aaabiao commited on
Commit
c19f29d
·
verified ·
1 Parent(s): 3811428

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151643,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 17408,
14
+ "max_position_embeddings": 32768,
15
+ "max_window_layers": 40,
16
+ "model_type": "qwen3",
17
+ "num_attention_heads": 40,
18
+ "num_hidden_layers": 40,
19
+ "num_key_value_heads": 8,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "rope_theta": 1000000,
23
+ "sliding_window": null,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.51.0",
27
+ "use_cache": false,
28
+ "use_sliding_window": false,
29
+ "vocab_size": 151936
30
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "4.51.0"
6
+ }
latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step450
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5490ccb2908b34881fe724ed2bc57bc234b63e27f5fa5caf270a65813f4b9179
3
+ size 4984780784
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d048257a7103ccfec243745b30b2d3485de741af7024371b9b5d1b27a915f6c1
3
+ size 4980892048
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:185b7846df9c2a75dab346fd407338e8f8202f62397c7df7d6e2b51842131b46
3
+ size 4928485104
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8830df26ac86c0414b94c093fb94368ad4fb6d4bb591537ac622d9948f284ec
3
+ size 4980892112
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42c7f7383d0988b8a65e88a24864423f5b6ab53d51c3222a7318b80ff036a61f
3
+ size 4928485104
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abbb2a5e8ee90bb269a6f76567efb29b4452c006224acca6373b787e60d9626f
3
+ size 4733130504
model.safetensors.index.json ADDED
@@ -0,0 +1,450 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 29536614400
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00006-of-00006.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
13
+ "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
16
+ "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
18
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
19
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
20
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
21
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
22
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
23
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
24
+ "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
25
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
26
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
27
+ "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
28
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
29
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
30
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
31
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
32
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
33
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
34
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
35
+ "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
36
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
37
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
38
+ "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
39
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
40
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
41
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
42
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
43
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
44
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
45
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
46
+ "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
47
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
48
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
49
+ "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
50
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
51
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
52
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
53
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
54
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
55
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
56
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
57
+ "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
58
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
59
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
60
+ "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
61
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
62
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
63
+ "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
64
+ "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
65
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
66
+ "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
67
+ "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
68
+ "model.layers.13.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
69
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
70
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
71
+ "model.layers.13.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
72
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
73
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
74
+ "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
75
+ "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
76
+ "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
77
+ "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
78
+ "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
79
+ "model.layers.14.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
80
+ "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
81
+ "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
82
+ "model.layers.14.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
83
+ "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
84
+ "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
85
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
86
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
87
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
88
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
89
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
90
+ "model.layers.15.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
91
+ "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
92
+ "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
93
+ "model.layers.15.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
94
+ "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
95
+ "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
96
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
97
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
98
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
99
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
100
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
101
+ "model.layers.16.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
102
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
103
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
104
+ "model.layers.16.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
105
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
106
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
107
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
108
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
109
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
110
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
111
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
112
+ "model.layers.17.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
113
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
114
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
115
+ "model.layers.17.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
116
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
117
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
118
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
119
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
120
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
121
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
122
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
123
+ "model.layers.18.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
124
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
125
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
126
+ "model.layers.18.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
127
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
128
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
129
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
130
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
131
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
132
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
133
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
134
+ "model.layers.19.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
135
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
136
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
137
+ "model.layers.19.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
138
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
139
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
140
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
141
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
142
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
143
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
144
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
145
+ "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
146
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
147
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
148
+ "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
149
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
150
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
151
+ "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
152
+ "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
153
+ "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
154
+ "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
155
+ "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
156
+ "model.layers.20.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
157
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
158
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
159
+ "model.layers.20.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
160
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
161
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
162
+ "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
163
+ "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
164
+ "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
165
+ "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
166
+ "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
167
+ "model.layers.21.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
168
+ "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
169
+ "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
170
+ "model.layers.21.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
171
+ "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
172
+ "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
173
+ "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
174
+ "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
175
+ "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
176
+ "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
177
+ "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
178
+ "model.layers.22.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
179
+ "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
180
+ "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
181
+ "model.layers.22.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
182
+ "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
183
+ "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
184
+ "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
185
+ "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
186
+ "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
187
+ "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
188
+ "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
189
+ "model.layers.23.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
190
+ "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
191
+ "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
192
+ "model.layers.23.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
193
+ "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
194
+ "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
195
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
196
+ "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
197
+ "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
198
+ "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
199
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
200
+ "model.layers.24.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
201
+ "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
202
+ "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
203
+ "model.layers.24.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
204
+ "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
205
+ "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
206
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
207
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
208
+ "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
209
+ "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
210
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
211
+ "model.layers.25.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
212
+ "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
213
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
214
+ "model.layers.25.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
215
+ "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
216
+ "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
217
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
218
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
219
+ "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
220
+ "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
221
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
222
+ "model.layers.26.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
223
+ "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
224
+ "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
225
+ "model.layers.26.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
226
+ "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
227
+ "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
228
+ "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
229
+ "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
230
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
231
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
232
+ "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
233
+ "model.layers.27.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
234
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
235
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
236
+ "model.layers.27.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
237
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
238
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
239
+ "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
240
+ "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
241
+ "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
242
+ "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
243
+ "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
244
+ "model.layers.28.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
245
+ "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
246
+ "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
247
+ "model.layers.28.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
248
+ "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
249
+ "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
250
+ "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
251
+ "model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
252
+ "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
253
+ "model.layers.29.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
254
+ "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
255
+ "model.layers.29.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
256
+ "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
257
+ "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
258
+ "model.layers.29.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
259
+ "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
260
+ "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
266
+ "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
269
+ "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
272
+ "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
273
+ "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
274
+ "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
275
+ "model.layers.30.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
276
+ "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
277
+ "model.layers.30.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
278
+ "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
279
+ "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
280
+ "model.layers.30.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
281
+ "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
282
+ "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
283
+ "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
284
+ "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
285
+ "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
286
+ "model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
287
+ "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
288
+ "model.layers.31.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
289
+ "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
290
+ "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
291
+ "model.layers.31.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
292
+ "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
293
+ "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
294
+ "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
295
+ "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
296
+ "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
297
+ "model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
298
+ "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
299
+ "model.layers.32.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
300
+ "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
301
+ "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
302
+ "model.layers.32.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
303
+ "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
304
+ "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
305
+ "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
306
+ "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
307
+ "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
308
+ "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
309
+ "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
310
+ "model.layers.33.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
311
+ "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
312
+ "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
313
+ "model.layers.33.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
314
+ "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
315
+ "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
316
+ "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
317
+ "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
318
+ "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
319
+ "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
320
+ "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
321
+ "model.layers.34.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
322
+ "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
323
+ "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
324
+ "model.layers.34.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
325
+ "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
326
+ "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
327
+ "model.layers.35.input_layernorm.weight": "model-00006-of-00006.safetensors",
328
+ "model.layers.35.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
329
+ "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
330
+ "model.layers.35.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
331
+ "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
332
+ "model.layers.35.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
333
+ "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
334
+ "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
335
+ "model.layers.35.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
336
+ "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
337
+ "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
338
+ "model.layers.36.input_layernorm.weight": "model-00006-of-00006.safetensors",
339
+ "model.layers.36.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
340
+ "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
341
+ "model.layers.36.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
342
+ "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
343
+ "model.layers.36.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
344
+ "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
345
+ "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
346
+ "model.layers.36.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
347
+ "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
348
+ "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
349
+ "model.layers.37.input_layernorm.weight": "model-00006-of-00006.safetensors",
350
+ "model.layers.37.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
351
+ "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
352
+ "model.layers.37.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
353
+ "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
354
+ "model.layers.37.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
355
+ "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
356
+ "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
357
+ "model.layers.37.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
358
+ "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
359
+ "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
360
+ "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
361
+ "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
362
+ "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
363
+ "model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
364
+ "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
365
+ "model.layers.38.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
366
+ "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
367
+ "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
368
+ "model.layers.38.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
369
+ "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
370
+ "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
371
+ "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
372
+ "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
373
+ "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
374
+ "model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
375
+ "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
376
+ "model.layers.39.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
377
+ "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
378
+ "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
379
+ "model.layers.39.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
380
+ "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
381
+ "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
382
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
383
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
384
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
385
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
386
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
387
+ "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
388
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
389
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
390
+ "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
391
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
392
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
393
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
394
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
395
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
396
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
397
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
398
+ "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
399
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
400
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
401
+ "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
402
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
403
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
404
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
405
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
406
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
407
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
408
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
409
+ "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
410
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
411
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
412
+ "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
413
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
414
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
415
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
416
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
417
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
418
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
419
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
420
+ "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
421
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
422
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
423
+ "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
424
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
425
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
426
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
427
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
428
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
429
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
430
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
431
+ "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
432
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
433
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
434
+ "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
435
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
436
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
437
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
438
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
439
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
440
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
441
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
442
+ "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
443
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
444
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
445
+ "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
446
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
447
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
448
+ "model.norm.weight": "model-00006-of-00006.safetensors"
449
+ }
450
+ }
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad8a35afd8967cbb748405387e44426e43ad127028e826eddc9b67d2ca873c85
3
+ size 15984
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f338ce80d7c441076bfc8c53b84067a0181f5a14e80c13d5acb8150b659f4d73
3
+ size 15984
rng_state_10.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d4c67c1d0ec6b889370f634ff29f584f829acaeaf69196a69304fdba936f9d7
3
+ size 15997
rng_state_11.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afd0c4e2ac5f61d5f4df5d9d5783018b7937173b4afdbb92816c2668982cb351
3
+ size 15997
rng_state_12.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9d1c7f561c5512193e8053ecf371e4fef647a8503481f2dad76332ddbe164fd
3
+ size 15997
rng_state_13.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7604a3cfaf0e3c3f2aa2b3547660615db82205d4158951bb90f69ffc560ed179
3
+ size 15997
rng_state_14.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d984186a3bc06445d6c077fcbf64da96d47d3ed704e68f0212045efb4b91dbb
3
+ size 15997
rng_state_15.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b3945ba3535361fa13a8460a70ebbd44ece2514a1c9dcb76abfe6f54a775c60
3
+ size 15997
rng_state_16.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:853a02543fd3223edd9334ea75c62e6e99ded22ac864e9930fbf5add26045fe7
3
+ size 15997
rng_state_17.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c0420ad6cf62c9fe9cda1807f68e8e40235a8917dbab858f800d24e3ba8eeae
3
+ size 15997
rng_state_18.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e167524b369e20a3a17ee7f6124322da680ccf2ae553b4adc0e7462d2dfba82b
3
+ size 15997
rng_state_19.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0915a78eba7c1d2768ecd03818e3c01afd7f3168a3318b1212413bd2c62f7f1
3
+ size 15997
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9fbc9fa428939be10b46779f0eb5cd833e0da426b1cbdee77b3a55b6952235b
3
+ size 15984
rng_state_20.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f8f2fdb90584ebb7247c85570082ac7c6338216de82b07f132a2c679923379a
3
+ size 15997
rng_state_21.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a3863ac6512e946a826d479520004385d29f3fd0a2b686ccbfdf488332aa442
3
+ size 15997
rng_state_22.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dfe94fb47194a2a298bed1b33ad18c2132747148814886bd9b8910a7691ba0b
3
+ size 15997
rng_state_23.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c683c09c8883037948fabb143cd972207db3cee22d7efcbcc5866a8ec85c94c6
3
+ size 15997
rng_state_24.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53c201c89debf1ca694786330ea98ca69da6340ac3b70f40aad77213d1771bf8
3
+ size 15997
rng_state_25.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7b8393dc10fb6ab2222179b268184fa5330fd417b66ebb65986818f47334a55
3
+ size 15997
rng_state_26.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b29094f6dcc92be7d58da39df551c573728836c5aec67bef90790810c0d3882
3
+ size 15997
rng_state_27.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b64ff98dfb30bbfa08760a0a79d9be7407917ff0e32f22b03d6528bf7e292e44
3
+ size 15997
rng_state_28.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04e19d4d07b899c9158590672b9acc125c3fb4082f5aed08ddaee573b4dbf33f
3
+ size 15997
rng_state_29.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47a620c2380d984b51262d8f8d1853631c1bd13c3da4ea8f73e8dc61dd3fb765
3
+ size 15997
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac55dba0b79d5fa4699d239da2f966d52040d576d31234ac8d4632e6956481bc
3
+ size 15984
rng_state_30.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1516e58b9c7537b0c41d41487bc1464770e53c3dabdb8cf4f5c07bcc51e07ed6
3
+ size 15997
rng_state_31.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58a50bef57066132c2e5b6b53fbb78e101505dd4ad585ec52fb3c11ca0663c22
3
+ size 15997
rng_state_32.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99a4c2a689f049aacd781b605116236e53b34a5922e8d04fbbe55133723c868f
3
+ size 15997
rng_state_33.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bf7e8473da86eef154ee31aa509c2f0c2f07585beb625194175cd6444e1fd66
3
+ size 15997
rng_state_34.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:834e8e4e3c2361b4d81f93438d54b746324fcbce4cfd8f9790e8bc796005e755
3
+ size 15997
rng_state_35.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7c37da1122cac643753c818052f274aac1cbd61149faea91d9e7a2128dcf7b7
3
+ size 15997
rng_state_36.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4024775fc0ac931abdc456008f08b687f4c431742d3d88982553c2cf92eaafe
3
+ size 15997
rng_state_37.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e15b08dd40e9c11eb1df2988986c8dc1fa21e45210e8f047caea420e1e95879
3
+ size 15997
rng_state_38.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eae0a9bd1151c39106890b996fd767e0569650a669126b6513dbbf0513900d10
3
+ size 15997
rng_state_39.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eee9728cafa59eb03f2f87509fb15ebb9a699c945c31d6a69b8c98f3b734e6ae
3
+ size 15997
rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af2d0c015100768ffa23faf3b6c2d54ea89eb045603e30e55cd211e06ff34972
3
+ size 15984
rng_state_40.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d72fd9062ec1657a02320be4ea8b65cdb5e813168fea79c16e7c18b96cf40685
3
+ size 15997
rng_state_41.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdff7110ce8b7a50a8081c524dfef45063fa0a2372f8ffc5dfbc36319331712e
3
+ size 15997