pytorch_model.bin.index.json · nllb-200-3.3B

1

{

2

"metadata": {

3

"total_size": 19675971584

4

},

5

"weight_map": {

6

"lm_head.weight": "pytorch_model-00003-of-00003.bin",

7

"model.decoder.embed_tokens.weight": "pytorch_model-00002-of-00003.bin",

8

"model.decoder.layer_norm.bias": "pytorch_model-00002-of-00003.bin",

9

"model.decoder.layer_norm.weight": "pytorch_model-00002-of-00003.bin",

10

"model.decoder.layers.0.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

11

"model.decoder.layers.0.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

12

"model.decoder.layers.0.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

13

"model.decoder.layers.0.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

14

"model.decoder.layers.0.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

15

"model.decoder.layers.0.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

16

"model.decoder.layers.0.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

17

"model.decoder.layers.0.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

18

"model.decoder.layers.0.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

19

"model.decoder.layers.0.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

20

"model.decoder.layers.0.fc1.bias": "pytorch_model-00002-of-00003.bin",

21

"model.decoder.layers.0.fc1.weight": "pytorch_model-00002-of-00003.bin",

22

"model.decoder.layers.0.fc2.bias": "pytorch_model-00002-of-00003.bin",

23

"model.decoder.layers.0.fc2.weight": "pytorch_model-00002-of-00003.bin",

24

"model.decoder.layers.0.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

25

"model.decoder.layers.0.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

26

"model.decoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

27

"model.decoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

28

"model.decoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

29

"model.decoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

30

"model.decoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

31

"model.decoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

32

"model.decoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

33

"model.decoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

34

"model.decoder.layers.0.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

35

"model.decoder.layers.0.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

36

"model.decoder.layers.1.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

37

"model.decoder.layers.1.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

38

"model.decoder.layers.1.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

39

"model.decoder.layers.1.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

40

"model.decoder.layers.1.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

41

"model.decoder.layers.1.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

42

"model.decoder.layers.1.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

43

"model.decoder.layers.1.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

44

"model.decoder.layers.1.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

45

"model.decoder.layers.1.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

46

"model.decoder.layers.1.fc1.bias": "pytorch_model-00002-of-00003.bin",

47

"model.decoder.layers.1.fc1.weight": "pytorch_model-00002-of-00003.bin",

48

"model.decoder.layers.1.fc2.bias": "pytorch_model-00002-of-00003.bin",

49

"model.decoder.layers.1.fc2.weight": "pytorch_model-00002-of-00003.bin",

50

"model.decoder.layers.1.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

51

"model.decoder.layers.1.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

52

"model.decoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

53

"model.decoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

54

"model.decoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

55

"model.decoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

56

"model.decoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

57

"model.decoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

58

"model.decoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

59

"model.decoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

60

"model.decoder.layers.1.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

61

"model.decoder.layers.1.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

62

"model.decoder.layers.10.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

63

"model.decoder.layers.10.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

64

"model.decoder.layers.10.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

65

"model.decoder.layers.10.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

66

"model.decoder.layers.10.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

67

"model.decoder.layers.10.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

68

"model.decoder.layers.10.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

69

"model.decoder.layers.10.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

70

"model.decoder.layers.10.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

71

"model.decoder.layers.10.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

72

"model.decoder.layers.10.fc1.bias": "pytorch_model-00002-of-00003.bin",

73

"model.decoder.layers.10.fc1.weight": "pytorch_model-00002-of-00003.bin",

74

"model.decoder.layers.10.fc2.bias": "pytorch_model-00002-of-00003.bin",

75

"model.decoder.layers.10.fc2.weight": "pytorch_model-00002-of-00003.bin",

76

"model.decoder.layers.10.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

77

"model.decoder.layers.10.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

78

"model.decoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

79

"model.decoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

80

"model.decoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

81

"model.decoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

82

"model.decoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

83

"model.decoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

84

"model.decoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

85

"model.decoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

86

"model.decoder.layers.10.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

87

"model.decoder.layers.10.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

88

"model.decoder.layers.11.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

89

"model.decoder.layers.11.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

90

"model.decoder.layers.11.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

91

"model.decoder.layers.11.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

92

"model.decoder.layers.11.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

93

"model.decoder.layers.11.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

94

"model.decoder.layers.11.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

95

"model.decoder.layers.11.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

96

"model.decoder.layers.11.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

97

"model.decoder.layers.11.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

98

"model.decoder.layers.11.fc1.bias": "pytorch_model-00002-of-00003.bin",

99

"model.decoder.layers.11.fc1.weight": "pytorch_model-00002-of-00003.bin",

100

"model.decoder.layers.11.fc2.bias": "pytorch_model-00002-of-00003.bin",

101

"model.decoder.layers.11.fc2.weight": "pytorch_model-00002-of-00003.bin",

102

"model.decoder.layers.11.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

103

"model.decoder.layers.11.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

104

"model.decoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

105

"model.decoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

106

"model.decoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

107

"model.decoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

108

"model.decoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

109

"model.decoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

110

"model.decoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

111

"model.decoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

112

"model.decoder.layers.11.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

113

"model.decoder.layers.11.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

114

"model.decoder.layers.12.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

115

"model.decoder.layers.12.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

116

"model.decoder.layers.12.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

117

"model.decoder.layers.12.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

118

"model.decoder.layers.12.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

119

"model.decoder.layers.12.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

120

"model.decoder.layers.12.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

121

"model.decoder.layers.12.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

122

"model.decoder.layers.12.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

123

"model.decoder.layers.12.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

124

"model.decoder.layers.12.fc1.bias": "pytorch_model-00002-of-00003.bin",

125

"model.decoder.layers.12.fc1.weight": "pytorch_model-00002-of-00003.bin",

126

"model.decoder.layers.12.fc2.bias": "pytorch_model-00002-of-00003.bin",

127

"model.decoder.layers.12.fc2.weight": "pytorch_model-00002-of-00003.bin",

128

"model.decoder.layers.12.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

129

"model.decoder.layers.12.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

130

"model.decoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

131

"model.decoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

132

"model.decoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

133

"model.decoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

134

"model.decoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

135

"model.decoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

136

"model.decoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

137

"model.decoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

138

"model.decoder.layers.12.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

139

"model.decoder.layers.12.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

140

"model.decoder.layers.13.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

141

"model.decoder.layers.13.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

142

"model.decoder.layers.13.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

143

"model.decoder.layers.13.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

144

"model.decoder.layers.13.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

145

"model.decoder.layers.13.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

146

"model.decoder.layers.13.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

147

"model.decoder.layers.13.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

148

"model.decoder.layers.13.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

149

"model.decoder.layers.13.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

150

"model.decoder.layers.13.fc1.bias": "pytorch_model-00002-of-00003.bin",

151

"model.decoder.layers.13.fc1.weight": "pytorch_model-00002-of-00003.bin",

152

"model.decoder.layers.13.fc2.bias": "pytorch_model-00002-of-00003.bin",

153

"model.decoder.layers.13.fc2.weight": "pytorch_model-00002-of-00003.bin",

154

"model.decoder.layers.13.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

155

"model.decoder.layers.13.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

156

"model.decoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

157

"model.decoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

158

"model.decoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

159

"model.decoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

160

"model.decoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

161

"model.decoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

162

"model.decoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

163

"model.decoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

164

"model.decoder.layers.13.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

165

"model.decoder.layers.13.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

166

"model.decoder.layers.14.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

167

"model.decoder.layers.14.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

168

"model.decoder.layers.14.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

169

"model.decoder.layers.14.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

170

"model.decoder.layers.14.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

171

"model.decoder.layers.14.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

172

"model.decoder.layers.14.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

173

"model.decoder.layers.14.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

174

"model.decoder.layers.14.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

175

"model.decoder.layers.14.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

176

"model.decoder.layers.14.fc1.bias": "pytorch_model-00002-of-00003.bin",

177

"model.decoder.layers.14.fc1.weight": "pytorch_model-00002-of-00003.bin",

178

"model.decoder.layers.14.fc2.bias": "pytorch_model-00002-of-00003.bin",

179

"model.decoder.layers.14.fc2.weight": "pytorch_model-00002-of-00003.bin",

180

"model.decoder.layers.14.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

181

"model.decoder.layers.14.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

182

"model.decoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

183

"model.decoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

184

"model.decoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

185

"model.decoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

186

"model.decoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

187

"model.decoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

188

"model.decoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

189

"model.decoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

190

"model.decoder.layers.14.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

191

"model.decoder.layers.14.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

192

"model.decoder.layers.15.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

193

"model.decoder.layers.15.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

194

"model.decoder.layers.15.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

195

"model.decoder.layers.15.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

196

"model.decoder.layers.15.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

197

"model.decoder.layers.15.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

198

"model.decoder.layers.15.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

199

"model.decoder.layers.15.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

200

"model.decoder.layers.15.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

201

"model.decoder.layers.15.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

202

"model.decoder.layers.15.fc1.bias": "pytorch_model-00002-of-00003.bin",

203

"model.decoder.layers.15.fc1.weight": "pytorch_model-00002-of-00003.bin",

204

"model.decoder.layers.15.fc2.bias": "pytorch_model-00002-of-00003.bin",

205

"model.decoder.layers.15.fc2.weight": "pytorch_model-00002-of-00003.bin",

206

"model.decoder.layers.15.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

207

"model.decoder.layers.15.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

208

"model.decoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

209

"model.decoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

210

"model.decoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

211

"model.decoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

212

"model.decoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

213

"model.decoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

214

"model.decoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

215

"model.decoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

216

"model.decoder.layers.15.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

217

"model.decoder.layers.15.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

218

"model.decoder.layers.16.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

219

"model.decoder.layers.16.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

220

"model.decoder.layers.16.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

221

"model.decoder.layers.16.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

222

"model.decoder.layers.16.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

223

"model.decoder.layers.16.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

224

"model.decoder.layers.16.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

225

"model.decoder.layers.16.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

226

"model.decoder.layers.16.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

227

"model.decoder.layers.16.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

228

"model.decoder.layers.16.fc1.bias": "pytorch_model-00002-of-00003.bin",

229

"model.decoder.layers.16.fc1.weight": "pytorch_model-00002-of-00003.bin",

230

"model.decoder.layers.16.fc2.bias": "pytorch_model-00002-of-00003.bin",

231

"model.decoder.layers.16.fc2.weight": "pytorch_model-00002-of-00003.bin",

232

"model.decoder.layers.16.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

233

"model.decoder.layers.16.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

234

"model.decoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

235

"model.decoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

236

"model.decoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

237

"model.decoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

238

"model.decoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

239

"model.decoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

240

"model.decoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

241

"model.decoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

242

"model.decoder.layers.16.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

243

"model.decoder.layers.16.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

244

"model.decoder.layers.17.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

245

"model.decoder.layers.17.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

246

"model.decoder.layers.17.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

247

"model.decoder.layers.17.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

248

"model.decoder.layers.17.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

249

"model.decoder.layers.17.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

250

"model.decoder.layers.17.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

251

"model.decoder.layers.17.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

252

"model.decoder.layers.17.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

253

"model.decoder.layers.17.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

254

"model.decoder.layers.17.fc1.bias": "pytorch_model-00002-of-00003.bin",

255

"model.decoder.layers.17.fc1.weight": "pytorch_model-00002-of-00003.bin",

256

"model.decoder.layers.17.fc2.bias": "pytorch_model-00002-of-00003.bin",

257

"model.decoder.layers.17.fc2.weight": "pytorch_model-00002-of-00003.bin",

258

"model.decoder.layers.17.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

259

"model.decoder.layers.17.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

260

"model.decoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

261

"model.decoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

262

"model.decoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

263

"model.decoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

264

"model.decoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

265

"model.decoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

266

"model.decoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

267

"model.decoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

268

"model.decoder.layers.17.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

269

"model.decoder.layers.17.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

270

"model.decoder.layers.18.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

271

"model.decoder.layers.18.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

272

"model.decoder.layers.18.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

273

"model.decoder.layers.18.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

274

"model.decoder.layers.18.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

275

"model.decoder.layers.18.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

276

"model.decoder.layers.18.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

277

"model.decoder.layers.18.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

278

"model.decoder.layers.18.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

279

"model.decoder.layers.18.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

280

"model.decoder.layers.18.fc1.bias": "pytorch_model-00002-of-00003.bin",

281

"model.decoder.layers.18.fc1.weight": "pytorch_model-00002-of-00003.bin",

282

"model.decoder.layers.18.fc2.bias": "pytorch_model-00002-of-00003.bin",

283

"model.decoder.layers.18.fc2.weight": "pytorch_model-00002-of-00003.bin",

284

"model.decoder.layers.18.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

285

"model.decoder.layers.18.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

286

"model.decoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

287

"model.decoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

288

"model.decoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

289

"model.decoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

290

"model.decoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

291

"model.decoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

292

"model.decoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

293

"model.decoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

294

"model.decoder.layers.18.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

295

"model.decoder.layers.18.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

296

"model.decoder.layers.19.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

297

"model.decoder.layers.19.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

298

"model.decoder.layers.19.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

299

"model.decoder.layers.19.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

300

"model.decoder.layers.19.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

301

"model.decoder.layers.19.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

302

"model.decoder.layers.19.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

303

"model.decoder.layers.19.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

304

"model.decoder.layers.19.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

305

"model.decoder.layers.19.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

306

"model.decoder.layers.19.fc1.bias": "pytorch_model-00002-of-00003.bin",

307

"model.decoder.layers.19.fc1.weight": "pytorch_model-00002-of-00003.bin",

308

"model.decoder.layers.19.fc2.bias": "pytorch_model-00002-of-00003.bin",

309

"model.decoder.layers.19.fc2.weight": "pytorch_model-00002-of-00003.bin",

310

"model.decoder.layers.19.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

311

"model.decoder.layers.19.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

312

"model.decoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

313

"model.decoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

314

"model.decoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

315

"model.decoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

316

"model.decoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

317

"model.decoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

318

"model.decoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

319

"model.decoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

320

"model.decoder.layers.19.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

321

"model.decoder.layers.19.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

322

"model.decoder.layers.2.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

323

"model.decoder.layers.2.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

324

"model.decoder.layers.2.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

325

"model.decoder.layers.2.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

326

"model.decoder.layers.2.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

327

"model.decoder.layers.2.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

328

"model.decoder.layers.2.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

329

"model.decoder.layers.2.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

330

"model.decoder.layers.2.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

331

"model.decoder.layers.2.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

332

"model.decoder.layers.2.fc1.bias": "pytorch_model-00002-of-00003.bin",

333

"model.decoder.layers.2.fc1.weight": "pytorch_model-00002-of-00003.bin",

334

"model.decoder.layers.2.fc2.bias": "pytorch_model-00002-of-00003.bin",

335

"model.decoder.layers.2.fc2.weight": "pytorch_model-00002-of-00003.bin",

336

"model.decoder.layers.2.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

337

"model.decoder.layers.2.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

338

"model.decoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

339

"model.decoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

340

"model.decoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

341

"model.decoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

342

"model.decoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

343

"model.decoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

344

"model.decoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

345

"model.decoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

346

"model.decoder.layers.2.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

347

"model.decoder.layers.2.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

348

"model.decoder.layers.20.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

349

"model.decoder.layers.20.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

350

"model.decoder.layers.20.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

351

"model.decoder.layers.20.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

352

"model.decoder.layers.20.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

353

"model.decoder.layers.20.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

354

"model.decoder.layers.20.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

355

"model.decoder.layers.20.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

356

"model.decoder.layers.20.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

357

"model.decoder.layers.20.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

358

"model.decoder.layers.20.fc1.bias": "pytorch_model-00002-of-00003.bin",

359

"model.decoder.layers.20.fc1.weight": "pytorch_model-00002-of-00003.bin",

360

"model.decoder.layers.20.fc2.bias": "pytorch_model-00002-of-00003.bin",

361

"model.decoder.layers.20.fc2.weight": "pytorch_model-00002-of-00003.bin",

362

"model.decoder.layers.20.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

363

"model.decoder.layers.20.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

364

"model.decoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

365

"model.decoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

366

"model.decoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

367

"model.decoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

368

"model.decoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

369

"model.decoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

370

"model.decoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

371

"model.decoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

372

"model.decoder.layers.20.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

373

"model.decoder.layers.20.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

374

"model.decoder.layers.21.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

375

"model.decoder.layers.21.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

376

"model.decoder.layers.21.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

377

"model.decoder.layers.21.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

378

"model.decoder.layers.21.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

379

"model.decoder.layers.21.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

380

"model.decoder.layers.21.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

381

"model.decoder.layers.21.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

382

"model.decoder.layers.21.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

383

"model.decoder.layers.21.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

384

"model.decoder.layers.21.fc1.bias": "pytorch_model-00002-of-00003.bin",

385

"model.decoder.layers.21.fc1.weight": "pytorch_model-00002-of-00003.bin",

386

"model.decoder.layers.21.fc2.bias": "pytorch_model-00002-of-00003.bin",

387

"model.decoder.layers.21.fc2.weight": "pytorch_model-00002-of-00003.bin",

388

"model.decoder.layers.21.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

389

"model.decoder.layers.21.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

390

"model.decoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

391

"model.decoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

392

"model.decoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

393

"model.decoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

394

"model.decoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

395

"model.decoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

396

"model.decoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

397

"model.decoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

398

"model.decoder.layers.21.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

399

"model.decoder.layers.21.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

400

"model.decoder.layers.22.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

401

"model.decoder.layers.22.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

402

"model.decoder.layers.22.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

403

"model.decoder.layers.22.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

404

"model.decoder.layers.22.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

405

"model.decoder.layers.22.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

406

"model.decoder.layers.22.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

407

"model.decoder.layers.22.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

408

"model.decoder.layers.22.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

409

"model.decoder.layers.22.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

410

"model.decoder.layers.22.fc1.bias": "pytorch_model-00002-of-00003.bin",

411

"model.decoder.layers.22.fc1.weight": "pytorch_model-00002-of-00003.bin",

412

"model.decoder.layers.22.fc2.bias": "pytorch_model-00002-of-00003.bin",

413

"model.decoder.layers.22.fc2.weight": "pytorch_model-00002-of-00003.bin",

414

"model.decoder.layers.22.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

415

"model.decoder.layers.22.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

416

"model.decoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

417

"model.decoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

418

"model.decoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

419

"model.decoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

420

"model.decoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

421

"model.decoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

422

"model.decoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

423

"model.decoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

424

"model.decoder.layers.22.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

425

"model.decoder.layers.22.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

426

"model.decoder.layers.23.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

427

"model.decoder.layers.23.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

428

"model.decoder.layers.23.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

429

"model.decoder.layers.23.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

430

"model.decoder.layers.23.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

431

"model.decoder.layers.23.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

432

"model.decoder.layers.23.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

433

"model.decoder.layers.23.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

434

"model.decoder.layers.23.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

435

"model.decoder.layers.23.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

436

"model.decoder.layers.23.fc1.bias": "pytorch_model-00002-of-00003.bin",

437

"model.decoder.layers.23.fc1.weight": "pytorch_model-00002-of-00003.bin",

438

"model.decoder.layers.23.fc2.bias": "pytorch_model-00002-of-00003.bin",

439

"model.decoder.layers.23.fc2.weight": "pytorch_model-00002-of-00003.bin",

440

"model.decoder.layers.23.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

441

"model.decoder.layers.23.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

442

"model.decoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

443

"model.decoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

444

"model.decoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

445

"model.decoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

446

"model.decoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

447

"model.decoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

448

"model.decoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

449

"model.decoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

450

"model.decoder.layers.23.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

451

"model.decoder.layers.23.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

452

"model.decoder.layers.3.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

453

"model.decoder.layers.3.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

454

"model.decoder.layers.3.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

455

"model.decoder.layers.3.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

456

"model.decoder.layers.3.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

457

"model.decoder.layers.3.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

458

"model.decoder.layers.3.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

459

"model.decoder.layers.3.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

460

"model.decoder.layers.3.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

461

"model.decoder.layers.3.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

462

"model.decoder.layers.3.fc1.bias": "pytorch_model-00002-of-00003.bin",

463

"model.decoder.layers.3.fc1.weight": "pytorch_model-00002-of-00003.bin",

464

"model.decoder.layers.3.fc2.bias": "pytorch_model-00002-of-00003.bin",

465

"model.decoder.layers.3.fc2.weight": "pytorch_model-00002-of-00003.bin",

466

"model.decoder.layers.3.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

467

"model.decoder.layers.3.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

468

"model.decoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

469

"model.decoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

470

"model.decoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

471

"model.decoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

472

"model.decoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

473

"model.decoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

474

"model.decoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

475

"model.decoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

476

"model.decoder.layers.3.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

477

"model.decoder.layers.3.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

478

"model.decoder.layers.4.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

479

"model.decoder.layers.4.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

480

"model.decoder.layers.4.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

481

"model.decoder.layers.4.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

482

"model.decoder.layers.4.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

483

"model.decoder.layers.4.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

484

"model.decoder.layers.4.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

485

"model.decoder.layers.4.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

486

"model.decoder.layers.4.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

487

"model.decoder.layers.4.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

488

"model.decoder.layers.4.fc1.bias": "pytorch_model-00002-of-00003.bin",

489

"model.decoder.layers.4.fc1.weight": "pytorch_model-00002-of-00003.bin",

490

"model.decoder.layers.4.fc2.bias": "pytorch_model-00002-of-00003.bin",

491

"model.decoder.layers.4.fc2.weight": "pytorch_model-00002-of-00003.bin",

492

"model.decoder.layers.4.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

493

"model.decoder.layers.4.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

494

"model.decoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

495

"model.decoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

496

"model.decoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

497

"model.decoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

498

"model.decoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

499

"model.decoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

500

"model.decoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

501

"model.decoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

502

"model.decoder.layers.4.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

503

"model.decoder.layers.4.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

504

"model.decoder.layers.5.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

505

"model.decoder.layers.5.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

506

"model.decoder.layers.5.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

507

"model.decoder.layers.5.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

508

"model.decoder.layers.5.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

509

"model.decoder.layers.5.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

510

"model.decoder.layers.5.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

511

"model.decoder.layers.5.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

512

"model.decoder.layers.5.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

513

"model.decoder.layers.5.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

514

"model.decoder.layers.5.fc1.bias": "pytorch_model-00002-of-00003.bin",

515

"model.decoder.layers.5.fc1.weight": "pytorch_model-00002-of-00003.bin",

516

"model.decoder.layers.5.fc2.bias": "pytorch_model-00002-of-00003.bin",

517

"model.decoder.layers.5.fc2.weight": "pytorch_model-00002-of-00003.bin",

518

"model.decoder.layers.5.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

519

"model.decoder.layers.5.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

520

"model.decoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

521

"model.decoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

522

"model.decoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

523

"model.decoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

524

"model.decoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

525

"model.decoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

526

"model.decoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

527

"model.decoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

528

"model.decoder.layers.5.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

529

"model.decoder.layers.5.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

530

"model.decoder.layers.6.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

531

"model.decoder.layers.6.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

532

"model.decoder.layers.6.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

533

"model.decoder.layers.6.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

534

"model.decoder.layers.6.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

535

"model.decoder.layers.6.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

536

"model.decoder.layers.6.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

537

"model.decoder.layers.6.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

538

"model.decoder.layers.6.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

539

"model.decoder.layers.6.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

540

"model.decoder.layers.6.fc1.bias": "pytorch_model-00002-of-00003.bin",

541

"model.decoder.layers.6.fc1.weight": "pytorch_model-00002-of-00003.bin",

542

"model.decoder.layers.6.fc2.bias": "pytorch_model-00002-of-00003.bin",

543

"model.decoder.layers.6.fc2.weight": "pytorch_model-00002-of-00003.bin",

544

"model.decoder.layers.6.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

545

"model.decoder.layers.6.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

546

"model.decoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

547

"model.decoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

548

"model.decoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

549

"model.decoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

550

"model.decoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

551

"model.decoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

552

"model.decoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

553

"model.decoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

554

"model.decoder.layers.6.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

555

"model.decoder.layers.6.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

556

"model.decoder.layers.7.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

557

"model.decoder.layers.7.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

558

"model.decoder.layers.7.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

559

"model.decoder.layers.7.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

560

"model.decoder.layers.7.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

561

"model.decoder.layers.7.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

562

"model.decoder.layers.7.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

563

"model.decoder.layers.7.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

564

"model.decoder.layers.7.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

565

"model.decoder.layers.7.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

566

"model.decoder.layers.7.fc1.bias": "pytorch_model-00002-of-00003.bin",

567

"model.decoder.layers.7.fc1.weight": "pytorch_model-00002-of-00003.bin",

568

"model.decoder.layers.7.fc2.bias": "pytorch_model-00002-of-00003.bin",

569

"model.decoder.layers.7.fc2.weight": "pytorch_model-00002-of-00003.bin",

570

"model.decoder.layers.7.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

571

"model.decoder.layers.7.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

572

"model.decoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

573

"model.decoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

574

"model.decoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

575

"model.decoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

576

"model.decoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

577

"model.decoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

578

"model.decoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

579

"model.decoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

580

"model.decoder.layers.7.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

581

"model.decoder.layers.7.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

582

"model.decoder.layers.8.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

583

"model.decoder.layers.8.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

584

"model.decoder.layers.8.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

585

"model.decoder.layers.8.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

586

"model.decoder.layers.8.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

587

"model.decoder.layers.8.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

588

"model.decoder.layers.8.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

589

"model.decoder.layers.8.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

590

"model.decoder.layers.8.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

591

"model.decoder.layers.8.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

592

"model.decoder.layers.8.fc1.bias": "pytorch_model-00002-of-00003.bin",

593

"model.decoder.layers.8.fc1.weight": "pytorch_model-00002-of-00003.bin",

594

"model.decoder.layers.8.fc2.bias": "pytorch_model-00002-of-00003.bin",

595

"model.decoder.layers.8.fc2.weight": "pytorch_model-00002-of-00003.bin",

596

"model.decoder.layers.8.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

597

"model.decoder.layers.8.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

598

"model.decoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

599

"model.decoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

600

"model.decoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

601

"model.decoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

602

"model.decoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

603

"model.decoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

604

"model.decoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

605

"model.decoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

606

"model.decoder.layers.8.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

607

"model.decoder.layers.8.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

608

"model.decoder.layers.9.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

609

"model.decoder.layers.9.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

610

"model.decoder.layers.9.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

611

"model.decoder.layers.9.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

612

"model.decoder.layers.9.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

613

"model.decoder.layers.9.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

614

"model.decoder.layers.9.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

615

"model.decoder.layers.9.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

616

"model.decoder.layers.9.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

617

"model.decoder.layers.9.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

618

"model.decoder.layers.9.fc1.bias": "pytorch_model-00002-of-00003.bin",

619

"model.decoder.layers.9.fc1.weight": "pytorch_model-00002-of-00003.bin",

620

"model.decoder.layers.9.fc2.bias": "pytorch_model-00002-of-00003.bin",

621

"model.decoder.layers.9.fc2.weight": "pytorch_model-00002-of-00003.bin",

622

"model.decoder.layers.9.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

623

"model.decoder.layers.9.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

624

"model.decoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",

625

"model.decoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",

626

"model.decoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",

627

"model.decoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",

628

"model.decoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",

629

"model.decoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",

630

"model.decoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",

631

"model.decoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",

632

"model.decoder.layers.9.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",

633

"model.decoder.layers.9.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",

634

"model.encoder.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",

635

"model.encoder.layer_norm.bias": "pytorch_model-00001-of-00003.bin",

636

"model.encoder.layer_norm.weight": "pytorch_model-00001-of-00003.bin",

637

"model.encoder.layers.0.fc1.bias": "pytorch_model-00001-of-00003.bin",

638

"model.encoder.layers.0.fc1.weight": "pytorch_model-00001-of-00003.bin",

639

"model.encoder.layers.0.fc2.bias": "pytorch_model-00001-of-00003.bin",

640

"model.encoder.layers.0.fc2.weight": "pytorch_model-00001-of-00003.bin",

641

"model.encoder.layers.0.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

642

"model.encoder.layers.0.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

643

"model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",

644

"model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",

645

"model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",

646

"model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",

647

"model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",

648

"model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",

649

"model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",

650

"model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",

651

"model.encoder.layers.0.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

652

"model.encoder.layers.0.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

653

"model.encoder.layers.1.fc1.bias": "pytorch_model-00001-of-00003.bin",

654

"model.encoder.layers.1.fc1.weight": "pytorch_model-00001-of-00003.bin",

655

"model.encoder.layers.1.fc2.bias": "pytorch_model-00001-of-00003.bin",

656

"model.encoder.layers.1.fc2.weight": "pytorch_model-00001-of-00003.bin",

657

"model.encoder.layers.1.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

658

"model.encoder.layers.1.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

659

"model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",

660

"model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",

661

"model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",

662

"model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",

663

"model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",

664

"model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",

665

"model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",

666

"model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",

667

"model.encoder.layers.1.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

668

"model.encoder.layers.1.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

669

"model.encoder.layers.10.fc1.bias": "pytorch_model-00001-of-00003.bin",

670

"model.encoder.layers.10.fc1.weight": "pytorch_model-00001-of-00003.bin",

671

"model.encoder.layers.10.fc2.bias": "pytorch_model-00001-of-00003.bin",

672

"model.encoder.layers.10.fc2.weight": "pytorch_model-00001-of-00003.bin",

673

"model.encoder.layers.10.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

674

"model.encoder.layers.10.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

675

"model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",

676

"model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",

677

"model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",

678

"model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",

679

"model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",

680

"model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",

681

"model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",

682

"model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",

683

"model.encoder.layers.10.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

684

"model.encoder.layers.10.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

685

"model.encoder.layers.11.fc1.bias": "pytorch_model-00001-of-00003.bin",

686

"model.encoder.layers.11.fc1.weight": "pytorch_model-00001-of-00003.bin",

687

"model.encoder.layers.11.fc2.bias": "pytorch_model-00001-of-00003.bin",

688

"model.encoder.layers.11.fc2.weight": "pytorch_model-00001-of-00003.bin",

689

"model.encoder.layers.11.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

690

"model.encoder.layers.11.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

691

"model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",

692

"model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",

693

"model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",

694

"model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",

695

"model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",

696

"model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",

697

"model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",

698

"model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",

699

"model.encoder.layers.11.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

700

"model.encoder.layers.11.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

701

"model.encoder.layers.12.fc1.bias": "pytorch_model-00001-of-00003.bin",

702

"model.encoder.layers.12.fc1.weight": "pytorch_model-00001-of-00003.bin",

703

"model.encoder.layers.12.fc2.bias": "pytorch_model-00001-of-00003.bin",

704

"model.encoder.layers.12.fc2.weight": "pytorch_model-00001-of-00003.bin",

705

"model.encoder.layers.12.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

706

"model.encoder.layers.12.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

707

"model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",

708

"model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",

709

"model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",

710

"model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",

711

"model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",

712

"model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",

713

"model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",

714

"model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",

715

"model.encoder.layers.12.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

716

"model.encoder.layers.12.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

717

"model.encoder.layers.13.fc1.bias": "pytorch_model-00001-of-00003.bin",

718

"model.encoder.layers.13.fc1.weight": "pytorch_model-00001-of-00003.bin",

719

"model.encoder.layers.13.fc2.bias": "pytorch_model-00001-of-00003.bin",

720

"model.encoder.layers.13.fc2.weight": "pytorch_model-00001-of-00003.bin",

721

"model.encoder.layers.13.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

722

"model.encoder.layers.13.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

723

"model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",

724

"model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",

725

"model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",

726

"model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",

727

"model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",

728

"model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",

729

"model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",

730

"model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",

731

"model.encoder.layers.13.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

732

"model.encoder.layers.13.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

733

"model.encoder.layers.14.fc1.bias": "pytorch_model-00001-of-00003.bin",

734

"model.encoder.layers.14.fc1.weight": "pytorch_model-00001-of-00003.bin",

735

"model.encoder.layers.14.fc2.bias": "pytorch_model-00001-of-00003.bin",

736

"model.encoder.layers.14.fc2.weight": "pytorch_model-00001-of-00003.bin",

737

"model.encoder.layers.14.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

738

"model.encoder.layers.14.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

739

"model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",

740

"model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",

741

"model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",

742

"model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",

743

"model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",

744

"model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",

745

"model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",

746

"model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",

747

"model.encoder.layers.14.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

748

"model.encoder.layers.14.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

749

"model.encoder.layers.15.fc1.bias": "pytorch_model-00001-of-00003.bin",

750

"model.encoder.layers.15.fc1.weight": "pytorch_model-00001-of-00003.bin",

751

"model.encoder.layers.15.fc2.bias": "pytorch_model-00001-of-00003.bin",

752

"model.encoder.layers.15.fc2.weight": "pytorch_model-00001-of-00003.bin",

753

"model.encoder.layers.15.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

754

"model.encoder.layers.15.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

755

"model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",

756

"model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",

757

"model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",

758

"model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",

759

"model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",

760

"model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",

761

"model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",

762

"model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",

763

"model.encoder.layers.15.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

764

"model.encoder.layers.15.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

765

"model.encoder.layers.16.fc1.bias": "pytorch_model-00001-of-00003.bin",

766

"model.encoder.layers.16.fc1.weight": "pytorch_model-00001-of-00003.bin",

767

"model.encoder.layers.16.fc2.bias": "pytorch_model-00001-of-00003.bin",

768

"model.encoder.layers.16.fc2.weight": "pytorch_model-00001-of-00003.bin",

769

"model.encoder.layers.16.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

770

"model.encoder.layers.16.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

771

"model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",

772

"model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",

773

"model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",

774

"model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",

775

"model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",

776

"model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",

777

"model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",

778

"model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",

779

"model.encoder.layers.16.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

780

"model.encoder.layers.16.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

781

"model.encoder.layers.17.fc1.bias": "pytorch_model-00001-of-00003.bin",

782

"model.encoder.layers.17.fc1.weight": "pytorch_model-00001-of-00003.bin",

783

"model.encoder.layers.17.fc2.bias": "pytorch_model-00001-of-00003.bin",

784

"model.encoder.layers.17.fc2.weight": "pytorch_model-00001-of-00003.bin",

785

"model.encoder.layers.17.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

786

"model.encoder.layers.17.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

787

"model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",

788

"model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",

789

"model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",

790

"model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",

791

"model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",

792

"model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",

793

"model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",

794

"model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",

795

"model.encoder.layers.17.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

796

"model.encoder.layers.17.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

797

"model.encoder.layers.18.fc1.bias": "pytorch_model-00001-of-00003.bin",

798

"model.encoder.layers.18.fc1.weight": "pytorch_model-00001-of-00003.bin",

799

"model.encoder.layers.18.fc2.bias": "pytorch_model-00001-of-00003.bin",

800

"model.encoder.layers.18.fc2.weight": "pytorch_model-00001-of-00003.bin",

801

"model.encoder.layers.18.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

802

"model.encoder.layers.18.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

803

"model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",

804

"model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",

805

"model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",

806

"model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",

807

"model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",

808

"model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",

809

"model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",

810

"model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",

811

"model.encoder.layers.18.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

812

"model.encoder.layers.18.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

813

"model.encoder.layers.19.fc1.bias": "pytorch_model-00001-of-00003.bin",

814

"model.encoder.layers.19.fc1.weight": "pytorch_model-00001-of-00003.bin",

815

"model.encoder.layers.19.fc2.bias": "pytorch_model-00001-of-00003.bin",

816

"model.encoder.layers.19.fc2.weight": "pytorch_model-00001-of-00003.bin",

817

"model.encoder.layers.19.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

818

"model.encoder.layers.19.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

819

"model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",

820

"model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",

821

"model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",

822

"model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",

823

"model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",

824

"model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",

825

"model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",

826

"model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",

827

"model.encoder.layers.19.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

828

"model.encoder.layers.19.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

829

"model.encoder.layers.2.fc1.bias": "pytorch_model-00001-of-00003.bin",

830

"model.encoder.layers.2.fc1.weight": "pytorch_model-00001-of-00003.bin",

831

"model.encoder.layers.2.fc2.bias": "pytorch_model-00001-of-00003.bin",

832

"model.encoder.layers.2.fc2.weight": "pytorch_model-00001-of-00003.bin",

833

"model.encoder.layers.2.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

834

"model.encoder.layers.2.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

835

"model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",

836

"model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",

837

"model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",

838

"model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",

839

"model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",

840

"model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",

841

"model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",

842

"model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",

843

"model.encoder.layers.2.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

844

"model.encoder.layers.2.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

845

"model.encoder.layers.20.fc1.bias": "pytorch_model-00001-of-00003.bin",

846

"model.encoder.layers.20.fc1.weight": "pytorch_model-00001-of-00003.bin",

847

"model.encoder.layers.20.fc2.bias": "pytorch_model-00001-of-00003.bin",

848

"model.encoder.layers.20.fc2.weight": "pytorch_model-00001-of-00003.bin",

849

"model.encoder.layers.20.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

850

"model.encoder.layers.20.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

851

"model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",

852

"model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",

853

"model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",

854

"model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",

855

"model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",

856

"model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",

857

"model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",

858

"model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",

859

"model.encoder.layers.20.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

860

"model.encoder.layers.20.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

861

"model.encoder.layers.21.fc1.bias": "pytorch_model-00001-of-00003.bin",

862

"model.encoder.layers.21.fc1.weight": "pytorch_model-00001-of-00003.bin",

863

"model.encoder.layers.21.fc2.bias": "pytorch_model-00001-of-00003.bin",

864

"model.encoder.layers.21.fc2.weight": "pytorch_model-00001-of-00003.bin",

865

"model.encoder.layers.21.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

866

"model.encoder.layers.21.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

867

"model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",

868

"model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",

869

"model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",

870

"model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",

871

"model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",

872

"model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",

873

"model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",

874

"model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",

875

"model.encoder.layers.21.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

876

"model.encoder.layers.21.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

877

"model.encoder.layers.22.fc1.bias": "pytorch_model-00001-of-00003.bin",

878

"model.encoder.layers.22.fc1.weight": "pytorch_model-00001-of-00003.bin",

879

"model.encoder.layers.22.fc2.bias": "pytorch_model-00001-of-00003.bin",

880

"model.encoder.layers.22.fc2.weight": "pytorch_model-00001-of-00003.bin",

881

"model.encoder.layers.22.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

882

"model.encoder.layers.22.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

883

"model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",

884

"model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",

885

"model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",

886

"model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",

887

"model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",

888

"model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",

889

"model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",

890

"model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",

891

"model.encoder.layers.22.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

892

"model.encoder.layers.22.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

893

"model.encoder.layers.23.fc1.bias": "pytorch_model-00001-of-00003.bin",

894

"model.encoder.layers.23.fc1.weight": "pytorch_model-00001-of-00003.bin",

895

"model.encoder.layers.23.fc2.bias": "pytorch_model-00001-of-00003.bin",

896

"model.encoder.layers.23.fc2.weight": "pytorch_model-00001-of-00003.bin",

897

"model.encoder.layers.23.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

898

"model.encoder.layers.23.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

899

"model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",

900

"model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",

901

"model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",

902

"model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",

903

"model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",

904

"model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",

905

"model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",

906

"model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",

907

"model.encoder.layers.23.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

908

"model.encoder.layers.23.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

909

"model.encoder.layers.3.fc1.bias": "pytorch_model-00001-of-00003.bin",

910

"model.encoder.layers.3.fc1.weight": "pytorch_model-00001-of-00003.bin",

911

"model.encoder.layers.3.fc2.bias": "pytorch_model-00001-of-00003.bin",

912

"model.encoder.layers.3.fc2.weight": "pytorch_model-00001-of-00003.bin",

913

"model.encoder.layers.3.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

914

"model.encoder.layers.3.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

915

"model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",

916

"model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",

917

"model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",

918

"model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",

919

"model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",

920

"model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",

921

"model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",

922

"model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",

923

"model.encoder.layers.3.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

924

"model.encoder.layers.3.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

925

"model.encoder.layers.4.fc1.bias": "pytorch_model-00001-of-00003.bin",

926

"model.encoder.layers.4.fc1.weight": "pytorch_model-00001-of-00003.bin",

927

"model.encoder.layers.4.fc2.bias": "pytorch_model-00001-of-00003.bin",

928

"model.encoder.layers.4.fc2.weight": "pytorch_model-00001-of-00003.bin",

929

"model.encoder.layers.4.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

930

"model.encoder.layers.4.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

931

"model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",

932

"model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",

933

"model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",

934

"model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",

935

"model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",

936

"model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",

937

"model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",

938

"model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",

939

"model.encoder.layers.4.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

940

"model.encoder.layers.4.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

941

"model.encoder.layers.5.fc1.bias": "pytorch_model-00001-of-00003.bin",

942

"model.encoder.layers.5.fc1.weight": "pytorch_model-00001-of-00003.bin",

943

"model.encoder.layers.5.fc2.bias": "pytorch_model-00001-of-00003.bin",

944

"model.encoder.layers.5.fc2.weight": "pytorch_model-00001-of-00003.bin",

945

"model.encoder.layers.5.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

946

"model.encoder.layers.5.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

947

"model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",

948

"model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",

949

"model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",

950

"model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",

951

"model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",

952

"model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",

953

"model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",

954

"model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",

955

"model.encoder.layers.5.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

956

"model.encoder.layers.5.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

957

"model.encoder.layers.6.fc1.bias": "pytorch_model-00001-of-00003.bin",

958

"model.encoder.layers.6.fc1.weight": "pytorch_model-00001-of-00003.bin",

959

"model.encoder.layers.6.fc2.bias": "pytorch_model-00001-of-00003.bin",

960

"model.encoder.layers.6.fc2.weight": "pytorch_model-00001-of-00003.bin",

961

"model.encoder.layers.6.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

962

"model.encoder.layers.6.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

963

"model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",

964

"model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",

965

"model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",

966

"model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",

967

"model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",

968

"model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",

969

"model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",

970

"model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",

971

"model.encoder.layers.6.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

972

"model.encoder.layers.6.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

973

"model.encoder.layers.7.fc1.bias": "pytorch_model-00001-of-00003.bin",

974

"model.encoder.layers.7.fc1.weight": "pytorch_model-00001-of-00003.bin",

975

"model.encoder.layers.7.fc2.bias": "pytorch_model-00001-of-00003.bin",

976

"model.encoder.layers.7.fc2.weight": "pytorch_model-00001-of-00003.bin",

977

"model.encoder.layers.7.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

978

"model.encoder.layers.7.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

979

"model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",

980

"model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",

981

"model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",

982

"model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",

983

"model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",

984

"model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",

985

"model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",

986

"model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",

987

"model.encoder.layers.7.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

988

"model.encoder.layers.7.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

989

"model.encoder.layers.8.fc1.bias": "pytorch_model-00001-of-00003.bin",

990

"model.encoder.layers.8.fc1.weight": "pytorch_model-00001-of-00003.bin",

991

"model.encoder.layers.8.fc2.bias": "pytorch_model-00001-of-00003.bin",

992

"model.encoder.layers.8.fc2.weight": "pytorch_model-00001-of-00003.bin",

993

"model.encoder.layers.8.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

994

"model.encoder.layers.8.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

995

"model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",

996

"model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",

997

"model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",

998

"model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",

999

"model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",

1000

"model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",

1001

"model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",

1002

"model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",

1003

"model.encoder.layers.8.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

1004

"model.encoder.layers.8.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

1005

"model.encoder.layers.9.fc1.bias": "pytorch_model-00001-of-00003.bin",

1006

"model.encoder.layers.9.fc1.weight": "pytorch_model-00001-of-00003.bin",

1007

"model.encoder.layers.9.fc2.bias": "pytorch_model-00001-of-00003.bin",

1008

"model.encoder.layers.9.fc2.weight": "pytorch_model-00001-of-00003.bin",

1009

"model.encoder.layers.9.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

1010

"model.encoder.layers.9.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

1011

"model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",

1012

"model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",

1013

"model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",

1014

"model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",

1015

"model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",

1016

"model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",

1017

"model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",

1018

"model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",

1019

"model.encoder.layers.9.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",

1020

"model.encoder.layers.9.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",

1021

"model.shared.weight": "pytorch_model-00001-of-00003.bin"

1022

}

1023

}

1024