Hugging Face's logo

fdschmidt93
/
NLLB-LLM2Vec-Meta-Llama-31-8B-Instruct-mntp-unsup-simcse

Sentence Similarity
Transformers
Safetensors
multilingual
nllb-llm2vec
feature-extraction
text-embedding
embeddings
information-retrieval
beir
text-classification
language-model
text-clustering
text-semantic-similarity
text-evaluation
text-reranking
Sentence Similarity
natural_questions
ms_marco
fever
hotpot_qa
mteb
custom_code
Model card Files
xet
Community
1
fdschmidt93 commited on
Commit
f19606f
·
1 Parent(s): e90621b

feat: update weights

Browse files
Files changed (10) hide show
  1. config.json +2 -1
  2. model-00001-of-00007.safetensors → model-00001-of-00004.safetensors +2 -2
  3. model-00002-of-00007.safetensors → model-00002-of-00004.safetensors +2 -2
  4. model-00003-of-00007.safetensors → model-00003-of-00004.safetensors +2 -2
  5. model-00004-of-00007.safetensors → model-00004-of-00004.safetensors +2 -2
  6. model-00005-of-00007.safetensors +0 -3
  7. model-00006-of-00007.safetensors +0 -3
  8. model-00007-of-00007.safetensors +0 -3
  9. model.safetensors.index.json +487 -487
  10. modeling_nllbllm2vec.py +115 -94
config.json CHANGED
@@ -5,7 +5,8 @@
5
  ],
6
  "auto_map": {
7
  "AutoConfig": "configuration_nllbllm2vec.NLLBLLM2VecConfig",
8
- "AutoModel": "modeling_nllbllm2vec.NLLBLLM2Vec"
 
9
  },
10
  "llm2vec_config": {
11
  "_name_or_path": "McGill-NLP/LLM2Vec-Meta-Llama-3-8B-Instruct-mntp",
 
5
  ],
6
  "auto_map": {
7
  "AutoConfig": "configuration_nllbllm2vec.NLLBLLM2VecConfig",
8
+ "AutoModel": "modeling_nllbllm2vec.NLLBLLM2Vec",
9
+ "AutoModelForSequenceClassification": "modeling_nllbllm2vec.NLLBLLM2VecForSequenceClassification"
10
  },
11
  "llm2vec_config": {
12
  "_name_or_path": "McGill-NLP/LLM2Vec-Meta-Llama-3-8B-Instruct-mntp",
model-00001-of-00007.safetensors → model-00001-of-00004.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2409158d0692d1b6d8ade7342ddf40bbaeda0ed6bb545624d679bd3549d4d894
3
- size 4795637544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb6354f592f4f71f22bfff9d701bea06ddcfc3eff08007eb5f229f17b770b3b4
3
+ size 4981626968
model-00002-of-00007.safetensors → model-00002-of-00004.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:302a8d954626008cb14b1f74ae39d399ade67fe2d3404a7788ed5cb792b68cfa
3
- size 4832007544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8e63137114fc34e3c148c251810c8a81d65e3faea8f38963caf0670f2e634d0
3
+ size 4949470904
model-00003-of-00007.safetensors → model-00003-of-00004.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a77f2fa237b592921ffecb745ac613764da66643fbe98145435532cc1e63707a
3
- size 4999813200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07ba4a26dcf8d0989f1074b50d917338751b05d020b940b9f69ba86601c7c7e6
3
+ size 4915916376
model-00004-of-00007.safetensors → model-00004-of-00004.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a22835800d55155cfc48b8ec2f06a173d203eec52af80c0923c5ad057ee977e9
3
- size 4999813232
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d8f3b260d5dc3813ebdf30f768ed733b71e47e1ca36093f99bdfba57f87a722
3
+ size 1006692968
model-00005-of-00007.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1482c1048034b6bbb552b0d6a3969f5e76149e8dd4a7cc45ddb6cfae4d524a92
3
- size 4832007592
 
 
 
 
model-00006-of-00007.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6a5b0755ef742857b9f785cd6b61c9f3f16677581208d105562f53d6094647b
3
- size 4999813232
 
 
 
 
model-00007-of-00007.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2b0493c68cadb801fe6b5c0ff4d6c9d2093eca333c98736665c36ab7c523900
3
- size 2231487200
 
 
 
 
model.safetensors.index.json CHANGED
@@ -1,493 +1,493 @@
1
  {
2
  "metadata": {
3
- "total_size": 31690522624
4
  },
5
  "weight_map": {
6
- "llm2vec.embed_tokens.weight": "model-00001-of-00007.safetensors",
7
- "llm2vec.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
8
- "llm2vec.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
9
- "llm2vec.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
10
- "llm2vec.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
11
- "llm2vec.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
12
- "llm2vec.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
13
- "llm2vec.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
14
- "llm2vec.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
15
- "llm2vec.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
16
- "llm2vec.layers.1.input_layernorm.weight": "model-00002-of-00007.safetensors",
17
- "llm2vec.layers.1.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
18
- "llm2vec.layers.1.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
19
- "llm2vec.layers.1.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
20
- "llm2vec.layers.1.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
21
- "llm2vec.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
22
- "llm2vec.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
23
- "llm2vec.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
24
- "llm2vec.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
25
- "llm2vec.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
26
- "llm2vec.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
27
- "llm2vec.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
28
- "llm2vec.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
29
- "llm2vec.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
30
- "llm2vec.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
31
- "llm2vec.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
32
- "llm2vec.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
33
- "llm2vec.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
34
- "llm2vec.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
35
- "llm2vec.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
36
- "llm2vec.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
37
- "llm2vec.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
38
- "llm2vec.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
39
- "llm2vec.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
40
- "llm2vec.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
41
- "llm2vec.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
42
- "llm2vec.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
43
- "llm2vec.layers.12.input_layernorm.weight": "model-00004-of-00007.safetensors",
44
- "llm2vec.layers.12.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
45
- "llm2vec.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
46
- "llm2vec.layers.12.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
47
- "llm2vec.layers.12.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
48
- "llm2vec.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
49
- "llm2vec.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
50
- "llm2vec.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
51
- "llm2vec.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
52
- "llm2vec.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
53
- "llm2vec.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
54
- "llm2vec.layers.13.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
55
- "llm2vec.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
56
- "llm2vec.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
57
- "llm2vec.layers.13.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
58
- "llm2vec.layers.13.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
59
- "llm2vec.layers.13.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
60
- "llm2vec.layers.13.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
61
- "llm2vec.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
62
- "llm2vec.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
63
- "llm2vec.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
64
- "llm2vec.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
65
- "llm2vec.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
66
- "llm2vec.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
67
- "llm2vec.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
68
- "llm2vec.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
69
- "llm2vec.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
70
- "llm2vec.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
71
- "llm2vec.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
72
- "llm2vec.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
73
- "llm2vec.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
74
- "llm2vec.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
75
- "llm2vec.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
76
- "llm2vec.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
77
- "llm2vec.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
78
- "llm2vec.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
79
- "llm2vec.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
80
- "llm2vec.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
81
- "llm2vec.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
82
- "llm2vec.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
83
- "llm2vec.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
84
- "llm2vec.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
85
- "llm2vec.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
86
- "llm2vec.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
87
- "llm2vec.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
88
- "llm2vec.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
89
- "llm2vec.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
90
- "llm2vec.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
91
- "llm2vec.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
92
- "llm2vec.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
93
- "llm2vec.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
94
- "llm2vec.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
95
- "llm2vec.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
96
- "llm2vec.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
97
- "llm2vec.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
98
- "llm2vec.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
99
- "llm2vec.layers.18.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
100
- "llm2vec.layers.18.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
101
- "llm2vec.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
102
- "llm2vec.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
103
- "llm2vec.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
104
- "llm2vec.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
105
- "llm2vec.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
106
- "llm2vec.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
107
- "llm2vec.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
108
- "llm2vec.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
109
- "llm2vec.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
110
- "llm2vec.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
111
- "llm2vec.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
112
- "llm2vec.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
113
- "llm2vec.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
114
- "llm2vec.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
115
- "llm2vec.layers.2.input_layernorm.weight": "model-00002-of-00007.safetensors",
116
- "llm2vec.layers.2.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
117
- "llm2vec.layers.2.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
118
- "llm2vec.layers.2.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
119
- "llm2vec.layers.2.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
120
- "llm2vec.layers.2.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
121
- "llm2vec.layers.2.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
122
- "llm2vec.layers.2.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
123
- "llm2vec.layers.2.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
124
- "llm2vec.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
125
- "llm2vec.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
126
- "llm2vec.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
127
- "llm2vec.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
128
- "llm2vec.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
129
- "llm2vec.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
130
- "llm2vec.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
131
- "llm2vec.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
132
- "llm2vec.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
133
- "llm2vec.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
134
- "llm2vec.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
135
- "llm2vec.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
136
- "llm2vec.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
137
- "llm2vec.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
138
- "llm2vec.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
139
- "llm2vec.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
140
- "llm2vec.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
141
- "llm2vec.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
142
- "llm2vec.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
143
- "llm2vec.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
144
- "llm2vec.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
145
- "llm2vec.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
146
- "llm2vec.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
147
- "llm2vec.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
148
- "llm2vec.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
149
- "llm2vec.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
150
- "llm2vec.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
151
- "llm2vec.layers.23.input_layernorm.weight": "model-00006-of-00007.safetensors",
152
- "llm2vec.layers.23.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
153
- "llm2vec.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
154
- "llm2vec.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
155
- "llm2vec.layers.23.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
156
- "llm2vec.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
157
- "llm2vec.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
158
- "llm2vec.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
159
- "llm2vec.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
160
- "llm2vec.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
161
- "llm2vec.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
162
- "llm2vec.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
163
- "llm2vec.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
164
- "llm2vec.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
165
- "llm2vec.layers.24.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
166
- "llm2vec.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
167
- "llm2vec.layers.24.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
168
- "llm2vec.layers.24.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
169
- "llm2vec.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
170
- "llm2vec.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
171
- "llm2vec.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
172
- "llm2vec.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
173
- "llm2vec.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
174
- "llm2vec.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
175
- "llm2vec.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
176
- "llm2vec.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
177
- "llm2vec.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
178
- "llm2vec.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
179
- "llm2vec.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
180
- "llm2vec.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
181
- "llm2vec.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
182
- "llm2vec.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
183
- "llm2vec.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
184
- "llm2vec.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
185
- "llm2vec.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
186
- "llm2vec.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
187
- "llm2vec.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
188
- "llm2vec.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
189
- "llm2vec.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
190
- "llm2vec.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
191
- "llm2vec.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
192
- "llm2vec.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
193
- "llm2vec.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
194
- "llm2vec.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
195
- "llm2vec.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
196
- "llm2vec.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
197
- "llm2vec.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
198
- "llm2vec.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
199
- "llm2vec.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
200
- "llm2vec.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
201
- "llm2vec.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
202
- "llm2vec.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
203
- "llm2vec.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
204
- "llm2vec.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
205
- "llm2vec.layers.29.input_layernorm.weight": "model-00007-of-00007.safetensors",
206
- "llm2vec.layers.29.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
207
- "llm2vec.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
208
- "llm2vec.layers.29.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
209
- "llm2vec.layers.29.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
210
- "llm2vec.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
211
- "llm2vec.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
212
- "llm2vec.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
213
- "llm2vec.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
214
- "llm2vec.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
215
- "llm2vec.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
216
- "llm2vec.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
217
- "llm2vec.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
218
- "llm2vec.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
219
- "llm2vec.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
220
- "llm2vec.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
221
- "llm2vec.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
222
- "llm2vec.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
223
- "llm2vec.layers.30.input_layernorm.weight": "model-00007-of-00007.safetensors",
224
- "llm2vec.layers.30.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
225
- "llm2vec.layers.30.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
226
- "llm2vec.layers.30.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
227
- "llm2vec.layers.30.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
228
- "llm2vec.layers.30.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
229
- "llm2vec.layers.30.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
230
- "llm2vec.layers.30.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
231
- "llm2vec.layers.30.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
232
- "llm2vec.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors",
233
- "llm2vec.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
234
- "llm2vec.layers.31.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
235
- "llm2vec.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
236
- "llm2vec.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
237
- "llm2vec.layers.31.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
238
- "llm2vec.layers.31.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
239
- "llm2vec.layers.31.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
240
- "llm2vec.layers.31.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
241
- "llm2vec.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
242
- "llm2vec.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
243
- "llm2vec.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
244
- "llm2vec.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
245
- "llm2vec.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
246
- "llm2vec.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
247
- "llm2vec.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
248
- "llm2vec.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
249
- "llm2vec.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
250
- "llm2vec.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
251
- "llm2vec.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
252
- "llm2vec.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
253
- "llm2vec.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
254
- "llm2vec.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
255
- "llm2vec.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
256
- "llm2vec.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
257
- "llm2vec.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
258
- "llm2vec.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
259
- "llm2vec.layers.6.input_layernorm.weight": "model-00003-of-00007.safetensors",
260
- "llm2vec.layers.6.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
261
- "llm2vec.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
262
- "llm2vec.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
263
- "llm2vec.layers.6.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
264
- "llm2vec.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
265
- "llm2vec.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
266
- "llm2vec.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
267
- "llm2vec.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
268
- "llm2vec.layers.7.input_layernorm.weight": "model-00003-of-00007.safetensors",
269
- "llm2vec.layers.7.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
270
- "llm2vec.layers.7.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
271
- "llm2vec.layers.7.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
272
- "llm2vec.layers.7.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
273
- "llm2vec.layers.7.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
274
- "llm2vec.layers.7.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
275
- "llm2vec.layers.7.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
276
- "llm2vec.layers.7.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
277
- "llm2vec.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
278
- "llm2vec.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
279
- "llm2vec.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
280
- "llm2vec.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
281
- "llm2vec.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
282
- "llm2vec.layers.8.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
283
- "llm2vec.layers.8.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
284
- "llm2vec.layers.8.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
285
- "llm2vec.layers.8.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
286
- "llm2vec.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
287
- "llm2vec.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
288
- "llm2vec.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
289
- "llm2vec.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
290
- "llm2vec.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
291
- "llm2vec.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
292
- "llm2vec.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
293
- "llm2vec.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
294
- "llm2vec.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
295
- "llm2vec.norm.weight": "model-00007-of-00007.safetensors",
296
- "nllb_encoder.embed_tokens.weight": "model-00001-of-00007.safetensors",
297
- "nllb_encoder.layer_norm.bias": "model-00001-of-00007.safetensors",
298
- "nllb_encoder.layer_norm.weight": "model-00001-of-00007.safetensors",
299
- "nllb_encoder.layers.0.fc1.bias": "model-00001-of-00007.safetensors",
300
- "nllb_encoder.layers.0.fc1.weight": "model-00001-of-00007.safetensors",
301
- "nllb_encoder.layers.0.fc2.bias": "model-00001-of-00007.safetensors",
302
- "nllb_encoder.layers.0.fc2.weight": "model-00001-of-00007.safetensors",
303
- "nllb_encoder.layers.0.final_layer_norm.bias": "model-00001-of-00007.safetensors",
304
- "nllb_encoder.layers.0.final_layer_norm.weight": "model-00001-of-00007.safetensors",
305
- "nllb_encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
306
- "nllb_encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
307
- "nllb_encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
308
- "nllb_encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
309
- "nllb_encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
310
- "nllb_encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
311
- "nllb_encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
312
- "nllb_encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
313
- "nllb_encoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00007.safetensors",
314
- "nllb_encoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00007.safetensors",
315
- "nllb_encoder.layers.1.fc1.bias": "model-00001-of-00007.safetensors",
316
- "nllb_encoder.layers.1.fc1.weight": "model-00001-of-00007.safetensors",
317
- "nllb_encoder.layers.1.fc2.bias": "model-00001-of-00007.safetensors",
318
- "nllb_encoder.layers.1.fc2.weight": "model-00001-of-00007.safetensors",
319
- "nllb_encoder.layers.1.final_layer_norm.bias": "model-00001-of-00007.safetensors",
320
- "nllb_encoder.layers.1.final_layer_norm.weight": "model-00001-of-00007.safetensors",
321
- "nllb_encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
322
- "nllb_encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
323
- "nllb_encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
324
- "nllb_encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
325
- "nllb_encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
326
- "nllb_encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
327
- "nllb_encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
328
- "nllb_encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
329
- "nllb_encoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00007.safetensors",
330
- "nllb_encoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00007.safetensors",
331
- "nllb_encoder.layers.10.fc1.bias": "model-00001-of-00007.safetensors",
332
- "nllb_encoder.layers.10.fc1.weight": "model-00001-of-00007.safetensors",
333
- "nllb_encoder.layers.10.fc2.bias": "model-00001-of-00007.safetensors",
334
- "nllb_encoder.layers.10.fc2.weight": "model-00001-of-00007.safetensors",
335
- "nllb_encoder.layers.10.final_layer_norm.bias": "model-00001-of-00007.safetensors",
336
- "nllb_encoder.layers.10.final_layer_norm.weight": "model-00001-of-00007.safetensors",
337
- "nllb_encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
338
- "nllb_encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
339
- "nllb_encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
340
- "nllb_encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
341
- "nllb_encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
342
- "nllb_encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
343
- "nllb_encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
344
- "nllb_encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
345
- "nllb_encoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00007.safetensors",
346
- "nllb_encoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00007.safetensors",
347
- "nllb_encoder.layers.11.fc1.bias": "model-00001-of-00007.safetensors",
348
- "nllb_encoder.layers.11.fc1.weight": "model-00001-of-00007.safetensors",
349
- "nllb_encoder.layers.11.fc2.bias": "model-00001-of-00007.safetensors",
350
- "nllb_encoder.layers.11.fc2.weight": "model-00001-of-00007.safetensors",
351
- "nllb_encoder.layers.11.final_layer_norm.bias": "model-00001-of-00007.safetensors",
352
- "nllb_encoder.layers.11.final_layer_norm.weight": "model-00001-of-00007.safetensors",
353
- "nllb_encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
354
- "nllb_encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
355
- "nllb_encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
356
- "nllb_encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
357
- "nllb_encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
358
- "nllb_encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
359
- "nllb_encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
360
- "nllb_encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
361
- "nllb_encoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00007.safetensors",
362
- "nllb_encoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00007.safetensors",
363
- "nllb_encoder.layers.2.fc1.bias": "model-00001-of-00007.safetensors",
364
- "nllb_encoder.layers.2.fc1.weight": "model-00001-of-00007.safetensors",
365
- "nllb_encoder.layers.2.fc2.bias": "model-00001-of-00007.safetensors",
366
- "nllb_encoder.layers.2.fc2.weight": "model-00001-of-00007.safetensors",
367
- "nllb_encoder.layers.2.final_layer_norm.bias": "model-00001-of-00007.safetensors",
368
- "nllb_encoder.layers.2.final_layer_norm.weight": "model-00001-of-00007.safetensors",
369
- "nllb_encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
370
- "nllb_encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
371
- "nllb_encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
372
- "nllb_encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
373
- "nllb_encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
374
- "nllb_encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
375
- "nllb_encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
376
- "nllb_encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
377
- "nllb_encoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00007.safetensors",
378
- "nllb_encoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00007.safetensors",
379
- "nllb_encoder.layers.3.fc1.bias": "model-00001-of-00007.safetensors",
380
- "nllb_encoder.layers.3.fc1.weight": "model-00001-of-00007.safetensors",
381
- "nllb_encoder.layers.3.fc2.bias": "model-00001-of-00007.safetensors",
382
- "nllb_encoder.layers.3.fc2.weight": "model-00001-of-00007.safetensors",
383
- "nllb_encoder.layers.3.final_layer_norm.bias": "model-00001-of-00007.safetensors",
384
- "nllb_encoder.layers.3.final_layer_norm.weight": "model-00001-of-00007.safetensors",
385
- "nllb_encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
386
- "nllb_encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
387
- "nllb_encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
388
- "nllb_encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
389
- "nllb_encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
390
- "nllb_encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
391
- "nllb_encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
392
- "nllb_encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
393
- "nllb_encoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00007.safetensors",
394
- "nllb_encoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00007.safetensors",
395
- "nllb_encoder.layers.4.fc1.bias": "model-00001-of-00007.safetensors",
396
- "nllb_encoder.layers.4.fc1.weight": "model-00001-of-00007.safetensors",
397
- "nllb_encoder.layers.4.fc2.bias": "model-00001-of-00007.safetensors",
398
- "nllb_encoder.layers.4.fc2.weight": "model-00001-of-00007.safetensors",
399
- "nllb_encoder.layers.4.final_layer_norm.bias": "model-00001-of-00007.safetensors",
400
- "nllb_encoder.layers.4.final_layer_norm.weight": "model-00001-of-00007.safetensors",
401
- "nllb_encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
402
- "nllb_encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
403
- "nllb_encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
404
- "nllb_encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
405
- "nllb_encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
406
- "nllb_encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
407
- "nllb_encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
408
- "nllb_encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
409
- "nllb_encoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00007.safetensors",
410
- "nllb_encoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00007.safetensors",
411
- "nllb_encoder.layers.5.fc1.bias": "model-00001-of-00007.safetensors",
412
- "nllb_encoder.layers.5.fc1.weight": "model-00001-of-00007.safetensors",
413
- "nllb_encoder.layers.5.fc2.bias": "model-00001-of-00007.safetensors",
414
- "nllb_encoder.layers.5.fc2.weight": "model-00001-of-00007.safetensors",
415
- "nllb_encoder.layers.5.final_layer_norm.bias": "model-00001-of-00007.safetensors",
416
- "nllb_encoder.layers.5.final_layer_norm.weight": "model-00001-of-00007.safetensors",
417
- "nllb_encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
418
- "nllb_encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
419
- "nllb_encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
420
- "nllb_encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
421
- "nllb_encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
422
- "nllb_encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
423
- "nllb_encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
424
- "nllb_encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
425
- "nllb_encoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00007.safetensors",
426
- "nllb_encoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00007.safetensors",
427
- "nllb_encoder.layers.6.fc1.bias": "model-00001-of-00007.safetensors",
428
- "nllb_encoder.layers.6.fc1.weight": "model-00001-of-00007.safetensors",
429
- "nllb_encoder.layers.6.fc2.bias": "model-00001-of-00007.safetensors",
430
- "nllb_encoder.layers.6.fc2.weight": "model-00001-of-00007.safetensors",
431
- "nllb_encoder.layers.6.final_layer_norm.bias": "model-00001-of-00007.safetensors",
432
- "nllb_encoder.layers.6.final_layer_norm.weight": "model-00001-of-00007.safetensors",
433
- "nllb_encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
434
- "nllb_encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
435
- "nllb_encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
436
- "nllb_encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
437
- "nllb_encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
438
- "nllb_encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
439
- "nllb_encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
440
- "nllb_encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
441
- "nllb_encoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00007.safetensors",
442
- "nllb_encoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00007.safetensors",
443
- "nllb_encoder.layers.7.fc1.bias": "model-00001-of-00007.safetensors",
444
- "nllb_encoder.layers.7.fc1.weight": "model-00001-of-00007.safetensors",
445
- "nllb_encoder.layers.7.fc2.bias": "model-00001-of-00007.safetensors",
446
- "nllb_encoder.layers.7.fc2.weight": "model-00001-of-00007.safetensors",
447
- "nllb_encoder.layers.7.final_layer_norm.bias": "model-00001-of-00007.safetensors",
448
- "nllb_encoder.layers.7.final_layer_norm.weight": "model-00001-of-00007.safetensors",
449
- "nllb_encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
450
- "nllb_encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
451
- "nllb_encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
452
- "nllb_encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
453
- "nllb_encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
454
- "nllb_encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
455
- "nllb_encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
456
- "nllb_encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
457
- "nllb_encoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00007.safetensors",
458
- "nllb_encoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00007.safetensors",
459
- "nllb_encoder.layers.8.fc1.bias": "model-00001-of-00007.safetensors",
460
- "nllb_encoder.layers.8.fc1.weight": "model-00001-of-00007.safetensors",
461
- "nllb_encoder.layers.8.fc2.bias": "model-00001-of-00007.safetensors",
462
- "nllb_encoder.layers.8.fc2.weight": "model-00001-of-00007.safetensors",
463
- "nllb_encoder.layers.8.final_layer_norm.bias": "model-00001-of-00007.safetensors",
464
- "nllb_encoder.layers.8.final_layer_norm.weight": "model-00001-of-00007.safetensors",
465
- "nllb_encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
466
- "nllb_encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
467
- "nllb_encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
468
- "nllb_encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
469
- "nllb_encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
470
- "nllb_encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
471
- "nllb_encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
472
- "nllb_encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
473
- "nllb_encoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00007.safetensors",
474
- "nllb_encoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00007.safetensors",
475
- "nllb_encoder.layers.9.fc1.bias": "model-00001-of-00007.safetensors",
476
- "nllb_encoder.layers.9.fc1.weight": "model-00001-of-00007.safetensors",
477
- "nllb_encoder.layers.9.fc2.bias": "model-00001-of-00007.safetensors",
478
- "nllb_encoder.layers.9.fc2.weight": "model-00001-of-00007.safetensors",
479
- "nllb_encoder.layers.9.final_layer_norm.bias": "model-00001-of-00007.safetensors",
480
- "nllb_encoder.layers.9.final_layer_norm.weight": "model-00001-of-00007.safetensors",
481
- "nllb_encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
482
- "nllb_encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
483
- "nllb_encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
484
- "nllb_encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
485
- "nllb_encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
486
- "nllb_encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
487
- "nllb_encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
488
- "nllb_encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
489
- "nllb_encoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00007.safetensors",
490
- "nllb_encoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00007.safetensors",
491
- "up_proj.weight": "model-00007-of-00007.safetensors"
492
  }
493
  }
 
1
  {
2
  "metadata": {
3
+ "total_size": 15853649920
4
  },
5
  "weight_map": {
6
+ "llm2vec.embed_tokens.weight": "model-00001-of-00004.safetensors",
7
+ "llm2vec.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
8
+ "llm2vec.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
9
+ "llm2vec.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
10
+ "llm2vec.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
11
+ "llm2vec.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
12
+ "llm2vec.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
13
+ "llm2vec.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
14
+ "llm2vec.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
15
+ "llm2vec.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
16
+ "llm2vec.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
17
+ "llm2vec.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
18
+ "llm2vec.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
19
+ "llm2vec.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
20
+ "llm2vec.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
21
+ "llm2vec.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
22
+ "llm2vec.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
23
+ "llm2vec.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
24
+ "llm2vec.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
25
+ "llm2vec.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
26
+ "llm2vec.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
27
+ "llm2vec.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
28
+ "llm2vec.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
29
+ "llm2vec.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
30
+ "llm2vec.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
31
+ "llm2vec.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
32
+ "llm2vec.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
33
+ "llm2vec.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
34
+ "llm2vec.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
35
+ "llm2vec.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
36
+ "llm2vec.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
37
+ "llm2vec.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
38
+ "llm2vec.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
39
+ "llm2vec.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
40
+ "llm2vec.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
41
+ "llm2vec.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
42
+ "llm2vec.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
43
+ "llm2vec.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
44
+ "llm2vec.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
45
+ "llm2vec.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
46
+ "llm2vec.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
47
+ "llm2vec.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
48
+ "llm2vec.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
49
+ "llm2vec.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
50
+ "llm2vec.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
51
+ "llm2vec.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
52
+ "llm2vec.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
53
+ "llm2vec.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
54
+ "llm2vec.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
55
+ "llm2vec.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
56
+ "llm2vec.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
57
+ "llm2vec.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
58
+ "llm2vec.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
59
+ "llm2vec.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
60
+ "llm2vec.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
61
+ "llm2vec.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
62
+ "llm2vec.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
63
+ "llm2vec.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
64
+ "llm2vec.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
65
+ "llm2vec.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
66
+ "llm2vec.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
67
+ "llm2vec.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
68
+ "llm2vec.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
69
+ "llm2vec.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
70
+ "llm2vec.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
71
+ "llm2vec.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
72
+ "llm2vec.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
73
+ "llm2vec.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
74
+ "llm2vec.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
75
+ "llm2vec.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
76
+ "llm2vec.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
77
+ "llm2vec.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
78
+ "llm2vec.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
79
+ "llm2vec.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
80
+ "llm2vec.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
81
+ "llm2vec.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
82
+ "llm2vec.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
83
+ "llm2vec.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
84
+ "llm2vec.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
85
+ "llm2vec.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
86
+ "llm2vec.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
87
+ "llm2vec.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
88
+ "llm2vec.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
89
+ "llm2vec.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
90
+ "llm2vec.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
91
+ "llm2vec.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
92
+ "llm2vec.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
93
+ "llm2vec.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
94
+ "llm2vec.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
95
+ "llm2vec.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
96
+ "llm2vec.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
97
+ "llm2vec.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
98
+ "llm2vec.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
99
+ "llm2vec.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
100
+ "llm2vec.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
101
+ "llm2vec.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
102
+ "llm2vec.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
103
+ "llm2vec.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
104
+ "llm2vec.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
105
+ "llm2vec.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
106
+ "llm2vec.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
107
+ "llm2vec.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
108
+ "llm2vec.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
109
+ "llm2vec.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
110
+ "llm2vec.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
111
+ "llm2vec.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
112
+ "llm2vec.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
113
+ "llm2vec.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
114
+ "llm2vec.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
115
+ "llm2vec.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
116
+ "llm2vec.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
117
+ "llm2vec.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
118
+ "llm2vec.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
119
+ "llm2vec.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
120
+ "llm2vec.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
121
+ "llm2vec.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
122
+ "llm2vec.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
123
+ "llm2vec.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
124
+ "llm2vec.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
125
+ "llm2vec.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
126
+ "llm2vec.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
127
+ "llm2vec.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
128
+ "llm2vec.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
129
+ "llm2vec.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
130
+ "llm2vec.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
131
+ "llm2vec.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
132
+ "llm2vec.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
133
+ "llm2vec.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
134
+ "llm2vec.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
135
+ "llm2vec.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
136
+ "llm2vec.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
137
+ "llm2vec.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
138
+ "llm2vec.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
139
+ "llm2vec.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
140
+ "llm2vec.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
141
+ "llm2vec.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
142
+ "llm2vec.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
143
+ "llm2vec.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
144
+ "llm2vec.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
145
+ "llm2vec.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
146
+ "llm2vec.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
147
+ "llm2vec.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
148
+ "llm2vec.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
149
+ "llm2vec.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
150
+ "llm2vec.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
151
+ "llm2vec.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
152
+ "llm2vec.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
153
+ "llm2vec.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
154
+ "llm2vec.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
155
+ "llm2vec.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
156
+ "llm2vec.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
157
+ "llm2vec.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
158
+ "llm2vec.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
159
+ "llm2vec.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
160
+ "llm2vec.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
161
+ "llm2vec.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
162
+ "llm2vec.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
163
+ "llm2vec.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
164
+ "llm2vec.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
165
+ "llm2vec.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
166
+ "llm2vec.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
167
+ "llm2vec.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
168
+ "llm2vec.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
169
+ "llm2vec.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
170
+ "llm2vec.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
171
+ "llm2vec.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
172
+ "llm2vec.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
173
+ "llm2vec.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
174
+ "llm2vec.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
175
+ "llm2vec.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
176
+ "llm2vec.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
177
+ "llm2vec.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
178
+ "llm2vec.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
179
+ "llm2vec.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
180
+ "llm2vec.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
181
+ "llm2vec.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
182
+ "llm2vec.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
183
+ "llm2vec.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
184
+ "llm2vec.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
185
+ "llm2vec.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
186
+ "llm2vec.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
187
+ "llm2vec.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
188
+ "llm2vec.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
189
+ "llm2vec.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
190
+ "llm2vec.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
191
+ "llm2vec.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
192
+ "llm2vec.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
193
+ "llm2vec.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
194
+ "llm2vec.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
195
+ "llm2vec.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
196
+ "llm2vec.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
197
+ "llm2vec.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
198
+ "llm2vec.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
199
+ "llm2vec.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
200
+ "llm2vec.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
201
+ "llm2vec.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
202
+ "llm2vec.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
203
+ "llm2vec.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
204
+ "llm2vec.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
205
+ "llm2vec.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
206
+ "llm2vec.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
207
+ "llm2vec.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
208
+ "llm2vec.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
209
+ "llm2vec.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
210
+ "llm2vec.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
211
+ "llm2vec.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
212
+ "llm2vec.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
213
+ "llm2vec.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
214
+ "llm2vec.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
215
+ "llm2vec.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
216
+ "llm2vec.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
217
+ "llm2vec.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
218
+ "llm2vec.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
219
+ "llm2vec.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
220
+ "llm2vec.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
221
+ "llm2vec.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
222
+ "llm2vec.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
223
+ "llm2vec.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
224
+ "llm2vec.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
225
+ "llm2vec.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
226
+ "llm2vec.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
227
+ "llm2vec.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
228
+ "llm2vec.layers.30.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
229
+ "llm2vec.layers.30.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
230
+ "llm2vec.layers.30.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
231
+ "llm2vec.layers.30.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
232
+ "llm2vec.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
233
+ "llm2vec.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
234
+ "llm2vec.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
235
+ "llm2vec.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
236
+ "llm2vec.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
237
+ "llm2vec.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
238
+ "llm2vec.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
239
+ "llm2vec.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
240
+ "llm2vec.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
241
+ "llm2vec.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
242
+ "llm2vec.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
243
+ "llm2vec.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
244
+ "llm2vec.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
245
+ "llm2vec.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
246
+ "llm2vec.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
247
+ "llm2vec.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
248
+ "llm2vec.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
249
+ "llm2vec.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
250
+ "llm2vec.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
251
+ "llm2vec.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
252
+ "llm2vec.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
253
+ "llm2vec.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
254
+ "llm2vec.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
255
+ "llm2vec.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
256
+ "llm2vec.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
257
+ "llm2vec.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
258
+ "llm2vec.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
259
+ "llm2vec.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
260
+ "llm2vec.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
261
+ "llm2vec.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
262
+ "llm2vec.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
263
+ "llm2vec.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
264
+ "llm2vec.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
265
+ "llm2vec.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
266
+ "llm2vec.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
267
+ "llm2vec.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
268
+ "llm2vec.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
269
+ "llm2vec.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
270
+ "llm2vec.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
271
+ "llm2vec.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
272
+ "llm2vec.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
273
+ "llm2vec.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
274
+ "llm2vec.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
275
+ "llm2vec.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
276
+ "llm2vec.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
277
+ "llm2vec.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
278
+ "llm2vec.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
279
+ "llm2vec.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
280
+ "llm2vec.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
281
+ "llm2vec.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
282
+ "llm2vec.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
283
+ "llm2vec.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
284
+ "llm2vec.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
285
+ "llm2vec.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
286
+ "llm2vec.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
287
+ "llm2vec.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
288
+ "llm2vec.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
289
+ "llm2vec.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
290
+ "llm2vec.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
291
+ "llm2vec.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
292
+ "llm2vec.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
293
+ "llm2vec.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
294
+ "llm2vec.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
295
+ "llm2vec.norm.weight": "model-00004-of-00004.safetensors",
296
+ "nllb_encoder.embed_tokens.weight": "model-00001-of-00004.safetensors",
297
+ "nllb_encoder.layer_norm.bias": "model-00001-of-00004.safetensors",
298
+ "nllb_encoder.layer_norm.weight": "model-00001-of-00004.safetensors",
299
+ "nllb_encoder.layers.0.fc1.bias": "model-00001-of-00004.safetensors",
300
+ "nllb_encoder.layers.0.fc1.weight": "model-00001-of-00004.safetensors",
301
+ "nllb_encoder.layers.0.fc2.bias": "model-00001-of-00004.safetensors",
302
+ "nllb_encoder.layers.0.fc2.weight": "model-00001-of-00004.safetensors",
303
+ "nllb_encoder.layers.0.final_layer_norm.bias": "model-00001-of-00004.safetensors",
304
+ "nllb_encoder.layers.0.final_layer_norm.weight": "model-00001-of-00004.safetensors",
305
+ "nllb_encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
306
+ "nllb_encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
307
+ "nllb_encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
308
+ "nllb_encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
309
+ "nllb_encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
310
+ "nllb_encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
311
+ "nllb_encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
312
+ "nllb_encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
313
+ "nllb_encoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
314
+ "nllb_encoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
315
+ "nllb_encoder.layers.1.fc1.bias": "model-00001-of-00004.safetensors",
316
+ "nllb_encoder.layers.1.fc1.weight": "model-00001-of-00004.safetensors",
317
+ "nllb_encoder.layers.1.fc2.bias": "model-00001-of-00004.safetensors",
318
+ "nllb_encoder.layers.1.fc2.weight": "model-00001-of-00004.safetensors",
319
+ "nllb_encoder.layers.1.final_layer_norm.bias": "model-00001-of-00004.safetensors",
320
+ "nllb_encoder.layers.1.final_layer_norm.weight": "model-00001-of-00004.safetensors",
321
+ "nllb_encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
322
+ "nllb_encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
323
+ "nllb_encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
324
+ "nllb_encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
325
+ "nllb_encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
326
+ "nllb_encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
327
+ "nllb_encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
328
+ "nllb_encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
329
+ "nllb_encoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
330
+ "nllb_encoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
331
+ "nllb_encoder.layers.10.fc1.bias": "model-00001-of-00004.safetensors",
332
+ "nllb_encoder.layers.10.fc1.weight": "model-00001-of-00004.safetensors",
333
+ "nllb_encoder.layers.10.fc2.bias": "model-00001-of-00004.safetensors",
334
+ "nllb_encoder.layers.10.fc2.weight": "model-00001-of-00004.safetensors",
335
+ "nllb_encoder.layers.10.final_layer_norm.bias": "model-00001-of-00004.safetensors",
336
+ "nllb_encoder.layers.10.final_layer_norm.weight": "model-00001-of-00004.safetensors",
337
+ "nllb_encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
338
+ "nllb_encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
339
+ "nllb_encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
340
+ "nllb_encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
341
+ "nllb_encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
342
+ "nllb_encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
343
+ "nllb_encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
344
+ "nllb_encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
345
+ "nllb_encoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
346
+ "nllb_encoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
347
+ "nllb_encoder.layers.11.fc1.bias": "model-00001-of-00004.safetensors",
348
+ "nllb_encoder.layers.11.fc1.weight": "model-00001-of-00004.safetensors",
349
+ "nllb_encoder.layers.11.fc2.bias": "model-00001-of-00004.safetensors",
350
+ "nllb_encoder.layers.11.fc2.weight": "model-00001-of-00004.safetensors",
351
+ "nllb_encoder.layers.11.final_layer_norm.bias": "model-00001-of-00004.safetensors",
352
+ "nllb_encoder.layers.11.final_layer_norm.weight": "model-00001-of-00004.safetensors",
353
+ "nllb_encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
354
+ "nllb_encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
355
+ "nllb_encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
356
+ "nllb_encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
357
+ "nllb_encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
358
+ "nllb_encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
359
+ "nllb_encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
360
+ "nllb_encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
361
+ "nllb_encoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
362
+ "nllb_encoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
363
+ "nllb_encoder.layers.2.fc1.bias": "model-00001-of-00004.safetensors",
364
+ "nllb_encoder.layers.2.fc1.weight": "model-00001-of-00004.safetensors",
365
+ "nllb_encoder.layers.2.fc2.bias": "model-00001-of-00004.safetensors",
366
+ "nllb_encoder.layers.2.fc2.weight": "model-00001-of-00004.safetensors",
367
+ "nllb_encoder.layers.2.final_layer_norm.bias": "model-00001-of-00004.safetensors",
368
+ "nllb_encoder.layers.2.final_layer_norm.weight": "model-00001-of-00004.safetensors",
369
+ "nllb_encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
370
+ "nllb_encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
371
+ "nllb_encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
372
+ "nllb_encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
373
+ "nllb_encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
374
+ "nllb_encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
375
+ "nllb_encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
376
+ "nllb_encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
377
+ "nllb_encoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
378
+ "nllb_encoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
379
+ "nllb_encoder.layers.3.fc1.bias": "model-00001-of-00004.safetensors",
380
+ "nllb_encoder.layers.3.fc1.weight": "model-00001-of-00004.safetensors",
381
+ "nllb_encoder.layers.3.fc2.bias": "model-00001-of-00004.safetensors",
382
+ "nllb_encoder.layers.3.fc2.weight": "model-00001-of-00004.safetensors",
383
+ "nllb_encoder.layers.3.final_layer_norm.bias": "model-00001-of-00004.safetensors",
384
+ "nllb_encoder.layers.3.final_layer_norm.weight": "model-00001-of-00004.safetensors",
385
+ "nllb_encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
386
+ "nllb_encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
387
+ "nllb_encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
388
+ "nllb_encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
389
+ "nllb_encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
390
+ "nllb_encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
391
+ "nllb_encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
392
+ "nllb_encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
393
+ "nllb_encoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
394
+ "nllb_encoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
395
+ "nllb_encoder.layers.4.fc1.bias": "model-00001-of-00004.safetensors",
396
+ "nllb_encoder.layers.4.fc1.weight": "model-00001-of-00004.safetensors",
397
+ "nllb_encoder.layers.4.fc2.bias": "model-00001-of-00004.safetensors",
398
+ "nllb_encoder.layers.4.fc2.weight": "model-00001-of-00004.safetensors",
399
+ "nllb_encoder.layers.4.final_layer_norm.bias": "model-00001-of-00004.safetensors",
400
+ "nllb_encoder.layers.4.final_layer_norm.weight": "model-00001-of-00004.safetensors",
401
+ "nllb_encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
402
+ "nllb_encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
403
+ "nllb_encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
404
+ "nllb_encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
405
+ "nllb_encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
406
+ "nllb_encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
407
+ "nllb_encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
408
+ "nllb_encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
409
+ "nllb_encoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
410
+ "nllb_encoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
411
+ "nllb_encoder.layers.5.fc1.bias": "model-00001-of-00004.safetensors",
412
+ "nllb_encoder.layers.5.fc1.weight": "model-00001-of-00004.safetensors",
413
+ "nllb_encoder.layers.5.fc2.bias": "model-00001-of-00004.safetensors",
414
+ "nllb_encoder.layers.5.fc2.weight": "model-00001-of-00004.safetensors",
415
+ "nllb_encoder.layers.5.final_layer_norm.bias": "model-00001-of-00004.safetensors",
416
+ "nllb_encoder.layers.5.final_layer_norm.weight": "model-00001-of-00004.safetensors",
417
+ "nllb_encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
418
+ "nllb_encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
419
+ "nllb_encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
420
+ "nllb_encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
421
+ "nllb_encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
422
+ "nllb_encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
423
+ "nllb_encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
424
+ "nllb_encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
425
+ "nllb_encoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
426
+ "nllb_encoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
427
+ "nllb_encoder.layers.6.fc1.bias": "model-00001-of-00004.safetensors",
428
+ "nllb_encoder.layers.6.fc1.weight": "model-00001-of-00004.safetensors",
429
+ "nllb_encoder.layers.6.fc2.bias": "model-00001-of-00004.safetensors",
430
+ "nllb_encoder.layers.6.fc2.weight": "model-00001-of-00004.safetensors",
431
+ "nllb_encoder.layers.6.final_layer_norm.bias": "model-00001-of-00004.safetensors",
432
+ "nllb_encoder.layers.6.final_layer_norm.weight": "model-00001-of-00004.safetensors",
433
+ "nllb_encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
434
+ "nllb_encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
435
+ "nllb_encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
436
+ "nllb_encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
437
+ "nllb_encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
438
+ "nllb_encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
439
+ "nllb_encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
440
+ "nllb_encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
441
+ "nllb_encoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
442
+ "nllb_encoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
443
+ "nllb_encoder.layers.7.fc1.bias": "model-00001-of-00004.safetensors",
444
+ "nllb_encoder.layers.7.fc1.weight": "model-00001-of-00004.safetensors",
445
+ "nllb_encoder.layers.7.fc2.bias": "model-00001-of-00004.safetensors",
446
+ "nllb_encoder.layers.7.fc2.weight": "model-00001-of-00004.safetensors",
447
+ "nllb_encoder.layers.7.final_layer_norm.bias": "model-00001-of-00004.safetensors",
448
+ "nllb_encoder.layers.7.final_layer_norm.weight": "model-00001-of-00004.safetensors",
449
+ "nllb_encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
450
+ "nllb_encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
451
+ "nllb_encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
452
+ "nllb_encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
453
+ "nllb_encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
454
+ "nllb_encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
455
+ "nllb_encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
456
+ "nllb_encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
457
+ "nllb_encoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
458
+ "nllb_encoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
459
+ "nllb_encoder.layers.8.fc1.bias": "model-00001-of-00004.safetensors",
460
+ "nllb_encoder.layers.8.fc1.weight": "model-00001-of-00004.safetensors",
461
+ "nllb_encoder.layers.8.fc2.bias": "model-00001-of-00004.safetensors",
462
+ "nllb_encoder.layers.8.fc2.weight": "model-00001-of-00004.safetensors",
463
+ "nllb_encoder.layers.8.final_layer_norm.bias": "model-00001-of-00004.safetensors",
464
+ "nllb_encoder.layers.8.final_layer_norm.weight": "model-00001-of-00004.safetensors",
465
+ "nllb_encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
466
+ "nllb_encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
467
+ "nllb_encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
468
+ "nllb_encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
469
+ "nllb_encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
470
+ "nllb_encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
471
+ "nllb_encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
472
+ "nllb_encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
473
+ "nllb_encoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
474
+ "nllb_encoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
475
+ "nllb_encoder.layers.9.fc1.bias": "model-00001-of-00004.safetensors",
476
+ "nllb_encoder.layers.9.fc1.weight": "model-00001-of-00004.safetensors",
477
+ "nllb_encoder.layers.9.fc2.bias": "model-00001-of-00004.safetensors",
478
+ "nllb_encoder.layers.9.fc2.weight": "model-00001-of-00004.safetensors",
479
+ "nllb_encoder.layers.9.final_layer_norm.bias": "model-00001-of-00004.safetensors",
480
+ "nllb_encoder.layers.9.final_layer_norm.weight": "model-00001-of-00004.safetensors",
481
+ "nllb_encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
482
+ "nllb_encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
483
+ "nllb_encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
484
+ "nllb_encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
485
+ "nllb_encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
486
+ "nllb_encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
487
+ "nllb_encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
488
+ "nllb_encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
489
+ "nllb_encoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
490
+ "nllb_encoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
491
+ "up_proj.weight": "model-00004-of-00004.safetensors"
492
  }
493
  }
modeling_nllbllm2vec.py CHANGED
@@ -3,7 +3,7 @@ from typing import Any, Dict, List, Optional, Tuple, cast, Union
3
  import torch
4
  import torch.nn as nn
5
  import torch.nn.functional as F
6
- from transformers.models.auto import AutoModel
7
  from transformers.modeling_outputs import (
8
  BaseModelOutputWithPooling,
9
  SequenceClassifierOutputWithPast,
@@ -18,6 +18,7 @@ from .modeling_llama_encoder import LlamaEncoderModel
18
 
19
  class NLLBLLM2Vec(PreTrainedModel):
20
  config_class = NLLBLLM2VecConfig
 
21
  """
22
  NLLBLLM2Vec model combining NLLB and LLama encoders.
23
 
@@ -29,8 +30,6 @@ class NLLBLLM2Vec(PreTrainedModel):
29
  **kwargs: Additional keyword arguments.
30
  """
31
 
32
- model_type = "nllb-llm2vec"
33
-
34
  def __init__(
35
  self,
36
  config: Optional[NLLBLLM2VecConfig] = None,
@@ -234,13 +233,126 @@ class NLLBLLM2Vec(PreTrainedModel):
234
  )
235
 
236
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
237
  AutoModel.register(NLLBLLM2VecConfig, NLLBLLM2Vec)
 
 
 
238
 
239
 
240
  def repl():
 
 
241
  cfg = NLLBLLM2VecConfig()
242
  model = NLLBLLM2Vec(cfg)
243
 
 
 
 
 
 
 
 
 
 
 
 
 
 
244
  from peft.mapping import get_peft_model
245
  from peft.tuners.lora.config import LoraConfig
246
 
@@ -483,94 +595,3 @@ def repl():
483
 
484
  with open("./model.safetensors.index.json", "r") as f:
485
  print(json.load(f))
486
-
487
-
488
- class NLLBLLM2VecForSequenceClassification(PreTrainedModel):
489
- def __init__(self, config):
490
- super().__init__(config)
491
- self.num_labels = config.num_labels
492
- self.model = NLLBLLM2Vec(config)
493
- self.score = nn.Linear(
494
- config.llm2vec_config.hidden_size, self.num_labels, bias=False
495
- )
496
-
497
- # Initialize weights and apply final processing
498
- self.post_init()
499
-
500
- def get_input_embeddings(self):
501
- return self.model.nllb.embed_tokens
502
-
503
- def set_input_embeddings(self, value):
504
- self.model.nllb.embed_tokens = value
505
-
506
- def forward(
507
- self,
508
- input_ids: Optional[torch.LongTensor] = None,
509
- attention_mask: Optional[torch.Tensor] = None,
510
- position_ids: Optional[torch.LongTensor] = None,
511
- past_key_values: Optional[Union[Cache, List[torch.FloatTensor]]] = None,
512
- inputs_embeds: Optional[torch.FloatTensor] = None,
513
- labels: Optional[torch.LongTensor] = None,
514
- use_cache: Optional[bool] = None,
515
- output_attentions: Optional[bool] = None,
516
- output_hidden_states: Optional[bool] = None,
517
- return_dict: Optional[bool] = None,
518
- ) -> Union[Tuple, SequenceClassifierOutputWithPast]:
519
- r"""
520
- labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
521
- Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
522
- config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
523
- `config.num_labels > 1` a classification loss is computed (Cross-Entropy).
524
- """
525
- return_dict = (
526
- return_dict if return_dict is not None else self.config.use_return_dict
527
- )
528
-
529
- transformer_outputs = self.model(
530
- input_ids,
531
- attention_mask=attention_mask,
532
- position_ids=position_ids,
533
- past_key_values=past_key_values,
534
- inputs_embeds=inputs_embeds,
535
- use_cache=use_cache,
536
- output_attentions=output_attentions,
537
- output_hidden_states=output_hidden_states,
538
- return_dict=return_dict,
539
- )
540
- hidden_states = transformer_outputs.pooler_output
541
- pooled_logits = self.score(hidden_states)
542
-
543
- loss = None
544
- if labels is not None:
545
- if self.config.problem_type is None:
546
- if self.num_labels == 1:
547
- self.config.problem_type = "regression"
548
- elif self.num_labels > 1 and (
549
- labels.dtype == torch.long or labels.dtype == torch.int
550
- ):
551
- self.config.problem_type = "single_label_classification"
552
- else:
553
- self.config.problem_type = "multi_label_classification"
554
-
555
- if self.config.problem_type == "regression":
556
- if self.num_labels == 1:
557
- loss = F.mse_loss(pooled_logits.squeeze(), labels.squeeze())
558
- else:
559
- loss = F.mse_loss(pooled_logits, labels)
560
- elif self.config.problem_type == "single_label_classification":
561
- loss = F.cross_entropy(
562
- pooled_logits.view(-1, self.num_labels), labels.view(-1)
563
- )
564
- elif self.config.problem_type == "multi_label_classification":
565
- loss = F.binary_cross_entropy_with_logits(pooled_logits, labels)
566
- if not return_dict:
567
- output = (pooled_logits,) + transformer_outputs[1:]
568
- return ((loss,) + output) if loss is not None else output
569
-
570
- return SequenceClassifierOutputWithPast(
571
- loss=loss,
572
- logits=pooled_logits,
573
- past_key_values=transformer_outputs.past_key_values,
574
- hidden_states=transformer_outputs.hidden_states,
575
- attentions=transformer_outputs.attentions,
576
- )
 
3
  import torch
4
  import torch.nn as nn
5
  import torch.nn.functional as F
6
+ from transformers.models.auto import AutoModel, AutoModelForSequenceClassification
7
  from transformers.modeling_outputs import (
8
  BaseModelOutputWithPooling,
9
  SequenceClassifierOutputWithPast,
 
18
 
19
  class NLLBLLM2Vec(PreTrainedModel):
20
  config_class = NLLBLLM2VecConfig
21
+ model_type = "nllb-llm2vec"
22
  """
23
  NLLBLLM2Vec model combining NLLB and LLama encoders.
24
 
 
30
  **kwargs: Additional keyword arguments.
31
  """
32
 
 
 
33
  def __init__(
34
  self,
35
  config: Optional[NLLBLLM2VecConfig] = None,
 
233
  )
234
 
235
 
236
+ class NLLBLLM2VecForSequenceClassification(PreTrainedModel):
237
+ config_class = NLLBLLM2VecConfig
238
+ model_type = "nllb-llm2vec"
239
+ base_model_prefix = "model"
240
+
241
+ def __init__(self, config):
242
+ super().__init__(config)
243
+ self.num_labels = config.num_labels
244
+ self.model = NLLBLLM2Vec(config)
245
+ self.score = nn.Linear(
246
+ config.llm2vec_config.hidden_size, self.num_labels, bias=False
247
+ )
248
+
249
+ # Initialize weights and apply final processing
250
+ self.post_init()
251
+
252
+ def get_input_embeddings(self):
253
+ return self.model.nllb.embed_tokens
254
+
255
+ def set_input_embeddings(self, value):
256
+ self.model.nllb.embed_tokens = value
257
+
258
+ def forward(
259
+ self,
260
+ input_ids: Optional[torch.LongTensor] = None,
261
+ attention_mask: Optional[torch.Tensor] = None,
262
+ position_ids: Optional[torch.LongTensor] = None,
263
+ past_key_values: Optional[Union[Cache, List[torch.FloatTensor]]] = None,
264
+ inputs_embeds: Optional[torch.FloatTensor] = None,
265
+ labels: Optional[torch.LongTensor] = None,
266
+ use_cache: Optional[bool] = None,
267
+ output_attentions: Optional[bool] = None,
268
+ output_hidden_states: Optional[bool] = None,
269
+ return_dict: Optional[bool] = None,
270
+ ) -> Union[Tuple, SequenceClassifierOutputWithPast]:
271
+ r"""
272
+ labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
273
+ Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
274
+ config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
275
+ `config.num_labels > 1` a classification loss is computed (Cross-Entropy).
276
+ """
277
+ return_dict = (
278
+ return_dict if return_dict is not None else self.config.use_return_dict
279
+ )
280
+
281
+ transformer_outputs = self.model(
282
+ input_ids,
283
+ attention_mask=attention_mask,
284
+ position_ids=position_ids,
285
+ past_key_values=past_key_values,
286
+ inputs_embeds=inputs_embeds,
287
+ use_cache=use_cache,
288
+ output_attentions=output_attentions,
289
+ output_hidden_states=output_hidden_states,
290
+ return_dict=return_dict,
291
+ )
292
+ hidden_states = transformer_outputs.pooler_output
293
+ pooled_logits = self.score(hidden_states)
294
+
295
+ loss = None
296
+ if labels is not None:
297
+ if self.config.problem_type is None:
298
+ if self.num_labels == 1:
299
+ self.config.problem_type = "regression"
300
+ elif self.num_labels > 1 and (
301
+ labels.dtype == torch.long or labels.dtype == torch.int
302
+ ):
303
+ self.config.problem_type = "single_label_classification"
304
+ else:
305
+ self.config.problem_type = "multi_label_classification"
306
+
307
+ if self.config.problem_type == "regression":
308
+ if self.num_labels == 1:
309
+ loss = F.mse_loss(pooled_logits.squeeze(), labels.squeeze())
310
+ else:
311
+ loss = F.mse_loss(pooled_logits, labels)
312
+ elif self.config.problem_type == "single_label_classification":
313
+ loss = F.cross_entropy(
314
+ pooled_logits.view(-1, self.num_labels), labels.view(-1)
315
+ )
316
+ elif self.config.problem_type == "multi_label_classification":
317
+ loss = F.binary_cross_entropy_with_logits(pooled_logits, labels)
318
+ if not return_dict:
319
+ output = (pooled_logits,) + transformer_outputs[1:]
320
+ return ((loss,) + output) if loss is not None else output
321
+
322
+ return SequenceClassifierOutputWithPast(
323
+ loss=loss,
324
+ logits=pooled_logits,
325
+ past_key_values=transformer_outputs.past_key_values,
326
+ hidden_states=transformer_outputs.hidden_states,
327
+ attentions=transformer_outputs.attentions,
328
+ )
329
+
330
+
331
  AutoModel.register(NLLBLLM2VecConfig, NLLBLLM2Vec)
332
+ AutoModelForSequenceClassification.register(
333
+ NLLBLLM2VecConfig, NLLBLLM2VecForSequenceClassification
334
+ )
335
 
336
 
337
  def repl():
338
+ from transformers import AutoModel
339
+
340
  cfg = NLLBLLM2VecConfig()
341
  model = NLLBLLM2Vec(cfg)
342
 
343
+ nllb = AutoModel.from_pretrained(
344
+ "facebook/nllb-200-distilled-600M", torch_dtype=torch.bfloat16
345
+ ).encoder
346
+ llm2vec = AutoModel.from_pretrained(
347
+ "fdschmidt93/LLM2Vec-Meta-Llama-3.1-8B-Instruct-mntp-unsup-simcse",
348
+ trust_remote_code=True,
349
+ torch_dtype=torch.bfloat16,
350
+ )
351
+
352
+ ckpt = torch.load("./step=20000-weights.ckpt", map_location="cpu")
353
+
354
+ model.up_proj.load_state_dict({"weight": proj})
355
+
356
  from peft.mapping import get_peft_model
357
  from peft.tuners.lora.config import LoraConfig
358
 
 
595
 
596
  with open("./model.safetensors.index.json", "r") as f:
597
  print(json.load(f))