Rijgersberg commited on
Commit
e6a1468
1 Parent(s): 80064d1

Remove checkpoints from main branch

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. checkpoint-1194/config.json +0 -27
  2. checkpoint-1194/generation_config.json +0 -6
  3. checkpoint-1194/model-00001-of-00003.safetensors +0 -3
  4. checkpoint-1194/model-00002-of-00003.safetensors +0 -3
  5. checkpoint-1194/model-00003-of-00003.safetensors +0 -3
  6. checkpoint-1194/model.safetensors.index.json +0 -298
  7. checkpoint-1194/optimizer.pt +0 -3
  8. checkpoint-1194/rng_state_0.pth +0 -3
  9. checkpoint-1194/rng_state_1.pth +0 -3
  10. checkpoint-1194/rng_state_2.pth +0 -3
  11. checkpoint-1194/rng_state_3.pth +0 -3
  12. checkpoint-1194/rng_state_4.pth +0 -3
  13. checkpoint-1194/rng_state_5.pth +0 -3
  14. checkpoint-1194/rng_state_6.pth +0 -3
  15. checkpoint-1194/rng_state_7.pth +0 -3
  16. checkpoint-1194/scheduler.pt +0 -3
  17. checkpoint-1194/special_tokens_map.json +0 -24
  18. checkpoint-1194/tokenizer.model +0 -3
  19. checkpoint-1194/tokenizer_config.json +0 -42
  20. checkpoint-1194/trainer_state.json +0 -0
  21. checkpoint-1194/training_args.bin +0 -3
  22. checkpoint-1592/config.json +0 -27
  23. checkpoint-1592/generation_config.json +0 -6
  24. checkpoint-1592/model-00001-of-00003.safetensors +0 -3
  25. checkpoint-1592/model-00002-of-00003.safetensors +0 -3
  26. checkpoint-1592/model-00003-of-00003.safetensors +0 -3
  27. checkpoint-1592/model.safetensors.index.json +0 -298
  28. checkpoint-1592/optimizer.pt +0 -3
  29. checkpoint-1592/rng_state_0.pth +0 -3
  30. checkpoint-1592/rng_state_1.pth +0 -3
  31. checkpoint-1592/rng_state_2.pth +0 -3
  32. checkpoint-1592/rng_state_3.pth +0 -3
  33. checkpoint-1592/rng_state_4.pth +0 -3
  34. checkpoint-1592/rng_state_5.pth +0 -3
  35. checkpoint-1592/rng_state_6.pth +0 -3
  36. checkpoint-1592/rng_state_7.pth +0 -3
  37. checkpoint-1592/scheduler.pt +0 -3
  38. checkpoint-1592/special_tokens_map.json +0 -24
  39. checkpoint-1592/tokenizer.model +0 -3
  40. checkpoint-1592/tokenizer_config.json +0 -42
  41. checkpoint-1592/trainer_state.json +0 -0
  42. checkpoint-1592/training_args.bin +0 -3
  43. checkpoint-1990/config.json +0 -27
  44. checkpoint-1990/generation_config.json +0 -6
  45. checkpoint-1990/model-00001-of-00003.safetensors +0 -3
  46. checkpoint-1990/model-00002-of-00003.safetensors +0 -3
  47. checkpoint-1990/model-00003-of-00003.safetensors +0 -3
  48. checkpoint-1990/model.safetensors.index.json +0 -298
  49. checkpoint-1990/optimizer.pt +0 -3
  50. checkpoint-1990/rng_state_0.pth +0 -3
checkpoint-1194/config.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "_name_or_path": "mistralai/Mistral-7B-v0.1",
3
- "architectures": [
4
- "MistralForCausalLM"
5
- ],
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 1,
8
- "eos_token_id": 2,
9
- "hidden_act": "silu",
10
- "hidden_size": 4096,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 14336,
13
- "max_position_embeddings": 32768,
14
- "model_type": "mistral",
15
- "num_attention_heads": 32,
16
- "num_hidden_layers": 32,
17
- "num_key_value_heads": 8,
18
- "pad_token_id": 2,
19
- "rms_norm_eps": 1e-05,
20
- "rope_theta": 10000.0,
21
- "sliding_window": 4096,
22
- "tie_word_embeddings": false,
23
- "torch_dtype": "bfloat16",
24
- "transformers_version": "4.36.0.dev0",
25
- "use_cache": true,
26
- "vocab_size": 32000
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1194/generation_config.json DELETED
@@ -1,6 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 1,
4
- "eos_token_id": 2,
5
- "transformers_version": "4.36.0.dev0"
6
- }
 
 
 
 
 
 
 
checkpoint-1194/model-00001-of-00003.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc967d7e09b24a15c159e3264fe80ef0ba1a91a815c33fb63e4f3294746b6c4b
3
- size 4943162336
 
 
 
 
checkpoint-1194/model-00002-of-00003.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a65f5f213c5d7467d89f5edd8350724f7fcba5488e963a4edb2075753807921
3
- size 4999819336
 
 
 
 
checkpoint-1194/model-00003-of-00003.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0128d7fe33e0f04806fcd8528853961f3a5337c8a4279fd12d83ac0abb917ea
3
- size 4540516344
 
 
 
 
checkpoint-1194/model.safetensors.index.json DELETED
@@ -1,298 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 14483464192
4
- },
5
- "weight_map": {
6
- "lm_head.weight": "model-00003-of-00003.safetensors",
7
- "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
- "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
- "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
- "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
27
- "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
28
- "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
- "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
- "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
31
- "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
- "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
- "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
- "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
- "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
36
- "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
37
- "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
38
- "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
39
- "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
40
- "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
41
- "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
42
- "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
43
- "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
44
- "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
- "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
- "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
47
- "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
48
- "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
- "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
- "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
51
- "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
52
- "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
53
- "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
- "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
- "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
- "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
- "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
- "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
- "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
- "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
- "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
- "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
- "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
- "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
- "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
- "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
- "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
- "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
- "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
- "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
- "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
- "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
- "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
- "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
- "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
- "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
- "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
- "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
- "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
- "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
- "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
- "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
- "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
- "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
- "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
- "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
- "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
- "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
- "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
- "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
- "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
- "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
- "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
- "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
- "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
- "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
- "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
- "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
- "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
- "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
- "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
- "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
- "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
- "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
- "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
- "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
- "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
- "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
- "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
- "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
- "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
- "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
- "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
- "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
- "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
- "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
- "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
- "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
- "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
- "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
- "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
- "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
- "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
- "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
- "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
- "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
- "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
- "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
- "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
- "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
- "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
- "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
- "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
- "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
- "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
144
- "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
145
- "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
146
- "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
147
- "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
148
- "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
- "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
- "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
- "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
- "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
153
- "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
154
- "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
155
- "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
156
- "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
157
- "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
158
- "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
159
- "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
160
- "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
161
- "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
162
- "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
163
- "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
164
- "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
165
- "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
166
- "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
167
- "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
168
- "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
169
- "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
170
- "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
171
- "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
172
- "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
173
- "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
174
- "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
175
- "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
176
- "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
177
- "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
178
- "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
179
- "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
180
- "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
181
- "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
182
- "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
183
- "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
184
- "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
185
- "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
186
- "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
187
- "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
188
- "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
- "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
- "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
- "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
- "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
- "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
- "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
- "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
196
- "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
197
- "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
198
- "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
199
- "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
200
- "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
201
- "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
202
- "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
203
- "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
204
- "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
205
- "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
206
- "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
207
- "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
208
- "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
209
- "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
210
- "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
211
- "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
212
- "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
213
- "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
214
- "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
215
- "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
- "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
- "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
- "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
227
- "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
228
- "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
- "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
- "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
231
- "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
232
- "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
233
- "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
- "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
- "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
- "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
- "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
- "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
- "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
- "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
- "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
- "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
243
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
244
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
246
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
247
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
- "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
252
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
253
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
254
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
256
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
257
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
258
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
259
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
- "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
261
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
262
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
263
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
264
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
265
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
266
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
267
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
268
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
269
- "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
270
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
271
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
272
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
273
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
274
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
275
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
276
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
277
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
278
- "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
279
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
280
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
281
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
282
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
283
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
284
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
285
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
286
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
287
- "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
288
- "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
289
- "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
290
- "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
291
- "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
292
- "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
293
- "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
294
- "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
295
- "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
296
- "model.norm.weight": "model-00003-of-00003.safetensors"
297
- }
298
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1194/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:644622e35f12e4499dc102cca00cd0c59800c73c5549380781cfe2ec48c565cc
3
- size 14512103560
 
 
 
 
checkpoint-1194/rng_state_0.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7d7e02ffb4d440dce7ab4ce0b5617578ec9ce3672acee7434ed6f1153f1ae0c
3
- size 15984
 
 
 
 
checkpoint-1194/rng_state_1.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5b40ca759e432b2688f021b81291d74a40f56a205e9842119f7e772275eebd3
3
- size 15984
 
 
 
 
checkpoint-1194/rng_state_2.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:cdaef955ddd36d6bc1c40584113dd6205483e2aa85b02439b8b27e82e02a8359
3
- size 15984
 
 
 
 
checkpoint-1194/rng_state_3.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:10b14ae5db356e6512538751d6b386c190754e307cc99cd652d5c6dd891e1f82
3
- size 15984
 
 
 
 
checkpoint-1194/rng_state_4.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f26e28be26826eeeed244b77185c67b443ac185175f8d4bf5ba94caa8b271bc5
3
- size 15984
 
 
 
 
checkpoint-1194/rng_state_5.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:847cedc1d6ca26f299a132c2ade9754887374acb9d98f26594a85d4c7742d474
3
- size 15984
 
 
 
 
checkpoint-1194/rng_state_6.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bcd043d1690ae0ff6991b03322799a0b28f021427b15fd9f1e5ed8b9905d9307
3
- size 15984
 
 
 
 
checkpoint-1194/rng_state_7.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:772190f7e6667c865d25fc72da7bdd1b5d39f46fe03bb5c2d754aee1ad3c99c7
3
- size 15984
 
 
 
 
checkpoint-1194/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:16a7c4866f6e6ad2649c5b44240e22849a3ac060771cdd807355f8b2b5d00479
3
- size 1064
 
 
 
 
checkpoint-1194/special_tokens_map.json DELETED
@@ -1,24 +0,0 @@
1
- {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "</s>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": "</s>",
17
- "unk_token": {
18
- "content": "<unk>",
19
- "lstrip": false,
20
- "normalized": false,
21
- "rstrip": false,
22
- "single_word": false
23
- }
24
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1194/tokenizer.model DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
- size 493443
 
 
 
 
checkpoint-1194/tokenizer_config.json DELETED
@@ -1,42 +0,0 @@
1
- {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
- "added_tokens_decoder": {
5
- "0": {
6
- "content": "<unk>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "1": {
14
- "content": "<s>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "2": {
22
- "content": "</s>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- }
29
- },
30
- "additional_special_tokens": [],
31
- "bos_token": "<s>",
32
- "clean_up_tokenization_spaces": false,
33
- "eos_token": "</s>",
34
- "legacy": true,
35
- "model_max_length": 1000000000000000019884624838656,
36
- "pad_token": "</s>",
37
- "sp_model_kwargs": {},
38
- "spaces_between_special_tokens": false,
39
- "tokenizer_class": "LlamaTokenizer",
40
- "unk_token": "<unk>",
41
- "use_default_system_prompt": true
42
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1194/trainer_state.json DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-1194/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4651a93cc01565784d01cabcc25e18b1250dbe9aba2246e9cf4e96cb779c6cdf
3
- size 4728
 
 
 
 
checkpoint-1592/config.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "_name_or_path": "mistralai/Mistral-7B-v0.1",
3
- "architectures": [
4
- "MistralForCausalLM"
5
- ],
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 1,
8
- "eos_token_id": 2,
9
- "hidden_act": "silu",
10
- "hidden_size": 4096,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 14336,
13
- "max_position_embeddings": 32768,
14
- "model_type": "mistral",
15
- "num_attention_heads": 32,
16
- "num_hidden_layers": 32,
17
- "num_key_value_heads": 8,
18
- "pad_token_id": 2,
19
- "rms_norm_eps": 1e-05,
20
- "rope_theta": 10000.0,
21
- "sliding_window": 4096,
22
- "tie_word_embeddings": false,
23
- "torch_dtype": "bfloat16",
24
- "transformers_version": "4.36.0.dev0",
25
- "use_cache": true,
26
- "vocab_size": 32000
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1592/generation_config.json DELETED
@@ -1,6 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 1,
4
- "eos_token_id": 2,
5
- "transformers_version": "4.36.0.dev0"
6
- }
 
 
 
 
 
 
 
checkpoint-1592/model-00001-of-00003.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e0c1d973fe8dba8837f33ed095c8dc417e036ccb5aebcf451a07726d1ddea265
3
- size 4943162336
 
 
 
 
checkpoint-1592/model-00002-of-00003.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e1efcdff5db880e764ca41478454352cdd5aad9171929c54d9c46e398f637a4
3
- size 4999819336
 
 
 
 
checkpoint-1592/model-00003-of-00003.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4ec182fe95fb7e0f61fb9618b764e9c51ebb557fe2aa5ada24ed528354e4bf0
3
- size 4540516344
 
 
 
 
checkpoint-1592/model.safetensors.index.json DELETED
@@ -1,298 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 14483464192
4
- },
5
- "weight_map": {
6
- "lm_head.weight": "model-00003-of-00003.safetensors",
7
- "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
- "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
- "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
- "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
27
- "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
28
- "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
- "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
- "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
31
- "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
- "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
- "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
- "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
- "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
36
- "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
37
- "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
38
- "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
39
- "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
40
- "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
41
- "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
42
- "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
43
- "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
44
- "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
- "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
- "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
47
- "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
48
- "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
- "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
- "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
51
- "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
52
- "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
53
- "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
- "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
- "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
- "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
- "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
- "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
- "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
- "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
- "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
- "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
- "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
- "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
- "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
- "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
- "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
- "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
- "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
- "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
- "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
- "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
- "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
- "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
- "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
- "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
- "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
- "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
- "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
- "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
- "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
- "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
- "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
- "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
- "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
- "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
- "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
- "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
- "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
- "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
- "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
- "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
- "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
- "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
- "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
- "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
- "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
- "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
- "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
- "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
- "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
- "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
- "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
- "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
- "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
- "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
- "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
- "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
- "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
- "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
- "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
- "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
- "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
- "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
- "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
- "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
- "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
- "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
- "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
- "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
- "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
- "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
- "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
- "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
- "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
- "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
- "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
- "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
- "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
- "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
- "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
- "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
- "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
- "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
- "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
144
- "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
145
- "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
146
- "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
147
- "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
148
- "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
- "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
- "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
- "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
- "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
153
- "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
154
- "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
155
- "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
156
- "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
157
- "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
158
- "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
159
- "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
160
- "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
161
- "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
162
- "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
163
- "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
164
- "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
165
- "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
166
- "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
167
- "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
168
- "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
169
- "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
170
- "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
171
- "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
172
- "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
173
- "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
174
- "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
175
- "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
176
- "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
177
- "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
178
- "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
179
- "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
180
- "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
181
- "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
182
- "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
183
- "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
184
- "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
185
- "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
186
- "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
187
- "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
188
- "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
- "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
- "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
- "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
- "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
- "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
- "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
- "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
196
- "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
197
- "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
198
- "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
199
- "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
200
- "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
201
- "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
202
- "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
203
- "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
204
- "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
205
- "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
206
- "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
207
- "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
208
- "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
209
- "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
210
- "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
211
- "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
212
- "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
213
- "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
214
- "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
215
- "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
- "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
- "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
- "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
227
- "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
228
- "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
- "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
- "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
231
- "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
232
- "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
233
- "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
- "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
- "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
- "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
- "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
- "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
- "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
- "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
- "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
- "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
243
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
244
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
246
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
247
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
- "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
252
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
253
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
254
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
256
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
257
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
258
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
259
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
- "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
261
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
262
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
263
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
264
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
265
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
266
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
267
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
268
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
269
- "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
270
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
271
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
272
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
273
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
274
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
275
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
276
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
277
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
278
- "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
279
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
280
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
281
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
282
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
283
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
284
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
285
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
286
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
287
- "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
288
- "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
289
- "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
290
- "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
291
- "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
292
- "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
293
- "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
294
- "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
295
- "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
296
- "model.norm.weight": "model-00003-of-00003.safetensors"
297
- }
298
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1592/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:39e3f9dbe5ebdc37fcd897a04a4bda7e33a062516f4ab1c7b5fbc08d8bdc4268
3
- size 14512103560
 
 
 
 
checkpoint-1592/rng_state_0.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae9162e03c562553a5d9d13120f544d3c47ea71bb39aa44e18253675e17ed4a4
3
- size 15984
 
 
 
 
checkpoint-1592/rng_state_1.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4809456871b3a40c8db7e0926a9db11b01149a1d483fb29b16fc69dabaf36c6f
3
- size 15984
 
 
 
 
checkpoint-1592/rng_state_2.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4bb6bcf25ff148b74eea7dd4895fc42e9433538fff5d75f0d2ae6cb0c2fdadf0
3
- size 15984
 
 
 
 
checkpoint-1592/rng_state_3.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f00ea04cd1a52c539d9cc948ac8a04676d6b99702acd09149565f781806f63f
3
- size 15984
 
 
 
 
checkpoint-1592/rng_state_4.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5571fb2fc1b413792b01ac691c759786855573992bab1d14875faccdaf8c881e
3
- size 15984
 
 
 
 
checkpoint-1592/rng_state_5.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:59019ba23ead9c15851cb4349397254458ce50ea3c2987090404f4f3842c6d8f
3
- size 15984
 
 
 
 
checkpoint-1592/rng_state_6.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:45fdffda57fda4a555da7a5de6fc6ec7324e0dae048b92519af6c4f6a1bc7412
3
- size 15984
 
 
 
 
checkpoint-1592/rng_state_7.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:62fb2c13e63aba83c4505fae1639f79a33853d8f1bebe20cecb73bf53c8e7c46
3
- size 15984
 
 
 
 
checkpoint-1592/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:eaeee36e9e32f47a8103c0282165dc979b2e4bb1e85781ded54e0c018f34feb4
3
- size 1064
 
 
 
 
checkpoint-1592/special_tokens_map.json DELETED
@@ -1,24 +0,0 @@
1
- {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "</s>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": "</s>",
17
- "unk_token": {
18
- "content": "<unk>",
19
- "lstrip": false,
20
- "normalized": false,
21
- "rstrip": false,
22
- "single_word": false
23
- }
24
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1592/tokenizer.model DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
- size 493443
 
 
 
 
checkpoint-1592/tokenizer_config.json DELETED
@@ -1,42 +0,0 @@
1
- {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
- "added_tokens_decoder": {
5
- "0": {
6
- "content": "<unk>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "1": {
14
- "content": "<s>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "2": {
22
- "content": "</s>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- }
29
- },
30
- "additional_special_tokens": [],
31
- "bos_token": "<s>",
32
- "clean_up_tokenization_spaces": false,
33
- "eos_token": "</s>",
34
- "legacy": true,
35
- "model_max_length": 1000000000000000019884624838656,
36
- "pad_token": "</s>",
37
- "sp_model_kwargs": {},
38
- "spaces_between_special_tokens": false,
39
- "tokenizer_class": "LlamaTokenizer",
40
- "unk_token": "<unk>",
41
- "use_default_system_prompt": true
42
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1592/trainer_state.json DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-1592/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4651a93cc01565784d01cabcc25e18b1250dbe9aba2246e9cf4e96cb779c6cdf
3
- size 4728
 
 
 
 
checkpoint-1990/config.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "_name_or_path": "mistralai/Mistral-7B-v0.1",
3
- "architectures": [
4
- "MistralForCausalLM"
5
- ],
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 1,
8
- "eos_token_id": 2,
9
- "hidden_act": "silu",
10
- "hidden_size": 4096,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 14336,
13
- "max_position_embeddings": 32768,
14
- "model_type": "mistral",
15
- "num_attention_heads": 32,
16
- "num_hidden_layers": 32,
17
- "num_key_value_heads": 8,
18
- "pad_token_id": 2,
19
- "rms_norm_eps": 1e-05,
20
- "rope_theta": 10000.0,
21
- "sliding_window": 4096,
22
- "tie_word_embeddings": false,
23
- "torch_dtype": "bfloat16",
24
- "transformers_version": "4.36.0.dev0",
25
- "use_cache": true,
26
- "vocab_size": 32000
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1990/generation_config.json DELETED
@@ -1,6 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 1,
4
- "eos_token_id": 2,
5
- "transformers_version": "4.36.0.dev0"
6
- }
 
 
 
 
 
 
 
checkpoint-1990/model-00001-of-00003.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:459ec1bc27bd2b3523fe4d6ed83f52f26c43ad0738443f101eb4bb8163c42d16
3
- size 4943162336
 
 
 
 
checkpoint-1990/model-00002-of-00003.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a103645169a2888431a264ed95bb680b4fb2a216102093240643cdb341e6096
3
- size 4999819336
 
 
 
 
checkpoint-1990/model-00003-of-00003.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:28375d257d9c63152ee1f03fda716112e2eabfad1ab554db01818e323a8588df
3
- size 4540516344
 
 
 
 
checkpoint-1990/model.safetensors.index.json DELETED
@@ -1,298 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 14483464192
4
- },
5
- "weight_map": {
6
- "lm_head.weight": "model-00003-of-00003.safetensors",
7
- "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
- "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
- "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
- "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
27
- "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
28
- "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
- "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
- "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
31
- "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
- "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
- "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
- "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
- "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
36
- "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
37
- "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
38
- "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
39
- "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
40
- "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
41
- "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
42
- "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
43
- "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
44
- "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
- "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
- "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
47
- "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
48
- "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
- "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
- "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
51
- "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
52
- "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
53
- "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
- "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
- "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
- "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
- "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
- "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
- "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
- "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
- "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
- "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
- "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
- "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
- "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
- "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
- "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
- "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
- "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
- "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
- "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
- "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
- "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
- "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
- "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
- "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
- "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
- "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
- "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
- "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
- "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
- "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
- "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
- "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
- "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
- "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
- "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
- "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
- "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
- "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
- "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
- "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
- "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
- "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
- "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
- "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
- "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
- "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
- "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
- "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
- "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
- "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
- "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
- "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
- "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
- "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
- "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
- "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
- "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
- "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
- "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
- "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
- "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
- "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
- "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
- "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
- "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
- "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
- "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
- "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
- "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
- "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
- "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
- "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
- "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
- "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
- "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
- "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
- "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
- "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
- "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
- "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
- "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
- "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
- "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
144
- "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
145
- "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
146
- "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
147
- "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
148
- "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
- "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
- "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
- "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
- "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
153
- "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
154
- "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
155
- "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
156
- "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
157
- "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
158
- "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
159
- "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
160
- "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
161
- "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
162
- "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
163
- "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
164
- "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
165
- "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
166
- "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
167
- "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
168
- "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
169
- "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
170
- "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
171
- "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
172
- "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
173
- "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
174
- "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
175
- "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
176
- "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
177
- "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
178
- "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
179
- "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
180
- "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
181
- "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
182
- "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
183
- "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
184
- "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
185
- "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
186
- "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
187
- "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
188
- "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
- "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
- "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
- "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
- "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
- "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
- "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
- "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
196
- "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
197
- "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
198
- "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
199
- "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
200
- "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
201
- "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
202
- "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
203
- "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
204
- "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
205
- "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
206
- "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
207
- "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
208
- "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
209
- "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
210
- "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
211
- "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
212
- "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
213
- "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
214
- "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
215
- "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
- "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
- "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
- "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
227
- "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
228
- "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
- "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
- "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
231
- "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
232
- "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
233
- "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
- "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
- "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
- "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
- "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
- "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
- "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
- "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
- "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
- "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
243
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
244
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
246
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
247
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
- "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
252
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
253
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
254
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
256
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
257
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
258
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
259
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
- "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
261
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
262
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
263
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
264
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
265
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
266
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
267
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
268
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
269
- "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
270
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
271
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
272
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
273
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
274
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
275
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
276
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
277
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
278
- "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
279
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
280
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
281
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
282
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
283
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
284
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
285
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
286
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
287
- "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
288
- "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
289
- "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
290
- "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
291
- "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
292
- "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
293
- "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
294
- "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
295
- "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
296
- "model.norm.weight": "model-00003-of-00003.safetensors"
297
- }
298
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1990/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0896ac95a388f9ba5c5ef6bcab656f87d3dd7af963f982d8668122bdd8e9d4c1
3
- size 14512103560
 
 
 
 
checkpoint-1990/rng_state_0.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba4c26c615bd5830d41566fab54dc69174be292761b34514b27fbe82b45b630b
3
- size 15984