Hugging Face's logo

Maani
/
PXZNNO

Text Generation
Transformers
Safetensors
lfm2
conversational
Model card Files
xet
Community
1
Maani commited on
Commit
6772e51
·
verified ·
1 Parent(s): f791355

Upload Lfm2ForCausalLM

Browse files
Files changed (5) hide show
  1. config.json +66 -32
  2. generation_config.json +4 -8
  3. model-00001-of-00002.safetensors +2 -2
  4. model-00002-of-00002.safetensors +2 -2
  5. model.safetensors.index.json +253 -241
config.json CHANGED
@@ -1,39 +1,73 @@
1
  {
2
  "architectures": [
3
- "LlamaForCausalLM"
4
  ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 128000,
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  "dtype": "bfloat16",
9
- "eos_token_id": [
10
- 128001,
11
- 128008,
12
- 128009
13
- ],
14
- "head_dim": 128,
15
- "hidden_act": "silu",
16
- "hidden_size": 3072,
17
  "initializer_range": 0.02,
18
- "intermediate_size": 8192,
19
- "max_position_embeddings": 131072,
20
- "mlp_bias": false,
21
- "model_type": "llama",
22
- "num_attention_heads": 24,
23
- "num_hidden_layers": 28,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
24
  "num_key_value_heads": 8,
25
- "pretraining_tp": 1,
26
- "rms_norm_eps": 1e-05,
27
- "rope_scaling": {
28
- "factor": 32.0,
29
- "high_freq_factor": 4.0,
30
- "low_freq_factor": 1.0,
31
- "original_max_position_embeddings": 8192,
32
- "rope_type": "llama3"
33
- },
34
- "rope_theta": 500000.0,
35
- "tie_word_embeddings": true,
36
- "transformers_version": "4.56.1",
37
- "use_cache": false,
38
- "vocab_size": 128256
39
  }
 
1
  {
2
  "architectures": [
3
+ "Lfm2ForCausalLM"
4
  ],
5
+ "block_auto_adjust_ff_dim": false,
6
+ "block_dim": 2048,
7
+ "block_ff_dim": 10752,
8
+ "block_ffn_dim_multiplier": 1.0,
9
+ "block_mlp_init_scale": 1.0,
10
+ "block_multiple_of": 256,
11
+ "block_norm_eps": 1e-05,
12
+ "block_out_init_scale": 1.0,
13
+ "block_use_swiglu": true,
14
+ "block_use_xavier_init": true,
15
+ "bos_token_id": 1,
16
+ "conv_L_cache": 3,
17
+ "conv_bias": false,
18
+ "conv_dim": 2048,
19
+ "conv_dim_out": 2048,
20
+ "conv_use_xavier_init": true,
21
  "dtype": "bfloat16",
22
+ "eos_token_id": 7,
23
+ "hidden_size": 2048,
 
 
 
 
 
 
24
  "initializer_range": 0.02,
25
+ "intermediate_size": 10752,
26
+ "layer_types": [
27
+ "conv",
28
+ "conv",
29
+ "full_attention",
30
+ "conv",
31
+ "conv",
32
+ "full_attention",
33
+ "conv",
34
+ "conv",
35
+ "conv",
36
+ "full_attention",
37
+ "conv",
38
+ "conv",
39
+ "conv",
40
+ "full_attention",
41
+ "conv",
42
+ "conv",
43
+ "conv",
44
+ "full_attention",
45
+ "conv",
46
+ "conv",
47
+ "conv",
48
+ "full_attention",
49
+ "conv",
50
+ "conv",
51
+ "full_attention",
52
+ "conv",
53
+ "conv",
54
+ "full_attention",
55
+ "conv",
56
+ "conv"
57
+ ],
58
+ "max_position_embeddings": 128000,
59
+ "model_type": "lfm2",
60
+ "norm_eps": 1e-05,
61
+ "num_attention_heads": 32,
62
+ "num_heads": 32,
63
+ "num_hidden_layers": 30,
64
  "num_key_value_heads": 8,
65
+ "pad_token_id": 0,
66
+ "rope_theta": 1000000.0,
67
+ "theta": 1000000.0,
68
+ "tie_embedding": true,
69
+ "transformers_version": "4.56.2",
70
+ "use_cache": true,
71
+ "use_pos_enc": true,
72
+ "vocab_size": 65536
 
 
 
 
 
 
73
  }
generation_config.json CHANGED
@@ -1,11 +1,7 @@
1
  {
2
  "_from_model_config": true,
3
- "bos_token_id": 128000,
4
- "eos_token_id": [
5
- 128001,
6
- 128008,
7
- 128009
8
- ],
9
- "transformers_version": "4.56.1",
10
- "use_cache": false
11
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 7,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.56.2"
 
 
 
 
7
  }
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea0fda549d1e0dd9050f1d913402ab26c44b3fabf0aad80f5c809a49be7a994f
3
- size 4965799096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8a7bdf7a78d24ea66d0c870d579a188369c85119cabc934fa6ed228f8333382
3
+ size 4998052624
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0889e0222b1c1c870335710ecb0c52de96a665b4cc087b1346d93ade5c2c87df
3
- size 1459729952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04c3c74c9cb4ad54b0b33084060a2cb2766a14071b10e1eff9a751342c8feb3e
3
+ size 140522264
model.safetensors.index.json CHANGED
@@ -1,262 +1,274 @@
1
  {
2
  "metadata": {
3
- "total_parameters": 3212749824,
4
- "total_size": 6425499648
5
  },
6
  "weight_map": {
7
  "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
- "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
14
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
15
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
16
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
17
- "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
18
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
19
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
20
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
21
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
22
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
23
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
24
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
25
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
26
- "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
27
- "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
28
- "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
29
- "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
30
- "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
31
- "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
32
- "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
33
- "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
34
- "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
35
- "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
36
- "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
37
- "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
38
- "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
39
- "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
40
- "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
41
- "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
42
- "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
43
- "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
44
- "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
45
- "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
- "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
47
- "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
48
- "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
49
- "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
50
- "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
51
- "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
52
- "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
53
- "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
54
- "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
55
- "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
56
- "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
57
- "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
58
  "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
59
- "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
 
60
  "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
61
  "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
62
- "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
63
- "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
64
- "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
65
- "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
66
- "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
67
- "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
68
- "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
69
- "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
70
- "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
71
- "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
72
- "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
73
- "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
74
- "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
75
- "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
76
- "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
77
- "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
78
- "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
79
- "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
80
- "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
- "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
82
- "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
83
- "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
84
- "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
85
- "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
86
- "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
87
- "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
88
- "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
89
- "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
90
- "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
91
- "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
92
- "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
93
- "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
94
  "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
95
- "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
 
96
  "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
97
  "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
98
- "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
99
- "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
100
- "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
101
- "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
102
- "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
103
- "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
104
- "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
105
- "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
106
- "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
107
- "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
108
- "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
109
- "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
110
- "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
111
- "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
112
- "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
113
- "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
114
- "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
115
- "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
116
- "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
117
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
118
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
119
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
120
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
121
  "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
122
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
 
123
  "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
124
  "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
125
- "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
126
- "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
127
- "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
128
- "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
129
- "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
130
- "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
131
- "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
132
- "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
133
- "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
134
- "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
135
- "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
136
- "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
137
- "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
138
- "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
139
- "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
140
- "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
141
- "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
142
- "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
143
- "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
144
- "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
145
- "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
146
- "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
147
- "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
148
- "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
149
- "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
150
- "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
151
- "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
152
- "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
153
- "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
154
- "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
155
- "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
156
- "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
157
- "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
158
- "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
159
- "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
160
- "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
161
- "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
162
- "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
163
- "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
164
- "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
165
- "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
166
- "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
167
- "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
168
- "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
169
- "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
170
- "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
171
- "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
172
- "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
173
- "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
174
- "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
175
- "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
176
- "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
177
- "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
178
- "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
179
- "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
180
- "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
181
- "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
182
- "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
183
- "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
184
- "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
185
- "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
186
- "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
187
- "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
188
- "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
189
- "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
190
- "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
191
- "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
192
- "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
193
- "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
194
- "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
195
- "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
196
- "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
197
- "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
198
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
199
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
200
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
201
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
202
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
203
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
204
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
205
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
206
- "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
207
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
208
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
209
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
210
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
211
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
212
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
213
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
214
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
215
- "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
216
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
217
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
218
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
219
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
220
  "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
221
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
 
222
  "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
223
  "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
224
- "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
225
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
226
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
227
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
228
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
229
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
230
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
231
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
232
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
233
- "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
234
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
235
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
236
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
237
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
238
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
239
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
240
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
241
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
242
- "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
243
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
244
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
245
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
246
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
247
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
248
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
249
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
250
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
251
- "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
252
- "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
253
- "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
254
- "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
255
- "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
256
  "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
257
- "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
 
258
  "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
259
- "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
260
- "model.norm.weight": "model-00002-of-00002.safetensors"
261
  }
262
  }
 
1
  {
2
  "metadata": {
3
+ "total_parameters": 2569272320,
4
+ "total_size": 5138544640
5
  },
6
  "weight_map": {
7
  "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.embedding_norm.weight": "model-00002-of-00002.safetensors",
9
+ "model.layers.0.conv.conv.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.conv.in_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.conv.out_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.ffn_norm.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.operator_norm.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.conv.conv.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.conv.in_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.conv.out_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.ffn_norm.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.operator_norm.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.10.conv.conv.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.10.conv.in_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.10.conv.out_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.10.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.ffn_norm.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.operator_norm.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.11.conv.conv.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.11.conv.in_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.11.conv.out_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.11.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.11.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.11.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.11.ffn_norm.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.11.operator_norm.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.12.conv.conv.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.12.conv.in_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.12.conv.out_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.12.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.12.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.12.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.12.ffn_norm.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.12.operator_norm.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.13.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.13.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.13.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.13.ffn_norm.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.13.operator_norm.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.13.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors",
 
 
 
55
  "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.13.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors",
58
  "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
59
  "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.14.conv.conv.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.14.conv.in_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.14.conv.out_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.14.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.14.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.14.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.14.ffn_norm.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.14.operator_norm.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.15.conv.conv.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.15.conv.in_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.15.conv.out_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.15.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.15.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.15.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.15.ffn_norm.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.15.operator_norm.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.16.conv.conv.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.16.conv.in_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.16.conv.out_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.16.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.16.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.16.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.16.ffn_norm.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.16.operator_norm.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.17.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.17.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.17.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.17.ffn_norm.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.17.operator_norm.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.17.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors",
 
 
90
  "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.17.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors",
93
  "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
94
  "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.18.conv.conv.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.18.conv.in_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.18.conv.out_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.18.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.18.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.18.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.18.ffn_norm.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.18.operator_norm.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.19.conv.conv.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.19.conv.in_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.19.conv.out_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.19.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.19.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.19.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.19.ffn_norm.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.19.operator_norm.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.2.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.2.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.2.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.2.ffn_norm.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.2.operator_norm.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.2.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors",
 
117
  "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.2.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors",
120
  "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
121
  "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.20.conv.conv.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.20.conv.in_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.20.conv.out_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.20.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.20.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.20.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.20.ffn_norm.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.20.operator_norm.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.21.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.21.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.21.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.21.ffn_norm.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.21.operator_norm.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.21.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.21.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.22.conv.conv.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.22.conv.in_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.22.conv.out_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.22.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.22.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.22.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.22.ffn_norm.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.22.operator_norm.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.23.conv.conv.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.23.conv.in_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.23.conv.out_proj.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.23.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.23.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.23.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.23.ffn_norm.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.23.operator_norm.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.24.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.24.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.24.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.24.ffn_norm.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.24.operator_norm.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.24.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.24.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.25.conv.conv.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.25.conv.in_proj.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.25.conv.out_proj.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.25.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.25.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.25.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
174
+ "model.layers.25.ffn_norm.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.25.operator_norm.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.26.conv.conv.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.26.conv.in_proj.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.26.conv.out_proj.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.26.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
180
+ "model.layers.26.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.26.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
182
+ "model.layers.26.ffn_norm.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.26.operator_norm.weight": "model-00001-of-00002.safetensors",
184
+ "model.layers.27.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.27.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
186
+ "model.layers.27.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.27.ffn_norm.weight": "model-00001-of-00002.safetensors",
188
+ "model.layers.27.operator_norm.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.27.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors",
190
+ "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.27.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.27.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors",
193
+ "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
194
+ "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.28.conv.conv.weight": "model-00001-of-00002.safetensors",
196
+ "model.layers.28.conv.in_proj.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.28.conv.out_proj.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.28.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.28.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
200
+ "model.layers.28.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.28.ffn_norm.weight": "model-00001-of-00002.safetensors",
202
+ "model.layers.28.operator_norm.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.29.conv.conv.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.29.conv.in_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.29.conv.out_proj.weight": "model-00002-of-00002.safetensors",
206
+ "model.layers.29.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
207
+ "model.layers.29.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
208
+ "model.layers.29.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
209
+ "model.layers.29.ffn_norm.weight": "model-00002-of-00002.safetensors",
210
+ "model.layers.29.operator_norm.weight": "model-00002-of-00002.safetensors",
211
+ "model.layers.3.conv.conv.weight": "model-00001-of-00002.safetensors",
212
+ "model.layers.3.conv.in_proj.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.3.conv.out_proj.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.3.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.3.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.3.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.3.ffn_norm.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.3.operator_norm.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.4.conv.conv.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.4.conv.in_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.4.conv.out_proj.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.4.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.4.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.4.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
225
+ "model.layers.4.ffn_norm.weight": "model-00001-of-00002.safetensors",
226
+ "model.layers.4.operator_norm.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.5.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
228
+ "model.layers.5.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
229
+ "model.layers.5.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
230
+ "model.layers.5.ffn_norm.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.5.operator_norm.weight": "model-00001-of-00002.safetensors",
232
+ "model.layers.5.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors",
233
  "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
234
+ "model.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
235
+ "model.layers.5.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors",
236
  "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
237
  "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
238
+ "model.layers.6.conv.conv.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.6.conv.in_proj.weight": "model-00001-of-00002.safetensors",
240
+ "model.layers.6.conv.out_proj.weight": "model-00001-of-00002.safetensors",
241
+ "model.layers.6.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
242
+ "model.layers.6.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.6.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.6.ffn_norm.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.6.operator_norm.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.7.conv.conv.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.7.conv.in_proj.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.7.conv.out_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.7.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.7.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.7.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.7.ffn_norm.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.7.operator_norm.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.8.conv.conv.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.8.conv.in_proj.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.8.conv.out_proj.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.8.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
258
+ "model.layers.8.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.8.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
260
+ "model.layers.8.ffn_norm.weight": "model-00001-of-00002.safetensors",
261
+ "model.layers.8.operator_norm.weight": "model-00001-of-00002.safetensors",
262
+ "model.layers.9.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.9.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
264
+ "model.layers.9.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.9.ffn_norm.weight": "model-00001-of-00002.safetensors",
266
+ "model.layers.9.operator_norm.weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.9.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors",
 
 
268
  "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
270
+ "model.layers.9.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors",
271
  "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
272
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors"
 
273
  }
274
  }