Hugging Face's logo

Colder203
/
phi

PEFT
Safetensors
phi3
custom_code
Model card Files Community
Colder203 commited on
Commit
f70e903
·
verified ·
1 Parent(s): 96614c3

Training in progress, step 4000

Browse files
Files changed (9) hide show
  1. adapter_model.safetensors +1 -1
  2. config.json +144 -0
  3. last_checkpoint/added_tokens.json +14 -0
  4. last_checkpoint/special_tokens_map.json +30 -0
  5. last_checkpoint/tokenizer.model +3 -0
  6. last_checkpoint/tokenizer_config.json +140 -0
  7. model-00001-of-00002.safetensors +3 -0
  8. model-00002-of-00002.safetensors +3 -0
  9. model.safetensors.index.json +459 -0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78c3bb7039d22d35f997a02b2710474f991595d4907d9b25ffa8c93d4462f95d
3
  size 599376136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:703c66fd8285f04bc6edbeb2fb535abcde7d879930d576ec241e7b400d04c2c3
3
  size 599376136
config.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/Phi-3.5-mini-instruct",
3
+ "architectures": [
4
+ "Phi3ForSequenceClassification"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "microsoft/Phi-3.5-mini-instruct--configuration_phi3.Phi3Config",
10
+ "AutoModelForCausalLM": "microsoft/Phi-3.5-mini-instruct--modeling_phi3.Phi3ForCausalLM"
11
+ },
12
+ "bos_token_id": 1,
13
+ "embd_pdrop": 0.0,
14
+ "eos_token_id": 32000,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 3072,
17
+ "id2label": {
18
+ "0": "LABEL_0"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 8192,
22
+ "label2id": {
23
+ "LABEL_0": 0
24
+ },
25
+ "max_position_embeddings": 131072,
26
+ "model_type": "phi3",
27
+ "num_attention_heads": 32,
28
+ "num_hidden_layers": 32,
29
+ "num_key_value_heads": 32,
30
+ "original_max_position_embeddings": 4096,
31
+ "pad_token_id": 32011,
32
+ "resid_pdrop": 0.0,
33
+ "rms_norm_eps": 1e-05,
34
+ "rope_scaling": {
35
+ "long_factor": [
36
+ 1.0800000429153442,
37
+ 1.1100000143051147,
38
+ 1.1399999856948853,
39
+ 1.340000033378601,
40
+ 1.5899999141693115,
41
+ 1.600000023841858,
42
+ 1.6200000047683716,
43
+ 2.620000123977661,
44
+ 3.2300000190734863,
45
+ 3.2300000190734863,
46
+ 4.789999961853027,
47
+ 7.400000095367432,
48
+ 7.700000286102295,
49
+ 9.09000015258789,
50
+ 12.199999809265137,
51
+ 17.670000076293945,
52
+ 24.46000099182129,
53
+ 28.57000160217285,
54
+ 30.420001983642578,
55
+ 30.840002059936523,
56
+ 32.590003967285156,
57
+ 32.93000411987305,
58
+ 42.320003509521484,
59
+ 44.96000289916992,
60
+ 50.340003967285156,
61
+ 50.45000457763672,
62
+ 57.55000305175781,
63
+ 57.93000411987305,
64
+ 58.21000289916992,
65
+ 60.1400032043457,
66
+ 62.61000442504883,
67
+ 62.62000274658203,
68
+ 62.71000289916992,
69
+ 63.1400032043457,
70
+ 63.1400032043457,
71
+ 63.77000427246094,
72
+ 63.93000411987305,
73
+ 63.96000289916992,
74
+ 63.970001220703125,
75
+ 64.02999877929688,
76
+ 64.06999969482422,
77
+ 64.08000183105469,
78
+ 64.12000274658203,
79
+ 64.41000366210938,
80
+ 64.4800033569336,
81
+ 64.51000213623047,
82
+ 64.52999877929688,
83
+ 64.83999633789062
84
+ ],
85
+ "short_factor": [
86
+ 1.0,
87
+ 1.0199999809265137,
88
+ 1.0299999713897705,
89
+ 1.0299999713897705,
90
+ 1.0499999523162842,
91
+ 1.0499999523162842,
92
+ 1.0499999523162842,
93
+ 1.0499999523162842,
94
+ 1.0499999523162842,
95
+ 1.0699999332427979,
96
+ 1.0999999046325684,
97
+ 1.1099998950958252,
98
+ 1.1599998474121094,
99
+ 1.1599998474121094,
100
+ 1.1699998378753662,
101
+ 1.2899998426437378,
102
+ 1.339999794960022,
103
+ 1.679999828338623,
104
+ 1.7899998426437378,
105
+ 1.8199998140335083,
106
+ 1.8499997854232788,
107
+ 1.8799997568130493,
108
+ 1.9099997282028198,
109
+ 1.9399996995925903,
110
+ 1.9899996519088745,
111
+ 2.0199997425079346,
112
+ 2.0199997425079346,
113
+ 2.0199997425079346,
114
+ 2.0199997425079346,
115
+ 2.0199997425079346,
116
+ 2.0199997425079346,
117
+ 2.0299997329711914,
118
+ 2.0299997329711914,
119
+ 2.0299997329711914,
120
+ 2.0299997329711914,
121
+ 2.0299997329711914,
122
+ 2.0299997329711914,
123
+ 2.0299997329711914,
124
+ 2.0299997329711914,
125
+ 2.0299997329711914,
126
+ 2.0799996852874756,
127
+ 2.0899996757507324,
128
+ 2.189999580383301,
129
+ 2.2199995517730713,
130
+ 2.5899994373321533,
131
+ 2.729999542236328,
132
+ 2.749999523162842,
133
+ 2.8399994373321533
134
+ ],
135
+ "type": "longrope"
136
+ },
137
+ "rope_theta": 10000.0,
138
+ "sliding_window": 262144,
139
+ "tie_word_embeddings": false,
140
+ "torch_dtype": "bfloat16",
141
+ "transformers_version": "4.46.3",
142
+ "use_cache": false,
143
+ "vocab_size": 32012
144
+ }
last_checkpoint/added_tokens.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|assistant|>": 32001,
3
+ "<|endoftext|>": 32000,
4
+ "<|end|>": 32007,
5
+ "<|placeholder1|>": 32002,
6
+ "<|placeholder2|>": 32003,
7
+ "<|placeholder3|>": 32004,
8
+ "<|placeholder4|>": 32005,
9
+ "<|placeholder5|>": 32008,
10
+ "<|placeholder6|>": 32009,
11
+ "<|system|>": 32006,
12
+ "<|user|>": 32010,
13
+ "[PAD]": 32011
14
+ }
last_checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
last_checkpoint/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
last_checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,140 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "32000": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|assistant|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|placeholder1|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|placeholder2|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|placeholder3|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|placeholder4|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|system|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|placeholder5|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|placeholder6|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": true,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|user|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": true,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "32011": {
119
+ "content": "[PAD]",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": true
125
+ }
126
+ },
127
+ "bos_token": "<s>",
128
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
129
+ "clean_up_tokenization_spaces": false,
130
+ "eos_token": "<|endoftext|>",
131
+ "legacy": false,
132
+ "model_max_length": 4096,
133
+ "pad_token": "[PAD]",
134
+ "padding_side": "left",
135
+ "sp_model_kwargs": {},
136
+ "spaces_between_special_tokens": false,
137
+ "tokenizer_class": "LlamaTokenizer",
138
+ "unk_token": "<unk>",
139
+ "use_default_system_prompt": false
140
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17ae45d4e427afe22e5392b948759e30416fc0e83dc788e62dc33787f2f7ccdd
3
+ size 4998916936
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:beb86a54b735a5b90bc712455a10893e07b56706367573fe89f7b040bd8bb52e
3
+ size 2848643632
model.safetensors.index.json ADDED
@@ -0,0 +1,459 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 7847503872
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.mlp.gate_up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.mlp.gate_up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.0.self_attn.qkv_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.0.self_attn.qkv_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.mlp.gate_up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.mlp.gate_up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.1.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.1.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.1.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.1.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.1.self_attn.qkv_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.1.self_attn.qkv_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.10.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.10.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.10.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.10.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.10.mlp.gate_up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.10.mlp.gate_up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.10.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.10.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.10.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.10.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.10.self_attn.qkv_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.10.self_attn.qkv_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.11.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.11.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.11.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.11.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.11.mlp.gate_up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.11.mlp.gate_up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.11.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.11.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.11.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.11.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.11.self_attn.qkv_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.11.self_attn.qkv_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.12.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.12.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.12.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.12.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.12.mlp.gate_up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.12.mlp.gate_up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.12.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.12.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.12.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.12.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.12.self_attn.qkv_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.12.self_attn.qkv_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.13.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.13.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.13.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.13.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.13.mlp.gate_up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.13.mlp.gate_up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.13.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.13.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.13.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.13.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.13.self_attn.qkv_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.13.self_attn.qkv_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.14.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.14.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.14.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.14.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.14.mlp.gate_up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.14.mlp.gate_up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.14.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.14.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.14.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.14.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.14.self_attn.qkv_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.14.self_attn.qkv_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.15.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.15.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.15.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.15.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.15.mlp.gate_up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.15.mlp.gate_up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.15.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.15.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.15.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.15.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.15.self_attn.qkv_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.15.self_attn.qkv_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.16.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.16.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.16.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.16.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.16.mlp.gate_up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.16.mlp.gate_up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.16.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.16.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.16.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.16.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.16.self_attn.qkv_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.16.self_attn.qkv_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.17.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.17.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.17.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.17.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.17.mlp.gate_up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.17.mlp.gate_up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.17.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.17.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.17.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.17.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.17.self_attn.qkv_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.17.self_attn.qkv_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.18.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.18.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.18.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.18.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.18.mlp.gate_up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.18.mlp.gate_up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.18.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.18.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.18.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.18.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.18.self_attn.qkv_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.18.self_attn.qkv_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.19.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.19.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.19.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.19.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.19.mlp.gate_up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.19.mlp.gate_up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.19.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.19.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.19.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.19.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.19.self_attn.qkv_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
174
+ "model.layers.19.self_attn.qkv_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.2.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.2.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.2.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.2.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
180
+ "model.layers.2.mlp.gate_up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.2.mlp.gate_up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
182
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.2.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
184
+ "model.layers.2.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.2.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
186
+ "model.layers.2.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.2.self_attn.qkv_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
188
+ "model.layers.2.self_attn.qkv_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.20.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.20.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.20.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
193
+ "model.layers.20.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
194
+ "model.layers.20.mlp.gate_up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.20.mlp.gate_up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
197
+ "model.layers.20.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.20.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.20.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
200
+ "model.layers.20.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00002.safetensors",
201
+ "model.layers.20.self_attn.qkv_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
202
+ "model.layers.20.self_attn.qkv_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
203
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
204
+ "model.layers.21.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
205
+ "model.layers.21.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
206
+ "model.layers.21.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
207
+ "model.layers.21.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
208
+ "model.layers.21.mlp.gate_up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
209
+ "model.layers.21.mlp.gate_up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
210
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
211
+ "model.layers.21.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
212
+ "model.layers.21.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
213
+ "model.layers.21.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
214
+ "model.layers.21.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00002.safetensors",
215
+ "model.layers.21.self_attn.qkv_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
216
+ "model.layers.21.self_attn.qkv_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
217
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
218
+ "model.layers.22.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
219
+ "model.layers.22.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
220
+ "model.layers.22.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
221
+ "model.layers.22.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
222
+ "model.layers.22.mlp.gate_up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
223
+ "model.layers.22.mlp.gate_up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
224
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
225
+ "model.layers.22.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.22.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
227
+ "model.layers.22.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
228
+ "model.layers.22.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00002.safetensors",
229
+ "model.layers.22.self_attn.qkv_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
230
+ "model.layers.22.self_attn.qkv_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
231
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
232
+ "model.layers.23.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
233
+ "model.layers.23.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
234
+ "model.layers.23.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
235
+ "model.layers.23.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
236
+ "model.layers.23.mlp.gate_up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
237
+ "model.layers.23.mlp.gate_up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
239
+ "model.layers.23.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
240
+ "model.layers.23.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
241
+ "model.layers.23.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
242
+ "model.layers.23.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00002.safetensors",
243
+ "model.layers.23.self_attn.qkv_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
244
+ "model.layers.23.self_attn.qkv_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
245
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
246
+ "model.layers.24.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
247
+ "model.layers.24.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
248
+ "model.layers.24.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
249
+ "model.layers.24.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
250
+ "model.layers.24.mlp.gate_up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
251
+ "model.layers.24.mlp.gate_up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
252
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
253
+ "model.layers.24.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
254
+ "model.layers.24.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
255
+ "model.layers.24.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
256
+ "model.layers.24.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00002.safetensors",
257
+ "model.layers.24.self_attn.qkv_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
258
+ "model.layers.24.self_attn.qkv_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
259
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
260
+ "model.layers.25.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
261
+ "model.layers.25.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
262
+ "model.layers.25.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
263
+ "model.layers.25.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
264
+ "model.layers.25.mlp.gate_up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
265
+ "model.layers.25.mlp.gate_up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
266
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
267
+ "model.layers.25.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
268
+ "model.layers.25.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
269
+ "model.layers.25.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
270
+ "model.layers.25.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00002.safetensors",
271
+ "model.layers.25.self_attn.qkv_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
272
+ "model.layers.25.self_attn.qkv_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
273
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
274
+ "model.layers.26.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
275
+ "model.layers.26.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
276
+ "model.layers.26.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
277
+ "model.layers.26.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
278
+ "model.layers.26.mlp.gate_up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
279
+ "model.layers.26.mlp.gate_up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
280
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
281
+ "model.layers.26.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
282
+ "model.layers.26.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
283
+ "model.layers.26.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
284
+ "model.layers.26.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00002.safetensors",
285
+ "model.layers.26.self_attn.qkv_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
286
+ "model.layers.26.self_attn.qkv_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
287
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
288
+ "model.layers.27.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
289
+ "model.layers.27.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
290
+ "model.layers.27.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
291
+ "model.layers.27.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
292
+ "model.layers.27.mlp.gate_up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
293
+ "model.layers.27.mlp.gate_up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
294
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
295
+ "model.layers.27.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
296
+ "model.layers.27.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
297
+ "model.layers.27.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
298
+ "model.layers.27.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00002.safetensors",
299
+ "model.layers.27.self_attn.qkv_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
300
+ "model.layers.27.self_attn.qkv_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
301
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
302
+ "model.layers.28.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
303
+ "model.layers.28.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
304
+ "model.layers.28.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
305
+ "model.layers.28.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
306
+ "model.layers.28.mlp.gate_up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
307
+ "model.layers.28.mlp.gate_up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
308
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
309
+ "model.layers.28.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
310
+ "model.layers.28.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
311
+ "model.layers.28.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
312
+ "model.layers.28.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00002.safetensors",
313
+ "model.layers.28.self_attn.qkv_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
314
+ "model.layers.28.self_attn.qkv_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
315
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
316
+ "model.layers.29.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
317
+ "model.layers.29.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
318
+ "model.layers.29.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
319
+ "model.layers.29.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
320
+ "model.layers.29.mlp.gate_up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
321
+ "model.layers.29.mlp.gate_up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
322
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
323
+ "model.layers.29.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
324
+ "model.layers.29.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
325
+ "model.layers.29.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
326
+ "model.layers.29.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00002.safetensors",
327
+ "model.layers.29.self_attn.qkv_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
328
+ "model.layers.29.self_attn.qkv_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
329
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
330
+ "model.layers.3.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
331
+ "model.layers.3.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
332
+ "model.layers.3.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
333
+ "model.layers.3.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
334
+ "model.layers.3.mlp.gate_up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
335
+ "model.layers.3.mlp.gate_up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
336
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
337
+ "model.layers.3.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
338
+ "model.layers.3.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
339
+ "model.layers.3.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
340
+ "model.layers.3.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00002.safetensors",
341
+ "model.layers.3.self_attn.qkv_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
342
+ "model.layers.3.self_attn.qkv_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
343
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
344
+ "model.layers.30.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
345
+ "model.layers.30.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
346
+ "model.layers.30.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
347
+ "model.layers.30.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
348
+ "model.layers.30.mlp.gate_up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
349
+ "model.layers.30.mlp.gate_up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
350
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
351
+ "model.layers.30.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
352
+ "model.layers.30.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
353
+ "model.layers.30.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
354
+ "model.layers.30.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00002.safetensors",
355
+ "model.layers.30.self_attn.qkv_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
356
+ "model.layers.30.self_attn.qkv_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
357
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
358
+ "model.layers.31.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
359
+ "model.layers.31.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
360
+ "model.layers.31.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
361
+ "model.layers.31.mlp.gate_up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
362
+ "model.layers.31.mlp.gate_up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
363
+ "model.layers.31.mlp.gate_up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
364
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
365
+ "model.layers.31.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
366
+ "model.layers.31.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
367
+ "model.layers.31.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
368
+ "model.layers.31.self_attn.qkv_proj.base_layer.weight": "model-00002-of-00002.safetensors",
369
+ "model.layers.31.self_attn.qkv_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
370
+ "model.layers.31.self_attn.qkv_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
371
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
372
+ "model.layers.4.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
373
+ "model.layers.4.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
374
+ "model.layers.4.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
375
+ "model.layers.4.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
376
+ "model.layers.4.mlp.gate_up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
377
+ "model.layers.4.mlp.gate_up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
378
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
379
+ "model.layers.4.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
380
+ "model.layers.4.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
381
+ "model.layers.4.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
382
+ "model.layers.4.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00002.safetensors",
383
+ "model.layers.4.self_attn.qkv_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
384
+ "model.layers.4.self_attn.qkv_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
385
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
386
+ "model.layers.5.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
387
+ "model.layers.5.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
388
+ "model.layers.5.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
389
+ "model.layers.5.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
390
+ "model.layers.5.mlp.gate_up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
391
+ "model.layers.5.mlp.gate_up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
392
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
393
+ "model.layers.5.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
394
+ "model.layers.5.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
395
+ "model.layers.5.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
396
+ "model.layers.5.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00002.safetensors",
397
+ "model.layers.5.self_attn.qkv_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
398
+ "model.layers.5.self_attn.qkv_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
399
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
400
+ "model.layers.6.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
401
+ "model.layers.6.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
402
+ "model.layers.6.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
403
+ "model.layers.6.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
404
+ "model.layers.6.mlp.gate_up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
405
+ "model.layers.6.mlp.gate_up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
406
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
407
+ "model.layers.6.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
408
+ "model.layers.6.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
409
+ "model.layers.6.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
410
+ "model.layers.6.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00002.safetensors",
411
+ "model.layers.6.self_attn.qkv_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
412
+ "model.layers.6.self_attn.qkv_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
413
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
414
+ "model.layers.7.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
415
+ "model.layers.7.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
416
+ "model.layers.7.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
417
+ "model.layers.7.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
418
+ "model.layers.7.mlp.gate_up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
419
+ "model.layers.7.mlp.gate_up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
420
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
421
+ "model.layers.7.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
422
+ "model.layers.7.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
423
+ "model.layers.7.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
424
+ "model.layers.7.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00002.safetensors",
425
+ "model.layers.7.self_attn.qkv_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
426
+ "model.layers.7.self_attn.qkv_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
427
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
428
+ "model.layers.8.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
429
+ "model.layers.8.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
430
+ "model.layers.8.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
431
+ "model.layers.8.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
432
+ "model.layers.8.mlp.gate_up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
433
+ "model.layers.8.mlp.gate_up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
434
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
435
+ "model.layers.8.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
436
+ "model.layers.8.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
437
+ "model.layers.8.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
438
+ "model.layers.8.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00002.safetensors",
439
+ "model.layers.8.self_attn.qkv_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
440
+ "model.layers.8.self_attn.qkv_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
441
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
442
+ "model.layers.9.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
443
+ "model.layers.9.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
444
+ "model.layers.9.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
445
+ "model.layers.9.mlp.gate_up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
446
+ "model.layers.9.mlp.gate_up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
447
+ "model.layers.9.mlp.gate_up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
448
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
449
+ "model.layers.9.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
450
+ "model.layers.9.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
451
+ "model.layers.9.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
452
+ "model.layers.9.self_attn.qkv_proj.base_layer.weight": "model-00001-of-00002.safetensors",
453
+ "model.layers.9.self_attn.qkv_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
454
+ "model.layers.9.self_attn.qkv_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
455
+ "model.norm.weight": "model-00002-of-00002.safetensors",
456
+ "score.modules_to_save.default.weight": "model-00002-of-00002.safetensors",
457
+ "score.original_module.weight": "model-00002-of-00002.safetensors"
458
+ }
459
+ }