
150
- "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
151
- "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
152
- "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
153
- "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
154
- "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
155
- "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
156
- "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
157
- "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
158
- "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
159
- "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
160
- "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
161
- "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
162
- "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
163
- "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
164
- "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
165
- "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
166
- "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
167
- "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
168
- "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
169
- "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
170
- "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
171
- "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
172
- "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
173
- "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
174
- "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
175
- "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
176
- "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
177
- "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
178
- "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
179
- "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
180
- "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
181
- "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
182
- "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
183
- "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
184
- "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
185
- "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
186
- "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
187
- "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
188
- "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
189
- "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
190
- "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
191
- "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
192
- "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
193
- "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
194
- "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
- "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
- "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
197
- "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
198
- "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
199
- "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
200
- "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
201
- "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
202
- "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
203
- "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
204
- "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
205
- "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
206
- "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
207
- "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
208
- "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
209
- "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
210
- "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
211
- "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
212
- "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
213
- "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
214
- "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
215
- "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
216
- "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
217
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
218
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
219
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
220
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
221
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
222
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
223
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
224
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
225
- "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
226
- "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
227
- "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
228
- "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
229
- "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
230
- "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
- "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
- "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
233
- "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
234
- "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
235
- "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
236
- "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
237
- "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
238
- "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
239
- "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
240
- "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
241
- "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
242
- "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
243
- "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
244
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
245
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
246
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
247
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
248
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
249
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
250
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
251
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
252
- "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
253
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
254
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
255
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
256
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
257
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
258
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
259
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
260
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
261
- "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
262
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
263
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
264
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
265
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
266
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
269
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
270
- "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
271
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
272
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
273
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
274
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
275
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
276
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
277
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
278
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
279
- "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
280
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
281
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
282
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
283
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
284
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
285
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
286
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
287
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
288
- "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
289
- "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
290
- "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
291
- "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
292
- "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
293
- "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
294
- "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
295
- "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
296
- "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
297
- "model.norm.weight": "model-00004-of-00004.safetensors"
298
- }
299
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw6.00_5-6-7-8bit/quantization_config.txt DELETED
@@ -1,251 +0,0 @@
1
- # Model: meta-llama/Llama-3.1-8B-Instruct
2
- # Layer directory: /nfs/scistore19/alistgrp/mhelcig/local/data/search/4_5_6_7_8bit_asym_g128/Llama-3.1-8B-Instruct/6bit/
3
- # Sensitivity method: linear
4
- # Estimation method: linear
5
- # Available bitwidths: [4, 5, 6, 7, 8]
6
- # Bitwidth map: {4: 4.3125, 5: 5.3125, 6: 6.3125, 7: 7.3125, 8: 8.3125}
7
- #
8
- # Mode: predicted_constraint_search
9
- # Constraint max_kl: 0.01
10
- # Weights: nll=0.0, kl=0.0, eap=1.0
11
- #
12
- # Average bitwidth: 6.0048
13
- # Total params: 6979321856
14
- # Total bits: 41909485568
15
- # Predicted KL: 0.009996
16
- # Predicted EAP: 0.610965
17
- # Predicted ETL: 0.389035
18
- # Satisfies constraints: True
19
- # Solver calls: 1
20
- # Evaluations: 0
21
- #
22
- # Bitwidth distribution:
23
- # 8-bit: 26 layers (11.6%)
24
- # 7-bit: 55 layers (24.6%)
25
- # 6-bit: 84 layers (37.5%)
26
- # 5-bit: 59 layers (26.3%)
27
- #
28
- model.layers.0.self_attn.q_proj: 8
29
- model.layers.0.self_attn.k_proj: 8
30
- model.layers.0.self_attn.v_proj: 8
31
- model.layers.0.self_attn.o_proj: 6
32
- model.layers.0.mlp.gate_proj: 5
33
- model.layers.0.mlp.up_proj: 5
34
- model.layers.0.mlp.down_proj: 6
35
- model.layers.1.self_attn.q_proj: 7
36
- model.layers.1.self_attn.k_proj: 8
37
- model.layers.1.self_attn.v_proj: 8
38
- model.layers.1.self_attn.o_proj: 6
39
- model.layers.1.mlp.gate_proj: 5
40
- model.layers.1.mlp.up_proj: 5
41
- model.layers.1.mlp.down_proj: 8
42
- model.layers.2.self_attn.q_proj: 7
43
- model.layers.2.self_attn.k_proj: 8
44
- model.layers.2.self_attn.v_proj: 8
45
- model.layers.2.self_attn.o_proj: 6
46
- model.layers.2.mlp.gate_proj: 6
47
- model.layers.2.mlp.up_proj: 6
48
- model.layers.2.mlp.down_proj: 5
49
- model.layers.3.self_attn.q_proj: 7
50
- model.layers.3.self_attn.k_proj: 8
51
- model.layers.3.self_attn.v_proj: 8
52
- model.layers.3.self_attn.o_proj: 6
53
- model.layers.3.mlp.gate_proj: 6
54
- model.layers.3.mlp.up_proj: 6
55
- model.layers.3.mlp.down_proj: 5
56
- model.layers.4.self_attn.q_proj: 7
57
- model.layers.4.self_attn.k_proj: 8
58
- model.layers.4.self_attn.v_proj: 8
59
- model.layers.4.self_attn.o_proj: 6
60
- model.layers.4.mlp.gate_proj: 6
61
- model.layers.4.mlp.up_proj: 6
62
- model.layers.4.mlp.down_proj: 5
63
- model.layers.5.self_attn.q_proj: 6
64
- model.layers.5.self_attn.k_proj: 7
65
- model.layers.5.self_attn.v_proj: 7
66
- model.layers.5.self_attn.o_proj: 6
67
- model.layers.5.mlp.gate_proj: 6
68
- model.layers.5.mlp.up_proj: 6
69
- model.layers.5.mlp.down_proj: 5
70
- model.layers.6.self_attn.q_proj: 6
71
- model.layers.6.self_attn.k_proj: 7
72
- model.layers.6.self_attn.v_proj: 7
73
- model.layers.6.self_attn.o_proj: 6
74
- model.layers.6.mlp.gate_proj: 6
75
- model.layers.6.mlp.up_proj: 6
76
- model.layers.6.mlp.down_proj: 5
77
- model.layers.7.self_attn.q_proj: 6
78
- model.layers.7.self_attn.k_proj: 7
79
- model.layers.7.self_attn.v_proj: 7
80
- model.layers.7.self_attn.o_proj: 6
81
- model.layers.7.mlp.gate_proj: 6
82
- model.layers.7.mlp.up_proj: 6
83
- model.layers.7.mlp.down_proj: 5
84
- model.layers.8.self_attn.q_proj: 6
85
- model.layers.8.self_attn.k_proj: 7
86
- model.layers.8.self_attn.v_proj: 7
87
- model.layers.8.self_attn.o_proj: 6
88
- model.layers.8.mlp.gate_proj: 6
89
- model.layers.8.mlp.up_proj: 5
90
- model.layers.8.mlp.down_proj: 5
91
- model.layers.9.self_attn.q_proj: 7
92
- model.layers.9.self_attn.k_proj: 8
93
- model.layers.9.self_attn.v_proj: 8
94
- model.layers.9.self_attn.o_proj: 6
95
- model.layers.9.mlp.gate_proj: 6
96
- model.layers.9.mlp.up_proj: 5
97
- model.layers.9.mlp.down_proj: 5
98
- model.layers.10.self_attn.q_proj: 6
99
- model.layers.10.self_attn.k_proj: 8
100
- model.layers.10.self_attn.v_proj: 7
101
- model.layers.10.self_attn.o_proj: 6
102
- model.layers.10.mlp.gate_proj: 5
103
- model.layers.10.mlp.up_proj: 5
104
- model.layers.10.mlp.down_proj: 5
105
- model.layers.11.self_attn.q_proj: 7
106
- model.layers.11.self_attn.k_proj: 8
107
- model.layers.11.self_attn.v_proj: 7
108
- model.layers.11.self_attn.o_proj: 6
109
- model.layers.11.mlp.gate_proj: 5
110
- model.layers.11.mlp.up_proj: 5
111
- model.layers.11.mlp.down_proj: 5
112
- model.layers.12.self_attn.q_proj: 7
113
- model.layers.12.self_attn.k_proj: 7
114
- model.layers.12.self_attn.v_proj: 7
115
- model.layers.12.self_attn.o_proj: 6
116
- model.layers.12.mlp.gate_proj: 6
117
- model.layers.12.mlp.up_proj: 6
118
- model.layers.12.mlp.down_proj: 5
119
- model.layers.13.self_attn.q_proj: 7
120
- model.layers.13.self_attn.k_proj: 8
121
- model.layers.13.self_attn.v_proj: 8
122
- model.layers.13.self_attn.o_proj: 6
123
- model.layers.13.mlp.gate_proj: 6
124
- model.layers.13.mlp.up_proj: 6
125
- model.layers.13.mlp.down_proj: 5
126
- model.layers.14.self_attn.q_proj: 7
127
- model.layers.14.self_attn.k_proj: 8
128
- model.layers.14.self_attn.v_proj: 8
129
- model.layers.14.self_attn.o_proj: 6
130
- model.layers.14.mlp.gate_proj: 6
131
- model.layers.14.mlp.up_proj: 6
132
- model.layers.14.mlp.down_proj: 5
133
- model.layers.15.self_attn.q_proj: 7
134
- model.layers.15.self_attn.k_proj: 8
135
- model.layers.15.self_attn.v_proj: 8
136
- model.layers.15.self_attn.o_proj: 6
137
- model.layers.15.mlp.gate_proj: 6
138
- model.layers.15.mlp.up_proj: 6
139
- model.layers.15.mlp.down_proj: 5
140
- model.layers.16.self_attn.q_proj: 7
141
- model.layers.16.self_attn.k_proj: 8
142
- model.layers.16.self_attn.v_proj: 8
143
- model.layers.16.self_attn.o_proj: 6
144
- model.layers.16.mlp.gate_proj: 6
145
- model.layers.16.mlp.up_proj: 6
146
- model.layers.16.mlp.down_proj: 5
147
- model.layers.17.self_attn.q_proj: 6
148
- model.layers.17.self_attn.k_proj: 7
149
- model.layers.17.self_attn.v_proj: 7
150
- model.layers.17.self_attn.o_proj: 6
151
- model.layers.17.mlp.gate_proj: 6
152
- model.layers.17.mlp.up_proj: 6
153
- model.layers.17.mlp.down_proj: 6
154
- model.layers.18.self_attn.q_proj: 6
155
- model.layers.18.self_attn.k_proj: 7
156
- model.layers.18.self_attn.v_proj: 7
157
- model.layers.18.self_attn.o_proj: 6
158
- model.layers.18.mlp.gate_proj: 6
159
- model.layers.18.mlp.up_proj: 6
160
- model.layers.18.mlp.down_proj: 5
161
- model.layers.19.self_attn.q_proj: 6
162
- model.layers.19.self_attn.k_proj: 7
163
- model.layers.19.self_attn.v_proj: 7
164
- model.layers.19.self_attn.o_proj: 6
165
- model.layers.19.mlp.gate_proj: 6
166
- model.layers.19.mlp.up_proj: 6
167
- model.layers.19.mlp.down_proj: 5
168
- model.layers.20.self_attn.q_proj: 6
169
- model.layers.20.self_attn.k_proj: 7
170
- model.layers.20.self_attn.v_proj: 7
171
- model.layers.20.self_attn.o_proj: 5
172
- model.layers.20.mlp.gate_proj: 6
173
- model.layers.20.mlp.up_proj: 6
174
- model.layers.20.mlp.down_proj: 5
175
- model.layers.21.self_attn.q_proj: 6
176
- model.layers.21.self_attn.k_proj: 7
177
- model.layers.21.self_attn.v_proj: 7
178
- model.layers.21.self_attn.o_proj: 6
179
- model.layers.21.mlp.gate_proj: 6
180
- model.layers.21.mlp.up_proj: 6
181
- model.layers.21.mlp.down_proj: 5
182
- model.layers.22.self_attn.q_proj: 6
183
- model.layers.22.self_attn.k_proj: 7
184
- model.layers.22.self_attn.v_proj: 7
185
- model.layers.22.self_attn.o_proj: 5
186
- model.layers.22.mlp.gate_proj: 6
187
- model.layers.22.mlp.up_proj: 6
188
- model.layers.22.mlp.down_proj: 5
189
- model.layers.23.self_attn.q_proj: 6
190
- model.layers.23.self_attn.k_proj: 7
191
- model.layers.23.self_attn.v_proj: 7
192
- model.layers.23.self_attn.o_proj: 5
193
- model.layers.23.mlp.gate_proj: 6
194
- model.layers.23.mlp.up_proj: 6
195
- model.layers.23.mlp.down_proj: 5
196
- model.layers.24.self_attn.q_proj: 6
197
- model.layers.24.self_attn.k_proj: 7
198
- model.layers.24.self_attn.v_proj: 7
199
- model.layers.24.self_attn.o_proj: 5
200
- model.layers.24.mlp.gate_proj: 5
201
- model.layers.24.mlp.up_proj: 5
202
- model.layers.24.mlp.down_proj: 5
203
- model.layers.25.self_attn.q_proj: 6
204
- model.layers.25.self_attn.k_proj: 7
205
- model.layers.25.self_attn.v_proj: 7
206
- model.layers.25.self_attn.o_proj: 5
207
- model.layers.25.mlp.gate_proj: 5
208
- model.layers.25.mlp.up_proj: 5
209
- model.layers.25.mlp.down_proj: 5
210
- model.layers.26.self_attn.q_proj: 6
211
- model.layers.26.self_attn.k_proj: 7
212
- model.layers.26.self_attn.v_proj: 7
213
- model.layers.26.self_attn.o_proj: 5
214
- model.layers.26.mlp.gate_proj: 5
215
- model.layers.26.mlp.up_proj: 5
216
- model.layers.26.mlp.down_proj: 5
217
- model.layers.27.self_attn.q_proj: 6
218
- model.layers.27.self_attn.k_proj: 7
219
- model.layers.27.self_attn.v_proj: 7
220
- model.layers.27.self_attn.o_proj: 5
221
- model.layers.27.mlp.gate_proj: 5
222
- model.layers.27.mlp.up_proj: 5
223
- model.layers.27.mlp.down_proj: 5
224
- model.layers.28.self_attn.q_proj: 6
225
- model.layers.28.self_attn.k_proj: 7
226
- model.layers.28.self_attn.v_proj: 7
227
- model.layers.28.self_attn.o_proj: 5
228
- model.layers.28.mlp.gate_proj: 5
229
- model.layers.28.mlp.up_proj: 5
230
- model.layers.28.mlp.down_proj: 5
231
- model.layers.29.self_attn.q_proj: 7
232
- model.layers.29.self_attn.k_proj: 8
233
- model.layers.29.self_attn.v_proj: 8
234
- model.layers.29.self_attn.o_proj: 5
235
- model.layers.29.mlp.gate_proj: 5
236
- model.layers.29.mlp.up_proj: 5
237
- model.layers.29.mlp.down_proj: 5
238
- model.layers.30.self_attn.q_proj: 6
239
- model.layers.30.self_attn.k_proj: 7
240
- model.layers.30.self_attn.v_proj: 7
241
- model.layers.30.self_attn.o_proj: 5
242
- model.layers.30.mlp.gate_proj: 6
243
- model.layers.30.mlp.up_proj: 6
244
- model.layers.30.mlp.down_proj: 6
245
- model.layers.31.self_attn.q_proj: 6
246
- model.layers.31.self_attn.k_proj: 7
247
- model.layers.31.self_attn.v_proj: 7
248
- model.layers.31.self_attn.o_proj: 6
249
- model.layers.31.mlp.gate_proj: 7
250
- model.layers.31.mlp.up_proj: 7
251
- model.layers.31.mlp.down_proj: 7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw6.00_5-6-7-8bit/special_tokens_map.json DELETED
@@ -1,17 +0,0 @@
1
- {
2
- "bos_token": {
3
- "content": "<|begin_of_text|>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "<|eot_id|>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": "<|eot_id|>"
17
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw6.00_5-6-7-8bit/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
- size 17209920
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw6.00_5-6-7-8bit/tokenizer_config.json DELETED
@@ -1,2063 +0,0 @@
1
- {
2
- "added_tokens_decoder": {
3
- "128000": {
4
- "content": "<|begin_of_text|>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "128001": {
12
- "content": "<|end_of_text|>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "128002": {
20
- "content": "<|reserved_special_token_0|>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "128003": {
28
- "content": "<|reserved_special_token_1|>",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "128004": {
36
- "content": "<|finetune_right_pad_id|>",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- },
43
- "128005": {
44
- "content": "<|reserved_special_token_2|>",
45
- "lstrip": false,
46
- "normalized": false,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": true
50
- },
51
- "128006": {
52
- "content": "<|start_header_id|>",
53
- "lstrip": false,
54
- "normalized": false,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": true
58
- },
59
- "128007": {
60
- "content": "<|end_header_id|>",
61
- "lstrip": false,
62
- "normalized": false,
63
- "rstrip": false,
64
- "single_word": false,
65
- "special": true
66
- },
67
- "128008": {
68
- "content": "<|eom_id|>",
69
- "lstrip": false,
70
- "normalized": false,
71
- "rstrip": false,
72
- "single_word": false,
73
- "special": true
74
- },
75
- "128009": {
76
- "content": "<|eot_id|>",
77
- "lstrip": false,
78
- "normalized": false,
79
- "rstrip": false,
80
- "single_word": false,
81
- "special": true
82
- },
83
- "128010": {
84
- "content": "<|python_tag|>",
85
- "lstrip": false,
86
- "normalized": false,
87
- "rstrip": false,
88
- "single_word": false,
89
- "special": true
90
- },
91
- "128011": {
92
- "content": "<|reserved_special_token_3|>",
93
- "lstrip": false,
94
- "normalized": false,
95
- "rstrip": false,
96
- "single_word": false,
97
- "special": true
98
- },
99
- "128012": {
100
- "content": "<|reserved_special_token_4|>",
101
- "lstrip": false,
102
- "normalized": false,
103
- "rstrip": false,
104
- "single_word": false,
105
- "special": true
106
- },
107
- "128013": {
108
- "content": "<|reserved_special_token_5|>",
109
- "lstrip": false,
110
- "normalized": false,
111
- "rstrip": false,
112
- "single_word": false,
113
- "special": true
114
- },
115
- "128014": {
116
- "content": "<|reserved_special_token_6|>",
117
- "lstrip": false,
118
- "normalized": false,
119
- "rstrip": false,
120
- "single_word": false,
121
- "special": true
122
- },
123
- "128015": {
124
- "content": "<|reserved_special_token_7|>",
125
- "lstrip": false,
126
- "normalized": false,
127
- "rstrip": false,
128
- "single_word": false,
129
- "special": true
130
- },
131
- "128016": {
132
- "content": "<|reserved_special_token_8|>",
133
- "lstrip": false,
134
- "normalized": false,
135
- "rstrip": false,
136
- "single_word": false,
137
- "special": true
138
- },
139
- "128017": {
140
- "content": "<|reserved_special_token_9|>",
141
- "lstrip": false,
142
- "normalized": false,
143
- "rstrip": false,
144
- "single_word": false,
145
- "special": true
146
- },
147
- "128018": {
148
- "content": "<|reserved_special_token_10|>",
149
- "lstrip": false,
150
- "normalized": false,
151
- "rstrip": false,
152
- "single_word": false,
153
- "special": true
154
- },
155
- "128019": {
156
- "content": "<|reserved_special_token_11|>",
157
- "lstrip": false,
158
- "normalized": false,
159
- "rstrip": false,
160
- "single_word": false,
161
- "special": true
162
- },
163
- "128020": {
164
- "content": "<|reserved_special_token_12|>",
165
- "lstrip": false,
166
- "normalized": false,
167
- "rstrip": false,
168
- "single_word": false,
169
- "special": true
170
- },
171
- "128021": {
172
- "content": "<|reserved_special_token_13|>",
173
- "lstrip": false,
174
- "normalized": false,
175
- "rstrip": false,
176
- "single_word": false,
177
- "special": true
178
- },
179
- "128022": {
180
- "content": "<|reserved_special_token_14|>",
181
- "lstrip": false,
182
- "normalized": false,
183
- "rstrip": false,
184
- "single_word": false,
185
- "special": true
186
- },
187
- "128023": {
188
- "content": "<|reserved_special_token_15|>",
189
- "lstrip": false,
190
- "normalized": false,
191
- "rstrip": false,
192
- "single_word": false,
193
- "special": true
194
- },
195
- "128024": {
196
- "content": "<|reserved_special_token_16|>",
197
- "lstrip": false,
198
- "normalized": false,
199
- "rstrip": false,
200
- "single_word": false,
201
- "special": true
202
- },
203
- "128025": {
204
- "content": "<|reserved_special_token_17|>",
205
- "lstrip": false,
206
- "normalized": false,
207
- "rstrip": false,
208
- "single_word": false,
209
- "special": true
210
- },
211
- "128026": {
212
- "content": "<|reserved_special_token_18|>",
213
- "lstrip": false,
214
- "normalized": false,
215
- "rstrip": false,
216
- "single_word": false,
217
- "special": true
218
- },
219
- "128027": {
220
- "content": "<|reserved_special_token_19|>",
221
- "lstrip": false,
222
- "normalized": false,
223
- "rstrip": false,
224
- "single_word": false,
225
- "special": true
226
- },
227
- "128028": {
228
- "content": "<|reserved_special_token_20|>",
229
- "lstrip": false,
230
- "normalized": false,
231
- "rstrip": false,
232
- "single_word": false,
233
- "special": true
234
- },
235
- "128029": {
236
- "content": "<|reserved_special_token_21|>",
237
- "lstrip": false,
238
- "normalized": false,
239
- "rstrip": false,
240
- "single_word": false,
241
- "special": true
242
- },
243
- "128030": {
244
- "content": "<|reserved_special_token_22|>",
245
- "lstrip": false,
246
- "normalized": false,
247
- "rstrip": false,
248
- "single_word": false,
249
- "special": true
250
- },
251
- "128031": {
252
- "content": "<|reserved_special_token_23|>",
253
- "lstrip": false,
254
- "normalized": false,
255
- "rstrip": false,
256
- "single_word": false,
257
- "special": true
258
- },
259
- "128032": {
260
- "content": "<|reserved_special_token_24|>",
261
- "lstrip": false,
262
- "normalized": false,
263
- "rstrip": false,
264
- "single_word": false,
265
- "special": true
266
- },
267
- "128033": {
268
- "content": "<|reserved_special_token_25|>",
269
- "lstrip": false,
270
- "normalized": false,
271
- "rstrip": false,
272
- "single_word": false,
273
- "special": true
274
- },
275
- "128034": {
276
- "content": "<|reserved_special_token_26|>",
277
- "lstrip": false,
278
- "normalized": false,
279
- "rstrip": false,
280
- "single_word": false,
281
- "special": true
282
- },
283
- "128035": {
284
- "content": "<|reserved_special_token_27|>",
285
- "lstrip": false,
286
- "normalized": false,
287
- "rstrip": false,
288
- "single_word": false,
289
- "special": true
290
- },
291
- "128036": {
292
- "content": "<|reserved_special_token_28|>",
293
- "lstrip": false,
294
- "normalized": false,
295
- "rstrip": false,
296
- "single_word": false,
297
- "special": true
298
- },
299
- "128037": {
300
- "content": "<|reserved_special_token_29|>",
301
- "lstrip": false,
302
- "normalized": false,
303
- "rstrip": false,
304
- "single_word": false,
305
- "special": true
306
- },
307
- "128038": {
308
- "content": "<|reserved_special_token_30|>",
309
- "lstrip": false,
310
- "normalized": false,
311
- "rstrip": false,
312
- "single_word": false,
313
- "special": true
314
- },
315
- "128039": {
316
- "content": "<|reserved_special_token_31|>",
317
- "lstrip": false,
318
- "normalized": false,
319
- "rstrip": false,
320
- "single_word": false,
321
- "special": true
322
- },
323
- "128040": {
324
- "content": "<|reserved_special_token_32|>",
325
- "lstrip": false,
326
- "normalized": false,
327
- "rstrip": false,
328
- "single_word": false,
329
- "special": true
330
- },
331
- "128041": {
332
- "content": "<|reserved_special_token_33|>",
333
- "lstrip": false,
334
- "normalized": false,
335
- "rstrip": false,
336
- "single_word": false,
337
- "special": true
338
- },
339
- "128042": {
340
- "content": "<|reserved_special_token_34|>",
341
- "lstrip": false,
342
- "normalized": false,
343
- "rstrip": false,
344
- "single_word": false,
345
- "special": true
346
- },
347
- "128043": {
348
- "content": "<|reserved_special_token_35|>",
349
- "lstrip": false,
350
- "normalized": false,
351
- "rstrip": false,
352
- "single_word": false,
353
- "special": true
354
- },
355
- "128044": {
356
- "content": "<|reserved_special_token_36|>",
357
- "lstrip": false,
358
- "normalized": false,
359
- "rstrip": false,
360
- "single_word": false,
361
- "special": true
362
- },
363
- "128045": {
364
- "content": "<|reserved_special_token_37|>",
365
- "lstrip": false,
366
- "normalized": false,
367
- "rstrip": false,
368
- "single_word": false,
369
- "special": true
370
- },
371
- "128046": {
372
- "content": "<|reserved_special_token_38|>",
373
- "lstrip": false,
374
- "normalized": false,
375
- "rstrip": false,
376
- "single_word": false,
377
- "special": true
378
- },
379
- "128047": {
380
- "content": "<|reserved_special_token_39|>",
381
- "lstrip": false,
382
- "normalized": false,
383
- "rstrip": false,
384
- "single_word": false,
385
- "special": true
386
- },
387
- "128048": {
388
- "content": "<|reserved_special_token_40|>",
389
- "lstrip": false,
390
- "normalized": false,
391
- "rstrip": false,
392
- "single_word": false,
393
- "special": true
394
- },
395
- "128049": {
396
- "content": "<|reserved_special_token_41|>",
397
- "lstrip": false,
398
- "normalized": false,
399
- "rstrip": false,
400
- "single_word": false,
401
- "special": true
402
- },
403
- "128050": {
404
- "content": "<|reserved_special_token_42|>",
405
- "lstrip": false,
406
- "normalized": false,
407
- "rstrip": false,
408
- "single_word": false,
409
- "special": true
410
- },
411
- "128051": {
412
- "content": "<|reserved_special_token_43|>",
413
- "lstrip": false,
414
- "normalized": false,
415
- "rstrip": false,
416
- "single_word": false,
417
- "special": true
418
- },
419
- "128052": {
420
- "content": "<|reserved_special_token_44|>",
421
- "lstrip": false,
422
- "normalized": false,
423
- "rstrip": false,
424
- "single_word": false,
425
- "special": true
426
- },
427
- "128053": {
428
- "content": "<|reserved_special_token_45|>",
429
- "lstrip": false,
430
- "normalized": false,
431
- "rstrip": false,
432
- "single_word": false,
433
- "special": true
434
- },
435
- "128054": {
436
- "content": "<|reserved_special_token_46|>",
437
- "lstrip": false,
438
- "normalized": false,
439
- "rstrip": false,
440
- "single_word": false,
441
- "special": true
442
- },
443
- "128055": {
444
- "content": "<|reserved_special_token_47|>",
445
- "lstrip": false,
446
- "normalized": false,
447
- "rstrip": false,
448
- "single_word": false,
449
- "special": true
450
- },
451
- "128056": {
452
- "content": "<|reserved_special_token_48|>",
453
- "lstrip": false,
454
- "normalized": false,
455
- "rstrip": false,
456
- "single_word": false,
457
- "special": true
458
- },
459
- "128057": {
460
- "content": "<|reserved_special_token_49|>",
461
- "lstrip": false,
462
- "normalized": false,
463
- "rstrip": false,
464
- "single_word": false,
465
- "special": true
466
- },
467
- "128058": {
468
- "content": "<|reserved_special_token_50|>",
469
- "lstrip": false,
470
- "normalized": false,
471
- "rstrip": false,
472
- "single_word": false,
473
- "special": true
474
- },
475
- "128059": {
476
- "content": "<|reserved_special_token_51|>",
477
- "lstrip": false,
478
- "normalized": false,
479
- "rstrip": false,
480
- "single_word": false,
481
- "special": true
482
- },
483
- "128060": {
484
- "content": "<|reserved_special_token_52|>",
485
- "lstrip": false,
486
- "normalized": false,
487
- "rstrip": false,
488
- "single_word": false,
489
- "special": true
490
- },
491
- "128061": {
492
- "content": "<|reserved_special_token_53|>",
493
- "lstrip": false,
494
- "normalized": false,
495
- "rstrip": false,
496
- "single_word": false,
497
- "special": true
498
- },
499
- "128062": {
500
- "content": "<|reserved_special_token_54|>",
501
- "lstrip": false,
502
- "normalized": false,
503
- "rstrip": false,
504
- "single_word": false,
505
- "special": true
506
- },
507
- "128063": {
508
- "content": "<|reserved_special_token_55|>",
509
- "lstrip": false,
510
- "normalized": false,
511
- "rstrip": false,
512
- "single_word": false,
513
- "special": true
514
- },
515
- "128064": {
516
- "content": "<|reserved_special_token_56|>",
517
- "lstrip": false,
518
- "normalized": false,
519
- "rstrip": false,
520
- "single_word": false,
521
- "special": true
522
- },
523
- "128065": {
524
- "content": "<|reserved_special_token_57|>",
525
- "lstrip": false,
526
- "normalized": false,
527
- "rstrip": false,
528
- "single_word": false,
529
- "special": true
530
- },
531
- "128066": {
532
- "content": "<|reserved_special_token_58|>",
533
- "lstrip": false,
534
- "normalized": false,
535
- "rstrip": false,
536
- "single_word": false,
537
- "special": true
538
- },
539
- "128067": {
540
- "content": "<|reserved_special_token_59|>",
541
- "lstrip": false,
542
- "normalized": false,
543
- "rstrip": false,
544
- "single_word": false,
545
- "special": true
546
- },
547
- "128068": {
548
- "content": "<|reserved_special_token_60|>",
549
- "lstrip": false,
550
- "normalized": false,
551
- "rstrip": false,
552
- "single_word": false,
553
- "special": true
554
- },
555
- "128069": {
556
- "content": "<|reserved_special_token_61|>",
557
- "lstrip": false,
558
- "normalized": false,
559
- "rstrip": false,
560
- "single_word": false,
561
- "special": true
562
- },
563
- "128070": {
564
- "content": "<|reserved_special_token_62|>",
565
- "lstrip": false,
566
- "normalized": false,
567
- "rstrip": false,
568
- "single_word": false,
569
- "special": true
570
- },
571
- "128071": {
572
- "content": "<|reserved_special_token_63|>",
573
- "lstrip": false,
574
- "normalized": false,
575
- "rstrip": false,
576
- "single_word": false,
577
- "special": true
578
- },
579
- "128072": {
580
- "content": "<|reserved_special_token_64|>",
581
- "lstrip": false,
582
- "normalized": false,
583
- "rstrip": false,
584
- "single_word": false,
585
- "special": true
586
- },
587
- "128073": {
588
- "content": "<|reserved_special_token_65|>",
589
- "lstrip": false,
590
- "normalized": false,
591
- "rstrip": false,
592
- "single_word": false,
593
- "special": true
594
- },
595
- "128074": {
596
- "content": "<|reserved_special_token_66|>",
597
- "lstrip": false,
598
- "normalized": false,
599
- "rstrip": false,
600
- "single_word": false,
601
- "special": true
602
- },
603
- "128075": {
604
- "content": "<|reserved_special_token_67|>",
605
- "lstrip": false,
606
- "normalized": false,
607
- "rstrip": false,
608
- "single_word": false,
609
- "special": true
610
- },
611
- "128076": {
612
- "content": "<|reserved_special_token_68|>",
613
- "lstrip": false,
614
- "normalized": false,
615
- "rstrip": false,
616
- "single_word": false,
617
- "special": true
618
- },
619
- "128077": {
620
- "content": "<|reserved_special_token_69|>",
621
- "lstrip": false,
622
- "normalized": false,
623
- "rstrip": false,
624
- "single_word": false,
625
- "special": true
626
- },
627
- "128078": {
628
- "content": "<|reserved_special_token_70|>",
629
- "lstrip": false,
630
- "normalized": false,
631
- "rstrip": false,
632
- "single_word": false,
633
- "special": true
634
- },
635
- "128079": {
636
- "content": "<|reserved_special_token_71|>",
637
- "lstrip": false,
638
- "normalized": false,
639
- "rstrip": false,
640
- "single_word": false,
641
- "special": true
642
- },
643
- "128080": {
644
- "content": "<|reserved_special_token_72|>",
645
- "lstrip": false,
646
- "normalized": false,
647
- "rstrip": false,
648
- "single_word": false,
649
- "special": true
650
- },
651
- "128081": {
652
- "content": "<|reserved_special_token_73|>",
653
- "lstrip": false,
654
- "normalized": false,
655
- "rstrip": false,
656
- "single_word": false,
657
- "special": true
658
- },
659
- "128082": {
660
- "content": "<|reserved_special_token_74|>",
661
- "lstrip": false,
662
- "normalized": false,
663
- "rstrip": false,
664
- "single_word": false,
665
- "special": true
666
- },
667
- "128083": {
668
- "content": "<|reserved_special_token_75|>",
669
- "lstrip": false,
670
- "normalized": false,
671
- "rstrip": false,
672
- "single_word": false,
673
- "special": true
674
- },
675
- "128084": {
676
- "content": "<|reserved_special_token_76|>",
677
- "lstrip": false,
678
- "normalized": false,
679
- "rstrip": false,
680
- "single_word": false,
681
- "special": true
682
- },
683
- "128085": {
684
- "content": "<|reserved_special_token_77|>",
685
- "lstrip": false,
686
- "normalized": false,
687
- "rstrip": false,
688
- "single_word": false,
689
- "special": true
690
- },
691
- "128086": {
692
- "content": "<|reserved_special_token_78|>",
693
- "lstrip": false,
694
- "normalized": false,
695
- "rstrip": false,
696
- "single_word": false,
697
- "special": true
698
- },
699
- "128087": {
700
- "content": "<|reserved_special_token_79|>",
701
- "lstrip": false,
702
- "normalized": false,
703
- "rstrip": false,
704
- "single_word": false,
705
- "special": true
706
- },
707
- "128088": {
708
- "content": "<|reserved_special_token_80|>",
709
- "lstrip": false,
710
- "normalized": false,
711
- "rstrip": false,
712
- "single_word": false,
713
- "special": true
714
- },
715
- "128089": {
716
- "content": "<|reserved_special_token_81|>",
717
- "lstrip": false,
718
- "normalized": false,
719
- "rstrip": false,
720
- "single_word": false,
721
- "special": true
722
- },
723
- "128090": {
724
- "content": "<|reserved_special_token_82|>",
725
- "lstrip": false,
726
- "normalized": false,
727
- "rstrip": false,
728
- "single_word": false,
729
- "special": true
730
- },
731
- "128091": {
732
- "content": "<|reserved_special_token_83|>",
733
- "lstrip": false,
734
- "normalized": false,
735
- "rstrip": false,
736
- "single_word": false,
737
- "special": true
738
- },
739
- "128092": {
740
- "content": "<|reserved_special_token_84|>",
741
- "lstrip": false,
742
- "normalized": false,
743
- "rstrip": false,
744
- "single_word": false,
745
- "special": true
746
- },
747
- "128093": {
748
- "content": "<|reserved_special_token_85|>",
749
- "lstrip": false,
750
- "normalized": false,
751
- "rstrip": false,
752
- "single_word": false,
753
- "special": true
754
- },
755
- "128094": {
756
- "content": "<|reserved_special_token_86|>",
757
- "lstrip": false,
758
- "normalized": false,
759
- "rstrip": false,
760
- "single_word": false,
761
- "special": true
762
- },
763
- "128095": {
764
- "content": "<|reserved_special_token_87|>",
765
- "lstrip": false,
766
- "normalized": false,
767
- "rstrip": false,
768
- "single_word": false,
769
- "special": true
770
- },
771
- "128096": {
772
- "content": "<|reserved_special_token_88|>",
773
- "lstrip": false,
774
- "normalized": false,
775
- "rstrip": false,
776
- "single_word": false,
777
- "special": true
778
- },
779
- "128097": {
780
- "content": "<|reserved_special_token_89|>",
781
- "lstrip": false,
782
- "normalized": false,
783
- "rstrip": false,
784
- "single_word": false,
785
- "special": true
786
- },
787
- "128098": {
788
- "content": "<|reserved_special_token_90|>",
789
- "lstrip": false,
790
- "normalized": false,
791
- "rstrip": false,
792
- "single_word": false,
793
- "special": true
794
- },
795
- "128099": {
796
- "content": "<|reserved_special_token_91|>",
797
- "lstrip": false,
798
- "normalized": false,
799
- "rstrip": false,
800
- "single_word": false,
801
- "special": true
802
- },
803
- "128100": {
804
- "content": "<|reserved_special_token_92|>",
805
- "lstrip": false,
806
- "normalized": false,
807
- "rstrip": false,
808
- "single_word": false,
809
- "special": true
810
- },
811
- "128101": {
812
- "content": "<|reserved_special_token_93|>",
813
- "lstrip": false,
814
- "normalized": false,
815
- "rstrip": false,
816
- "single_word": false,
817
- "special": true
818
- },
819
- "128102": {
820
- "content": "<|reserved_special_token_94|>",
821
- "lstrip": false,
822
- "normalized": false,
823
- "rstrip": false,
824
- "single_word": false,
825
- "special": true
826
- },
827
- "128103": {
828
- "content": "<|reserved_special_token_95|>",
829
- "lstrip": false,
830
- "normalized": false,
831
- "rstrip": false,
832
- "single_word": false,
833
- "special": true
834
- },
835
- "128104": {
836
- "content": "<|reserved_special_token_96|>",
837
- "lstrip": false,
838
- "normalized": false,
839
- "rstrip": false,
840
- "single_word": false,
841
- "special": true
842
- },
843
- "128105": {
844
- "content": "<|reserved_special_token_97|>",
845
- "lstrip": false,
846
- "normalized": false,
847
- "rstrip": false,
848
- "single_word": false,
849
- "special": true
850
- },
851
- "128106": {
852
- "content": "<|reserved_special_token_98|>",
853
- "lstrip": false,
854
- "normalized": false,
855
- "rstrip": false,
856
- "single_word": false,
857
- "special": true
858
- },
859
- "128107": {
860
- "content": "<|reserved_special_token_99|>",
861
- "lstrip": false,
862
- "normalized": false,
863
- "rstrip": false,
864
- "single_word": false,
865
- "special": true
866
- },
867
- "128108": {
868
- "content": "<|reserved_special_token_100|>",
869
- "lstrip": false,
870
- "normalized": false,
871
- "rstrip": false,
872
- "single_word": false,
873
- "special": true
874
- },
875
- "128109": {
876
- "content": "<|reserved_special_token_101|>",
877
- "lstrip": false,
878
- "normalized": false,
879
- "rstrip": false,
880
- "single_word": false,
881
- "special": true
882
- },
883
- "128110": {
884
- "content": "<|reserved_special_token_102|>",
885
- "lstrip": false,
886
- "normalized": false,
887
- "rstrip": false,
888
- "single_word": false,
889
- "special": true
890
- },
891
- "128111": {
892
- "content": "<|reserved_special_token_103|>",
893
- "lstrip": false,
894
- "normalized": false,
895
- "rstrip": false,
896
- "single_word": false,
897
- "special": true
898
- },
899
- "128112": {
900
- "content": "<|reserved_special_token_104|>",
901
- "lstrip": false,
902
- "normalized": false,
903
- "rstrip": false,
904
- "single_word": false,
905
- "special": true
906
- },
907
- "128113": {
908
- "content": "<|reserved_special_token_105|>",
909
- "lstrip": false,
910
- "normalized": false,
911
- "rstrip": false,
912
- "single_word": false,
913
- "special": true
914
- },
915
- "128114": {
916
- "content": "<|reserved_special_token_106|>",
917
- "lstrip": false,
918
- "normalized": false,
919
- "rstrip": false,
920
- "single_word": false,
921
- "special": true
922
- },
923
- "128115": {
924
- "content": "<|reserved_special_token_107|>",
925
- "lstrip": false,
926
- "normalized": false,
927
- "rstrip": false,
928
- "single_word": false,
929
- "special": true
930
- },
931
- "128116": {
932
- "content": "<|reserved_special_token_108|>",
933
- "lstrip": false,
934
- "normalized": false,
935
- "rstrip": false,
936
- "single_word": false,
937
- "special": true
938
- },
939
- "128117": {
940
- "content": "<|reserved_special_token_109|>",
941
- "lstrip": false,
942
- "normalized": false,
943
- "rstrip": false,
944
- "single_word": false,
945
- "special": true
946
- },
947
- "128118": {
948
- "content": "<|reserved_special_token_110|>",
949
- "lstrip": false,
950
- "normalized": false,
951
- "rstrip": false,
952
- "single_word": false,
953
- "special": true
954
- },
955
- "128119": {
956
- "content": "<|reserved_special_token_111|>",
957
- "lstrip": false,
958
- "normalized": false,
959
- "rstrip": false,
960
- "single_word": false,
961
- "special": true
962
- },
963
- "128120": {
964
- "content": "<|reserved_special_token_112|>",
965
- "lstrip": false,
966
- "normalized": false,
967
- "rstrip": false,
968
- "single_word": false,
969
- "special": true
970
- },
971
- "128121": {
972
- "content": "<|reserved_special_token_113|>",
973
- "lstrip": false,
974
- "normalized": false,
975
- "rstrip": false,
976
- "single_word": false,
977
- "special": true
978
- },
979
- "128122": {
980
- "content": "<|reserved_special_token_114|>",
981
- "lstrip": false,
982
- "normalized": false,
983
- "rstrip": false,
984
- "single_word": false,
985
- "special": true
986
- },
987
- "128123": {
988
- "content": "<|reserved_special_token_115|>",
989
- "lstrip": false,
990
- "normalized": false,
991
- "rstrip": false,
992
- "single_word": false,
993
- "special": true
994
- },
995
- "128124": {
996
- "content": "<|reserved_special_token_116|>",
997
- "lstrip": false,
998
- "normalized": false,
999
- "rstrip": false,
1000
- "single_word": false,
1001
- "special": true
1002
- },
1003
- "128125": {
1004
- "content": "<|reserved_special_token_117|>",
1005
- "lstrip": false,
1006
- "normalized": false,
1007
- "rstrip": false,
1008
- "single_word": false,
1009
- "special": true
1010
- },
1011
- "128126": {
1012
- "content": "<|reserved_special_token_118|>",
1013
- "lstrip": false,
1014
- "normalized": false,
1015
- "rstrip": false,
1016
- "single_word": false,
1017
- "special": true
1018
- },
1019
- "128127": {
1020
- "content": "<|reserved_special_token_119|>",
1021
- "lstrip": false,
1022
- "normalized": false,
1023
- "rstrip": false,
1024
- "single_word": false,
1025
- "special": true
1026
- },
1027
- "128128": {
1028
- "content": "<|reserved_special_token_120|>",
1029
- "lstrip": false,
1030
- "normalized": false,
1031
- "rstrip": false,
1032
- "single_word": false,
1033
- "special": true
1034
- },
1035
- "128129": {
1036
- "content": "<|reserved_special_token_121|>",
1037
- "lstrip": false,
1038
- "normalized": false,
1039
- "rstrip": false,
1040
- "single_word": false,
1041
- "special": true
1042
- },
1043
- "128130": {
1044
- "content": "<|reserved_special_token_122|>",
1045
- "lstrip": false,
1046
- "normalized": false,
1047
- "rstrip": false,
1048
- "single_word": false,
1049
- "special": true
1050
- },
1051
- "128131": {
1052
- "content": "<|reserved_special_token_123|>",
1053
- "lstrip": false,
1054
- "normalized": false,
1055
- "rstrip": false,
1056
- "single_word": false,
1057
- "special": true
1058
- },
1059
- "128132": {
1060
- "content": "<|reserved_special_token_124|>",
1061
- "lstrip": false,
1062
- "normalized": false,
1063
- "rstrip": false,
1064
- "single_word": false,
1065
- "special": true
1066
- },
1067
- "128133": {
1068
- "content": "<|reserved_special_token_125|>",
1069
- "lstrip": false,
1070
- "normalized": false,
1071
- "rstrip": false,
1072
- "single_word": false,
1073
- "special": true
1074
- },
1075
- "128134": {
1076
- "content": "<|reserved_special_token_126|>",
1077
- "lstrip": false,
1078
- "normalized": false,
1079
- "rstrip": false,
1080
- "single_word": false,
1081
- "special": true
1082
- },
1083
- "128135": {
1084
- "content": "<|reserved_special_token_127|>",
1085
- "lstrip": false,
1086
- "normalized": false,
1087
- "rstrip": false,
1088
- "single_word": false,
1089
- "special": true
1090
- },
1091
- "128136": {
1092
- "content": "<|reserved_special_token_128|>",
1093
- "lstrip": false,
1094
- "normalized": false,
1095
- "rstrip": false,
1096
- "single_word": false,
1097
- "special": true
1098
- },
1099
- "128137": {
1100
- "content": "<|reserved_special_token_129|>",
1101
- "lstrip": false,
1102
- "normalized": false,
1103
- "rstrip": false,
1104
- "single_word": false,
1105
- "special": true
1106
- },
1107
- "128138": {
1108
- "content": "<|reserved_special_token_130|>",
1109
- "lstrip": false,
1110
- "normalized": false,
1111
- "rstrip": false,
1112
- "single_word": false,
1113
- "special": true
1114
- },
1115
- "128139": {
1116
- "content": "<|reserved_special_token_131|>",
1117
- "lstrip": false,
1118
- "normalized": false,
1119
- "rstrip": false,
1120
- "single_word": false,
1121
- "special": true
1122
- },
1123
- "128140": {
1124
- "content": "<|reserved_special_token_132|>",
1125
- "lstrip": false,
1126
- "normalized": false,
1127
- "rstrip": false,
1128
- "single_word": false,
1129
- "special": true
1130
- },
1131
- "128141": {
1132
- "content": "<|reserved_special_token_133|>",
1133
- "lstrip": false,
1134
- "normalized": false,
1135
- "rstrip": false,
1136
- "single_word": false,
1137
- "special": true
1138
- },
1139
- "128142": {
1140
- "content": "<|reserved_special_token_134|>",
1141
- "lstrip": false,
1142
- "normalized": false,
1143
- "rstrip": false,
1144
- "single_word": false,
1145
- "special": true
1146
- },
1147
- "128143": {
1148
- "content": "<|reserved_special_token_135|>",
1149
- "lstrip": false,
1150
- "normalized": false,
1151
- "rstrip": false,
1152
- "single_word": false,
1153
- "special": true
1154
- },
1155
- "128144": {
1156
- "content": "<|reserved_special_token_136|>",
1157
- "lstrip": false,
1158
- "normalized": false,
1159
- "rstrip": false,
1160
- "single_word": false,
1161
- "special": true
1162
- },
1163
- "128145": {
1164
- "content": "<|reserved_special_token_137|>",
1165
- "lstrip": false,
1166
- "normalized": false,
1167
- "rstrip": false,
1168
- "single_word": false,
1169
- "special": true
1170
- },
1171
- "128146": {
1172
- "content": "<|reserved_special_token_138|>",
1173
- "lstrip": false,
1174
- "normalized": false,
1175
- "rstrip": false,
1176
- "single_word": false,
1177
- "special": true
1178
- },
1179
- "128147": {
1180
- "content": "<|reserved_special_token_139|>",
1181
- "lstrip": false,
1182
- "normalized": false,
1183
- "rstrip": false,
1184
- "single_word": false,
1185
- "special": true
1186
- },
1187
- "128148": {
1188
- "content": "<|reserved_special_token_140|>",
1189
- "lstrip": false,
1190
- "normalized": false,
1191
- "rstrip": false,
1192
- "single_word": false,
1193
- "special": true
1194
- },
1195
- "128149": {
1196
- "content": "<|reserved_special_token_141|>",
1197
- "lstrip": false,
1198
- "normalized": false,
1199
- "rstrip": false,
1200
- "single_word": false,
1201
- "special": true
1202
- },
1203
- "128150": {
1204
- "content": "<|reserved_special_token_142|>",
1205
- "lstrip": false,
1206
- "normalized": false,
1207
- "rstrip": false,
1208
- "single_word": false,
1209
- "special": true
1210
- },
1211
- "128151": {
1212
- "content": "<|reserved_special_token_143|>",
1213
- "lstrip": false,
1214
- "normalized": false,
1215
- "rstrip": false,
1216
- "single_word": false,
1217
- "special": true
1218
- },
1219
- "128152": {
1220
- "content": "<|reserved_special_token_144|>",
1221
- "lstrip": false,
1222
- "normalized": false,
1223
- "rstrip": false,
1224
- "single_word": false,
1225
- "special": true
1226
- },
1227
- "128153": {
1228
- "content": "<|reserved_special_token_145|>",
1229
- "lstrip": false,
1230
- "normalized": false,
1231
- "rstrip": false,
1232
- "single_word": false,
1233
- "special": true
1234
- },
1235
- "128154": {
1236
- "content": "<|reserved_special_token_146|>",
1237
- "lstrip": false,
1238
- "normalized": false,
1239
- "rstrip": false,
1240
- "single_word": false,
1241
- "special": true
1242
- },
1243
- "128155": {
1244
- "content": "<|reserved_special_token_147|>",
1245
- "lstrip": false,
1246
- "normalized": false,
1247
- "rstrip": false,
1248
- "single_word": false,
1249
- "special": true
1250
- },
1251
- "128156": {
1252
- "content": "<|reserved_special_token_148|>",
1253
- "lstrip": false,
1254
- "normalized": false,
1255
- "rstrip": false,
1256
- "single_word": false,
1257
- "special": true
1258
- },
1259
- "128157": {
1260
- "content": "<|reserved_special_token_149|>",
1261
- "lstrip": false,
1262
- "normalized": false,
1263
- "rstrip": false,
1264
- "single_word": false,
1265
- "special": true
1266
- },
1267
- "128158": {
1268
- "content": "<|reserved_special_token_150|>",
1269
- "lstrip": false,
1270
- "normalized": false,
1271
- "rstrip": false,
1272
- "single_word": false,
1273
- "special": true
1274
- },
1275
- "128159": {
1276
- "content": "<|reserved_special_token_151|>",
1277
- "lstrip": false,
1278
- "normalized": false,
1279
- "rstrip": false,
1280
- "single_word": false,
1281
- "special": true
1282
- },
1283
- "128160": {
1284
- "content": "<|reserved_special_token_152|>",
1285
- "lstrip": false,
1286
- "normalized": false,
1287
- "rstrip": false,
1288
- "single_word": false,
1289
- "special": true
1290
- },
1291
- "128161": {
1292
- "content": "<|reserved_special_token_153|>",
1293
- "lstrip": false,
1294
- "normalized": false,
1295
- "rstrip": false,
1296
- "single_word": false,
1297
- "special": true
1298
- },
1299
- "128162": {
1300
- "content": "<|reserved_special_token_154|>",
1301
- "lstrip": false,
1302
- "normalized": false,
1303
- "rstrip": false,
1304
- "single_word": false,
1305
- "special": true
1306
- },
1307
- "128163": {
1308
- "content": "<|reserved_special_token_155|>",
1309
- "lstrip": false,
1310
- "normalized": false,
1311
- "rstrip": false,
1312
- "single_word": false,
1313
- "special": true
1314
- },
1315
- "128164": {
1316
- "content": "<|reserved_special_token_156|>",
1317
- "lstrip": false,
1318
- "normalized": false,
1319
- "rstrip": false,
1320
- "single_word": false,
1321
- "special": true
1322
- },
1323
- "128165": {
1324
- "content": "<|reserved_special_token_157|>",
1325
- "lstrip": false,
1326
- "normalized": false,
1327
- "rstrip": false,
1328
- "single_word": false,
1329
- "special": true
1330
- },
1331
- "128166": {
1332
- "content": "<|reserved_special_token_158|>",
1333
- "lstrip": false,
1334
- "normalized": false,
1335
- "rstrip": false,
1336
- "single_word": false,
1337
- "special": true
1338
- },
1339
- "128167": {
1340
- "content": "<|reserved_special_token_159|>",
1341
- "lstrip": false,
1342
- "normalized": false,
1343
- "rstrip": false,
1344
- "single_word": false,
1345
- "special": true
1346
- },
1347
- "128168": {
1348
- "content": "<|reserved_special_token_160|>",
1349
- "lstrip": false,
1350
- "normalized": false,
1351
- "rstrip": false,
1352
- "single_word": false,
1353
- "special": true
1354
- },
1355
- "128169": {
1356
- "content": "<|reserved_special_token_161|>",
1357
- "lstrip": false,
1358
- "normalized": false,
1359
- "rstrip": false,
1360
- "single_word": false,
1361
- "special": true
1362
- },
1363
- "128170": {
1364
- "content": "<|reserved_special_token_162|>",
1365
- "lstrip": false,
1366
- "normalized": false,
1367
- "rstrip": false,
1368
- "single_word": false,
1369
- "special": true
1370
- },
1371
- "128171": {
1372
- "content": "<|reserved_special_token_163|>",
1373
- "lstrip": false,
1374
- "normalized": false,
1375
- "rstrip": false,
1376
- "single_word": false,
1377
- "special": true
1378
- },
1379
- "128172": {
1380
- "content": "<|reserved_special_token_164|>",
1381
- "lstrip": false,
1382
- "normalized": false,
1383
- "rstrip": false,
1384
- "single_word": false,
1385
- "special": true
1386
- },
1387
- "128173": {
1388
- "content": "<|reserved_special_token_165|>",
1389
- "lstrip": false,
1390
- "normalized": false,
1391
- "rstrip": false,
1392
- "single_word": false,
1393
- "special": true
1394
- },
1395
- "128174": {
1396
- "content": "<|reserved_special_token_166|>",
1397
- "lstrip": false,
1398
- "normalized": false,
1399
- "rstrip": false,
1400
- "single_word": false,
1401
- "special": true
1402
- },
1403
- "128175": {
1404
- "content": "<|reserved_special_token_167|>",
1405
- "lstrip": false,
1406
- "normalized": false,
1407
- "rstrip": false,
1408
- "single_word": false,
1409
- "special": true
1410
- },
1411
- "128176": {
1412
- "content": "<|reserved_special_token_168|>",
1413
- "lstrip": false,
1414
- "normalized": false,
1415
- "rstrip": false,
1416
- "single_word": false,
1417
- "special": true
1418
- },
1419
- "128177": {
1420
- "content": "<|reserved_special_token_169|>",
1421
- "lstrip": false,
1422
- "normalized": false,
1423
- "rstrip": false,
1424
- "single_word": false,
1425
- "special": true
1426
- },
1427
- "128178": {
1428
- "content": "<|reserved_special_token_170|>",
1429
- "lstrip": false,
1430
- "normalized": false,
1431
- "rstrip": false,
1432
- "single_word": false,
1433
- "special": true
1434
- },
1435
- "128179": {
1436
- "content": "<|reserved_special_token_171|>",
1437
- "lstrip": false,
1438
- "normalized": false,
1439
- "rstrip": false,
1440
- "single_word": false,
1441
- "special": true
1442
- },
1443
- "128180": {
1444
- "content": "<|reserved_special_token_172|>",
1445
- "lstrip": false,
1446
- "normalized": false,
1447
- "rstrip": false,
1448
- "single_word": false,
1449
- "special": true
1450
- },
1451
- "128181": {
1452
- "content": "<|reserved_special_token_173|>",
1453
- "lstrip": false,
1454
- "normalized": false,
1455
- "rstrip": false,
1456
- "single_word": false,
1457
- "special": true
1458
- },
1459
- "128182": {
1460
- "content": "<|reserved_special_token_174|>",
1461
- "lstrip": false,
1462
- "normalized": false,
1463
- "rstrip": false,
1464
- "single_word": false,
1465
- "special": true
1466
- },
1467
- "128183": {
1468
- "content": "<|reserved_special_token_175|>",
1469
- "lstrip": false,
1470
- "normalized": false,
1471
- "rstrip": false,
1472
- "single_word": false,
1473
- "special": true
1474
- },
1475
- "128184": {
1476
- "content": "<|reserved_special_token_176|>",
1477
- "lstrip": false,
1478
- "normalized": false,
1479
- "rstrip": false,
1480
- "single_word": false,
1481
- "special": true
1482
- },
1483
- "128185": {
1484
- "content": "<|reserved_special_token_177|>",
1485
- "lstrip": false,
1486
- "normalized": false,
1487
- "rstrip": false,
1488
- "single_word": false,
1489
- "special": true
1490
- },
1491
- "128186": {
1492
- "content": "<|reserved_special_token_178|>",
1493
- "lstrip": false,
1494
- "normalized": false,
1495
- "rstrip": false,
1496
- "single_word": false,
1497
- "special": true
1498
- },
1499
- "128187": {
1500
- "content": "<|reserved_special_token_179|>",
1501
- "lstrip": false,
1502
- "normalized": false,
1503
- "rstrip": false,
1504
- "single_word": false,
1505
- "special": true
1506
- },
1507
- "128188": {
1508
- "content": "<|reserved_special_token_180|>",
1509
- "lstrip": false,
1510
- "normalized": false,
1511
- "rstrip": false,
1512
- "single_word": false,
1513
- "special": true
1514
- },
1515
- "128189": {
1516
- "content": "<|reserved_special_token_181|>",
1517
- "lstrip": false,
1518
- "normalized": false,
1519
- "rstrip": false,
1520
- "single_word": false,
1521
- "special": true
1522
- },
1523
- "128190": {
1524
- "content": "<|reserved_special_token_182|>",
1525
- "lstrip": false,
1526
- "normalized": false,
1527
- "rstrip": false,
1528
- "single_word": false,
1529
- "special": true
1530
- },
1531
- "128191": {
1532
- "content": "<|reserved_special_token_183|>",
1533
- "lstrip": false,
1534
- "normalized": false,
1535
- "rstrip": false,
1536
- "single_word": false,
1537
- "special": true
1538
- },
1539
- "128192": {
1540
- "content": "<|reserved_special_token_184|>",
1541
- "lstrip": false,
1542
- "normalized": false,
1543
- "rstrip": false,
1544
- "single_word": false,
1545
- "special": true
1546
- },
1547
- "128193": {
1548
- "content": "<|reserved_special_token_185|>",
1549
- "lstrip": false,
1550
- "normalized": false,
1551
- "rstrip": false,
1552
- "single_word": false,
1553
- "special": true
1554
- },
1555
- "128194": {
1556
- "content": "<|reserved_special_token_186|>",
1557
- "lstrip": false,
1558
- "normalized": false,
1559
- "rstrip": false,
1560
- "single_word": false,
1561
- "special": true
1562
- },
1563
- "128195": {
1564
- "content": "<|reserved_special_token_187|>",
1565
- "lstrip": false,
1566
- "normalized": false,
1567
- "rstrip": false,
1568
- "single_word": false,
1569
- "special": true
1570
- },
1571
- "128196": {
1572
- "content": "<|reserved_special_token_188|>",
1573
- "lstrip": false,
1574
- "normalized": false,
1575
- "rstrip": false,
1576
- "single_word": false,
1577
- "special": true
1578
- },
1579
- "128197": {
1580
- "content": "<|reserved_special_token_189|>",
1581
- "lstrip": false,
1582
- "normalized": false,
1583
- "rstrip": false,
1584
- "single_word": false,
1585
- "special": true
1586
- },
1587
- "128198": {
1588
- "content": "<|reserved_special_token_190|>",
1589
- "lstrip": false,
1590
- "normalized": false,
1591
- "rstrip": false,
1592
- "single_word": false,
1593
- "special": true
1594
- },
1595
- "128199": {
1596
- "content": "<|reserved_special_token_191|>",
1597
- "lstrip": false,
1598
- "normalized": false,
1599
- "rstrip": false,
1600
- "single_word": false,
1601
- "special": true
1602
- },
1603
- "128200": {
1604
- "content": "<|reserved_special_token_192|>",
1605
- "lstrip": false,
1606
- "normalized": false,
1607
- "rstrip": false,
1608
- "single_word": false,
1609
- "special": true
1610
- },
1611
- "128201": {
1612
- "content": "<|reserved_special_token_193|>",
1613
- "lstrip": false,
1614
- "normalized": false,
1615
- "rstrip": false,
1616
- "single_word": false,
1617
- "special": true
1618
- },
1619
- "128202": {
1620
- "content": "<|reserved_special_token_194|>",
1621
- "lstrip": false,
1622
- "normalized": false,
1623
- "rstrip": false,
1624
- "single_word": false,
1625
- "special": true
1626
- },
1627
- "128203": {
1628
- "content": "<|reserved_special_token_195|>",
1629
- "lstrip": false,
1630
- "normalized": false,
1631
- "rstrip": false,
1632
- "single_word": false,
1633
- "special": true
1634
- },
1635
- "128204": {
1636
- "content": "<|reserved_special_token_196|>",
1637
- "lstrip": false,
1638
- "normalized": false,
1639
- "rstrip": false,
1640
- "single_word": false,
1641
- "special": true
1642
- },
1643
- "128205": {
1644
- "content": "<|reserved_special_token_197|>",
1645
- "lstrip": false,
1646
- "normalized": false,
1647
- "rstrip": false,
1648
- "single_word": false,
1649
- "special": true
1650
- },
1651
- "128206": {
1652
- "content": "<|reserved_special_token_198|>",
1653
- "lstrip": false,
1654
- "normalized": false,
1655
- "rstrip": false,
1656
- "single_word": false,
1657
- "special": true
1658
- },
1659
- "128207": {
1660
- "content": "<|reserved_special_token_199|>",
1661
- "lstrip": false,
1662
- "normalized": false,
1663
- "rstrip": false,
1664
- "single_word": false,
1665
- "special": true
1666
- },
1667
- "128208": {
1668
- "content": "<|reserved_special_token_200|>",
1669
- "lstrip": false,
1670
- "normalized": false,
1671
- "rstrip": false,
1672
- "single_word": false,
1673
- "special": true
1674
- },
1675
- "128209": {
1676
- "content": "<|reserved_special_token_201|>",
1677
- "lstrip": false,
1678
- "normalized": false,
1679
- "rstrip": false,
1680
- "single_word": false,
1681
- "special": true
1682
- },
1683
- "128210": {
1684
- "content": "<|reserved_special_token_202|>",
1685
- "lstrip": false,
1686
- "normalized": false,
1687
- "rstrip": false,
1688
- "single_word": false,
1689
- "special": true
1690
- },
1691
- "128211": {
1692
- "content": "<|reserved_special_token_203|>",
1693
- "lstrip": false,
1694
- "normalized": false,
1695
- "rstrip": false,
1696
- "single_word": false,
1697
- "special": true
1698
- },
1699
- "128212": {
1700
- "content": "<|reserved_special_token_204|>",
1701
- "lstrip": false,
1702
- "normalized": false,
1703
- "rstrip": false,
1704
- "single_word": false,
1705
- "special": true
1706
- },
1707
- "128213": {
1708
- "content": "<|reserved_special_token_205|>",
1709
- "lstrip": false,
1710
- "normalized": false,
1711
- "rstrip": false,
1712
- "single_word": false,
1713
- "special": true
1714
- },
1715
- "128214": {
1716
- "content": "<|reserved_special_token_206|>",
1717
- "lstrip": false,
1718
- "normalized": false,
1719
- "rstrip": false,
1720
- "single_word": false,
1721
- "special": true
1722
- },
1723
- "128215": {
1724
- "content": "<|reserved_special_token_207|>",
1725
- "lstrip": false,
1726
- "normalized": false,
1727
- "rstrip": false,
1728
- "single_word": false,
1729
- "special": true
1730
- },
1731
- "128216": {
1732
- "content": "<|reserved_special_token_208|>",
1733
- "lstrip": false,
1734
- "normalized": false,
1735
- "rstrip": false,
1736
- "single_word": false,
1737
- "special": true
1738
- },
1739
- "128217": {
1740
- "content": "<|reserved_special_token_209|>",
1741
- "lstrip": false,
1742
- "normalized": false,
1743
- "rstrip": false,
1744
- "single_word": false,
1745
- "special": true
1746
- },
1747
- "128218": {
1748
- "content": "<|reserved_special_token_210|>",
1749
- "lstrip": false,
1750
- "normalized": false,
1751
- "rstrip": false,
1752
- "single_word": false,
1753
- "special": true
1754
- },
1755
- "128219": {
1756
- "content": "<|reserved_special_token_211|>",
1757
- "lstrip": false,
1758
- "normalized": false,
1759
- "rstrip": false,
1760
- "single_word": false,
1761
- "special": true
1762
- },
1763
- "128220": {
1764
- "content": "<|reserved_special_token_212|>",
1765
- "lstrip": false,
1766
- "normalized": false,
1767
- "rstrip": false,
1768
- "single_word": false,
1769
- "special": true
1770
- },
1771
- "128221": {
1772
- "content": "<|reserved_special_token_213|>",
1773
- "lstrip": false,
1774
- "normalized": false,
1775
- "rstrip": false,
1776
- "single_word": false,
1777
- "special": true
1778
- },
1779
- "128222": {
1780
- "content": "<|reserved_special_token_214|>",
1781
- "lstrip": false,
1782
- "normalized": false,
1783
- "rstrip": false,
1784
- "single_word": false,
1785
- "special": true
1786
- },
1787
- "128223": {
1788
- "content": "<|reserved_special_token_215|>",
1789
- "lstrip": false,
1790
- "normalized": false,
1791
- "rstrip": false,
1792
- "single_word": false,
1793
- "special": true
1794
- },
1795
- "128224": {
1796
- "content": "<|reserved_special_token_216|>",
1797
- "lstrip": false,
1798
- "normalized": false,
1799
- "rstrip": false,
1800
- "single_word": false,
1801
- "special": true
1802
- },
1803
- "128225": {
1804
- "content": "<|reserved_special_token_217|>",
1805
- "lstrip": false,
1806
- "normalized": false,
1807
- "rstrip": false,
1808
- "single_word": false,
1809
- "special": true
1810
- },
1811
- "128226": {
1812
- "content": "<|reserved_special_token_218|>",
1813
- "lstrip": false,
1814
- "normalized": false,
1815
- "rstrip": false,
1816
- "single_word": false,
1817
- "special": true
1818
- },
1819
- "128227": {
1820
- "content": "<|reserved_special_token_219|>",
1821
- "lstrip": false,
1822
- "normalized": false,
1823
- "rstrip": false,
1824
- "single_word": false,
1825
- "special": true
1826
- },
1827
- "128228": {
1828
- "content": "<|reserved_special_token_220|>",
1829
- "lstrip": false,
1830
- "normalized": false,
1831
- "rstrip": false,
1832
- "single_word": false,
1833
- "special": true
1834
- },
1835
- "128229": {
1836
- "content": "<|reserved_special_token_221|>",
1837
- "lstrip": false,
1838
- "normalized": false,
1839
- "rstrip": false,
1840
- "single_word": false,
1841
- "special": true
1842
- },
1843
- "128230": {
1844
- "content": "<|reserved_special_token_222|>",
1845
- "lstrip": false,
1846
- "normalized": false,
1847
- "rstrip": false,
1848
- "single_word": false,
1849
- "special": true
1850
- },
1851
- "128231": {
1852
- "content": "<|reserved_special_token_223|>",
1853
- "lstrip": false,
1854
- "normalized": false,
1855
- "rstrip": false,
1856
- "single_word": false,
1857
- "special": true
1858
- },
1859
- "128232": {
1860
- "content": "<|reserved_special_token_224|>",
1861
- "lstrip": false,
1862
- "normalized": false,
1863
- "rstrip": false,
1864
- "single_word": false,
1865
- "special": true
1866
- },
1867
- "128233": {
1868
- "content": "<|reserved_special_token_225|>",
1869
- "lstrip": false,
1870
- "normalized": false,
1871
- "rstrip": false,
1872
- "single_word": false,
1873
- "special": true
1874
- },
1875
- "128234": {
1876
- "content": "<|reserved_special_token_226|>",
1877
- "lstrip": false,
1878
- "normalized": false,
1879
- "rstrip": false,
1880
- "single_word": false,
1881
- "special": true
1882
- },
1883
- "128235": {
1884
- "content": "<|reserved_special_token_227|>",
1885
- "lstrip": false,
1886
- "normalized": false,
1887
- "rstrip": false,
1888
- "single_word": false,
1889
- "special": true
1890
- },
1891
- "128236": {
1892
- "content": "<|reserved_special_token_228|>",
1893
- "lstrip": false,
1894
- "normalized": false,
1895
- "rstrip": false,
1896
- "single_word": false,
1897
- "special": true
1898
- },
1899
- "128237": {
1900
- "content": "<|reserved_special_token_229|>",
1901
- "lstrip": false,
1902
- "normalized": false,
1903
- "rstrip": false,
1904
- "single_word": false,
1905
- "special": true
1906
- },
1907
- "128238": {
1908
- "content": "<|reserved_special_token_230|>",
1909
- "lstrip": false,
1910
- "normalized": false,
1911
- "rstrip": false,
1912
- "single_word": false,
1913
- "special": true
1914
- },
1915
- "128239": {
1916
- "content": "<|reserved_special_token_231|>",
1917
- "lstrip": false,
1918
- "normalized": false,
1919
- "rstrip": false,
1920
- "single_word": false,
1921
- "special": true
1922
- },
1923
- "128240": {
1924
- "content": "<|reserved_special_token_232|>",
1925
- "lstrip": false,
1926
- "normalized": false,
1927
- "rstrip": false,
1928
- "single_word": false,
1929
- "special": true
1930
- },
1931
- "128241": {
1932
- "content": "<|reserved_special_token_233|>",
1933
- "lstrip": false,
1934
- "normalized": false,
1935
- "rstrip": false,
1936
- "single_word": false,
1937
- "special": true
1938
- },
1939
- "128242": {
1940
- "content": "<|reserved_special_token_234|>",
1941
- "lstrip": false,
1942
- "normalized": false,
1943
- "rstrip": false,
1944
- "single_word": false,
1945
- "special": true
1946
- },
1947
- "128243": {
1948
- "content": "<|reserved_special_token_235|>",
1949
- "lstrip": false,
1950
- "normalized": false,
1951
- "rstrip": false,
1952
- "single_word": false,
1953
- "special": true
1954
- },
1955
- "128244": {
1956
- "content": "<|reserved_special_token_236|>",
1957
- "lstrip": false,
1958
- "normalized": false,
1959
- "rstrip": false,
1960
- "single_word": false,
1961
- "special": true
1962
- },
1963
- "128245": {
1964
- "content": "<|reserved_special_token_237|>",
1965
- "lstrip": false,
1966
- "normalized": false,
1967
- "rstrip": false,
1968
- "single_word": false,
1969
- "special": true
1970
- },
1971
- "128246": {
1972
- "content": "<|reserved_special_token_238|>",
1973
- "lstrip": false,
1974
- "normalized": false,
1975
- "rstrip": false,
1976
- "single_word": false,
1977
- "special": true
1978
- },
1979
- "128247": {
1980
- "content": "<|reserved_special_token_239|>",
1981
- "lstrip": false,
1982
- "normalized": false,
1983
- "rstrip": false,
1984
- "single_word": false,
1985
- "special": true
1986
- },
1987
- "128248": {
1988
- "content": "<|reserved_special_token_240|>",
1989
- "lstrip": false,
1990
- "normalized": false,
1991
- "rstrip": false,
1992
- "single_word": false,
1993
- "special": true
1994
- },
1995
- "128249": {
1996
- "content": "<|reserved_special_token_241|>",
1997
- "lstrip": false,
1998
- "normalized": false,
1999
- "rstrip": false,
2000
- "single_word": false,
2001
- "special": true
2002
- },
2003
- "128250": {
2004
- "content": "<|reserved_special_token_242|>",
2005
- "lstrip": false,
2006
- "normalized": false,
2007
- "rstrip": false,
2008
- "single_word": false,
2009
- "special": true
2010
- },
2011
- "128251": {
2012
- "content": "<|reserved_special_token_243|>",
2013
- "lstrip": false,
2014
- "normalized": false,
2015
- "rstrip": false,
2016
- "single_word": false,
2017
- "special": true
2018
- },
2019
- "128252": {
2020
- "content": "<|reserved_special_token_244|>",
2021
- "lstrip": false,
2022
- "normalized": false,
2023
- "rstrip": false,
2024
- "single_word": false,
2025
- "special": true
2026
- },
2027
- "128253": {
2028
- "content": "<|reserved_special_token_245|>",
2029
- "lstrip": false,
2030
- "normalized": false,
2031
- "rstrip": false,
2032
- "single_word": false,
2033
- "special": true
2034
- },
2035
- "128254": {
2036
- "content": "<|reserved_special_token_246|>",
2037
- "lstrip": false,
2038
- "normalized": false,
2039
- "rstrip": false,
2040
- "single_word": false,
2041
- "special": true
2042
- },
2043
- "128255": {
2044
- "content": "<|reserved_special_token_247|>",
2045
- "lstrip": false,
2046
- "normalized": false,
2047
- "rstrip": false,
2048
- "single_word": false,
2049
- "special": true
2050
- }
2051
- },
2052
- "bos_token": "<|begin_of_text|>",
2053
- "clean_up_tokenization_spaces": true,
2054
- "eos_token": "<|eot_id|>",
2055
- "extra_special_tokens": {},
2056
- "model_input_names": [
2057
- "input_ids",
2058
- "attention_mask"
2059
- ],
2060
- "model_max_length": 131072,
2061
- "pad_token": "<|eot_id|>",
2062
- "tokenizer_class": "PreTrainedTokenizerFast"
2063
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw7.56_4-8bit/README.md DELETED
@@ -1,16 +0,0 @@
1
- # Quantized Model Checkpoint
2
-
3
- **Base model:** meta-llama/Llama-3.1-8B-Instruct
4
-
5
- **Average bitwidth:** 7.5625
6
-
7
- **Sensitivity method:** linear
8
-
9
- **Constraints:**
10
- - max_kl: 0.01
11
-
12
- **Metrics:**
13
- - predicted_kl: 0.009987
14
- - predicted_eap: 0.554600
15
-
16
- See `quantization_config.txt` for full configuration details.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw7.56_4-8bit/chat_template.jinja DELETED
@@ -1,109 +0,0 @@
1
- {{- bos_token }}
2
- {%- if custom_tools is defined %}
3
- {%- set tools = custom_tools %}
4
- {%- endif %}
5
- {%- if not tools_in_user_message is defined %}
6
- {%- set tools_in_user_message = true %}
7
- {%- endif %}
8
- {%- if not date_string is defined %}
9
- {%- set date_string = "26 Jul 2024" %}
10
- {%- endif %}
11
- {%- if not tools is defined %}
12
- {%- set tools = none %}
13
- {%- endif %}
14
-
15
- {#- This block extracts the system message, so we can slot it into the right place. #}
16
- {%- if messages[0]['role'] == 'system' %}
17
- {%- set system_message = messages[0]['content']|trim %}
18
- {%- set messages = messages[1:] %}
19
- {%- else %}
20
- {%- set system_message = "" %}
21
- {%- endif %}
22
-
23
- {#- System message + builtin tools #}
24
- {{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
25
- {%- if builtin_tools is defined or tools is not none %}
26
- {{- "Environment: ipython\n" }}
27
- {%- endif %}
28
- {%- if builtin_tools is defined %}
29
- {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
30
- {%- endif %}
31
- {{- "Cutting Knowledge Date: December 2023\n" }}
32
- {{- "Today Date: " + date_string + "\n\n" }}
33
- {%- if tools is not none and not tools_in_user_message %}
34
- {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
35
- {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
36
- {{- "Do not use variables.\n\n" }}
37
- {%- for t in tools %}
38
- {{- t | tojson(indent=4) }}
39
- {{- "\n\n" }}
40
- {%- endfor %}
41
- {%- endif %}
42
- {{- system_message }}
43
- {{- "<|eot_id|>" }}
44
-
45
- {#- Custom tools are passed in a user message with some extra guidance #}
46
- {%- if tools_in_user_message and not tools is none %}
47
- {#- Extract the first user message so we can plug it in here #}
48
- {%- if messages | length != 0 %}
49
- {%- set first_user_message = messages[0]['content']|trim %}
50
- {%- set messages = messages[1:] %}
51
- {%- else %}
52
- {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
53
- {%- endif %}
54
- {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
55
- {{- "Given the following functions, please respond with a JSON for a function call " }}
56
- {{- "with its proper arguments that best answers the given prompt.\n\n" }}
57
- {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
58
- {{- "Do not use variables.\n\n" }}
59
- {%- for t in tools %}
60
- {{- t | tojson(indent=4) }}
61
- {{- "\n\n" }}
62
- {%- endfor %}
63
- {{- first_user_message + "<|eot_id|>"}}
64
- {%- endif %}
65
-
66
- {%- for message in messages %}
67
- {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
68
- {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
69
- {%- elif 'tool_calls' in message %}
70
- {%- if not message.tool_calls|length == 1 %}
71
- {{- raise_exception("This model only supports single tool-calls at once!") }}
72
- {%- endif %}
73
- {%- set tool_call = message.tool_calls[0].function %}
74
- {%- if builtin_tools is defined and tool_call.name in builtin_tools %}
75
- {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
76
- {{- "<|python_tag|>" + tool_call.name + ".call(" }}
77
- {%- for arg_name, arg_val in tool_call.arguments | items %}
78
- {{- arg_name + '="' + arg_val + '"' }}
79
- {%- if not loop.last %}
80
- {{- ", " }}
81
- {%- endif %}
82
- {%- endfor %}
83
- {{- ")" }}
84
- {%- else %}
85
- {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
86
- {{- '{"name": "' + tool_call.name + '", ' }}
87
- {{- '"parameters": ' }}
88
- {{- tool_call.arguments | tojson }}
89
- {{- "}" }}
90
- {%- endif %}
91
- {%- if builtin_tools is defined %}
92
- {#- This means we're in ipython mode #}
93
- {{- "<|eom_id|>" }}
94
- {%- else %}
95
- {{- "<|eot_id|>" }}
96
- {%- endif %}
97
- {%- elif message.role == "tool" or message.role == "ipython" %}
98
- {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
99
- {%- if message.content is mapping or message.content is iterable %}
100
- {{- message.content | tojson }}
101
- {%- else %}
102
- {{- message.content }}
103
- {%- endif %}
104
- {{- "<|eot_id|>" }}
105
- {%- endif %}
106
- {%- endfor %}
107
- {%- if add_generation_prompt %}
108
- {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
109
- {%- endif %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw7.56_4-8bit/config.json DELETED
@@ -1,39 +0,0 @@
1
- {
2
- "architectures": [
3
- "LlamaForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 128000,
8
- "dtype": "float16",
9
- "eos_token_id": [
10
- 128001,
11
- 128008,
12
- 128009
13
- ],
14
- "head_dim": 128,
15
- "hidden_act": "silu",
16
- "hidden_size": 4096,
17
- "initializer_range": 0.02,
18
- "intermediate_size": 14336,
19
- "max_position_embeddings": 131072,
20
- "mlp_bias": false,
21
- "model_type": "llama",
22
- "num_attention_heads": 32,
23
- "num_hidden_layers": 32,
24
- "num_key_value_heads": 8,
25
- "pretraining_tp": 1,
26
- "rms_norm_eps": 1e-05,
27
- "rope_scaling": {
28
- "factor": 8.0,
29
- "high_freq_factor": 4.0,
30
- "low_freq_factor": 1.0,
31
- "original_max_position_embeddings": 8192,
32
- "rope_type": "llama3"
33
- },
34
- "rope_theta": 500000.0,
35
- "tie_word_embeddings": false,
36
- "transformers_version": "4.57.3",
37
- "use_cache": false,
38
- "vocab_size": 128256
39
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw7.56_4-8bit/generation_config.json DELETED
@@ -1,12 +0,0 @@
1
- {
2
- "bos_token_id": 128000,
3
- "do_sample": true,
4
- "eos_token_id": [
5
- 128001,
6
- 128008,
7
- 128009
8
- ],
9
- "temperature": 0.6,
10
- "top_p": 0.9,
11
- "transformers_version": "4.57.3"
12
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw7.56_4-8bit/model-00001-of-00004.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a5f62139dec457e820c871de03dcf8cd6cb7b3dff4340dd6b4da8e8307e922b
3
- size 4976698592
 
 
 
 
Llama-3.1-8B-Instruct/ll_pred_kl0.01_lin_bw7.56_4-8bit/model-00002-of-00004.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7038b8a751f0563d8e730dee3d8d6a71340f26191fff5aaadc68324c9ed6bb5
3
- size 4999802616