vhab10 commited on
Commit
a85a35c
1 Parent(s): 0f50dca

Trained with Unsloth

Browse files
README.md CHANGED
@@ -9,6 +9,7 @@ tags:
9
  - unsloth
10
  - llama
11
  - trl
 
12
  ---
13
 
14
  # Uploaded model
 
9
  - unsloth
10
  - llama
11
  - trl
12
+ - sft
13
  ---
14
 
15
  # Uploaded model
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unsloth/llama-3.2-3b-instruct-bnb-4bit",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
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
+ "pad_token_id": 128004,
26
+ "pretraining_tp": 1,
27
+ "rms_norm_eps": 1e-05,
28
+ "rope_scaling": {
29
+ "factor": 32.0,
30
+ "high_freq_factor": 4.0,
31
+ "low_freq_factor": 1.0,
32
+ "original_max_position_embeddings": 8192,
33
+ "rope_type": "llama3"
34
+ },
35
+ "rope_theta": 500000.0,
36
+ "tie_word_embeddings": true,
37
+ "torch_dtype": "float16",
38
+ "transformers_version": "4.44.2",
39
+ "unsloth_version": "2024.10.2",
40
+ "use_cache": true,
41
+ "vocab_size": 128256
42
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "max_length": 131072,
10
+ "pad_token_id": 128004,
11
+ "temperature": 0.6,
12
+ "top_p": 0.9,
13
+ "transformers_version": "4.44.2"
14
+ }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8eb1b102f5ae10edbb17f05d530501f7538140939de826a407c1d6ca8b46662c
3
+ size 4965844039
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ff7b77261cfd958fb59532a79aa8867803724c724677e47b0c7b4e227454fec
3
+ size 1459746080
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,261 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6425499648
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
7
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
8
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
9
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
10
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
11
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
12
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
13
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
14
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
15
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
16
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
17
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
18
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
19
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
20
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
21
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
22
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
23
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
24
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
25
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
26
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
27
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
28
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
29
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
30
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
31
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
32
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
33
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
34
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
35
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
36
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
37
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
38
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
39
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
40
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
41
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
42
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
43
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
44
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
45
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
46
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
47
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
48
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
49
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
50
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
51
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
52
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
53
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
54
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
55
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
56
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
57
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
58
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
59
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
60
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
61
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
62
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
63
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
64
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
65
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
66
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
67
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
68
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
69
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
70
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
71
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
72
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
73
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
74
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
75
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
76
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
77
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
78
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
79
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
80
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
81
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
82
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
83
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
84
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
85
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
86
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
87
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
88
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
89
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
90
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
91
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
92
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
93
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
94
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
95
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
96
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
97
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
98
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
99
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
100
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
101
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
102
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
103
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
104
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
105
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
106
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
107
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
108
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
109
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
110
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
111
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
112
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
113
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
114
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
115
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
116
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
117
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
118
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
119
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
120
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
121
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
122
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
123
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
124
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
125
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
126
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
127
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
128
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
129
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
130
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
131
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
132
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
133
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
134
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
135
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
136
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
137
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
138
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
139
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
140
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
141
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
142
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
143
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
144
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
145
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
146
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
147
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
148
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
149
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
150
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
151
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
152
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
153
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
154
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
155
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
156
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
157
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
158
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
159
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
160
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
161
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
162
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
163
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
164
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
165
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
166
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
167
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
168
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
169
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
170
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
171
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
172
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
173
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
174
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
175
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
176
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
177
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
178
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
179
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
180
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
181
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
182
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
183
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
184
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
185
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
186
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
187
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
188
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
189
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
190
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
191
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
192
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
193
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
194
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
195
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
196
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
197
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
198
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
199
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
200
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
201
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
202
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
203
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
204
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
205
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
206
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
207
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
208
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
209
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
210
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
211
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
212
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
213
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
214
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
215
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
216
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
217
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
218
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
219
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
220
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
221
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
222
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
223
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
224
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
225
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
226
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
227
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
228
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
229
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
230
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
231
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
232
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
233
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
234
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
235
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
236
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
237
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
238
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
239
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
240
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
241
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
242
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
243
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
244
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
245
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
246
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
247
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
248
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
249
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
250
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
251
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
252
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
253
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
254
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
255
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
256
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
257
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
258
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
259
+ "model.norm.weight": "pytorch_model-00002-of-00002.bin"
260
+ }
261
+ }