jcarbonnell commited on
Commit
0cb9c28
1 Parent(s): 73138df

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - autotrain
4
+ - text-generation-inference
5
+ - text-generation
6
+ - peft
7
+ library_name: transformers
8
+ widget:
9
+ - messages:
10
+ - role: user
11
+ content: What is your favorite condiment?
12
+ license: other
13
+ datasets:
14
+ - jcarbonnell/preTrainingNEAR
15
+ ---
16
+
17
+ # Model Trained Using AutoTrain
18
+
19
+ This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
20
+
21
+ # Usage
22
+
23
+ ```python
24
+
25
+ from transformers import AutoModelForCausalLM, AutoTokenizer
26
+
27
+ model_path = "PATH_TO_THIS_REPO"
28
+
29
+ tokenizer = AutoTokenizer.from_pretrained(model_path)
30
+ model = AutoModelForCausalLM.from_pretrained(
31
+ model_path,
32
+ device_map="auto",
33
+ torch_dtype='auto'
34
+ ).eval()
35
+
36
+ # Prompt content: "hi"
37
+ messages = [
38
+ {"role": "user", "content": "hi"}
39
+ ]
40
+
41
+ input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
42
+ output_ids = model.generate(input_ids.to('cuda'))
43
+ response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
44
+
45
+ # Model response: "Hello! How can I assist you today?"
46
+ print(response)
47
+ ```
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bigcode/starcoder2-3b",
3
+ "architectures": [
4
+ "Starcoder2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "bos_token_id": 0,
8
+ "embedding_dropout": 0.1,
9
+ "eos_token_id": 0,
10
+ "hidden_act": "gelu_pytorch_tanh",
11
+ "hidden_size": 3072,
12
+ "initializer_range": 0.018042,
13
+ "intermediate_size": 12288,
14
+ "max_position_embeddings": 16384,
15
+ "mlp_type": "default",
16
+ "model_type": "starcoder2",
17
+ "norm_epsilon": 1e-05,
18
+ "norm_type": "layer_norm",
19
+ "num_attention_heads": 24,
20
+ "num_hidden_layers": 30,
21
+ "num_key_value_heads": 2,
22
+ "residual_dropout": 0.1,
23
+ "rope_theta": 999999.4420358813,
24
+ "sliding_window": 4096,
25
+ "torch_dtype": "float16",
26
+ "transformers_version": "4.41.0",
27
+ "use_bias": true,
28
+ "use_cache": true,
29
+ "vocab_size": 49152
30
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.41.0"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:084ace1c64e90f53531a7c1203e8d36aa63849cd8456df26d52a6b79aa1c3b4f
3
+ size 4949933808
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8c9f56bcfb86ee778f1ebe26a31861e15c1f8e5655dd222af8174851d4ed7c5
3
+ size 1110862480
model.safetensors.index.json ADDED
@@ -0,0 +1,490 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6060742656
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "model.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
20
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
22
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
28
+ "model.layers.1.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.1.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
30
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
32
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.1.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
34
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
36
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
38
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
40
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.10.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
42
+ "model.layers.10.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.10.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
44
+ "model.layers.10.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.10.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
46
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
48
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.10.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
50
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
52
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
54
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
56
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.11.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
58
+ "model.layers.11.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.11.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
60
+ "model.layers.11.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.11.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
62
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
64
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.11.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
66
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
68
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
70
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
72
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.12.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
74
+ "model.layers.12.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.12.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
76
+ "model.layers.12.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.12.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
78
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
80
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.12.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
82
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
84
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
86
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
88
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.13.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
90
+ "model.layers.13.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.13.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
92
+ "model.layers.13.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.13.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
94
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
96
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.13.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
98
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
100
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
102
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
104
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.14.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
106
+ "model.layers.14.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.14.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
108
+ "model.layers.14.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.14.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
110
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
112
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.14.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
114
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
116
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
118
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
120
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.15.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
122
+ "model.layers.15.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.15.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
124
+ "model.layers.15.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.15.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
126
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
128
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.15.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
130
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
132
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
134
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
136
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.16.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
138
+ "model.layers.16.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.16.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
140
+ "model.layers.16.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.16.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
142
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
144
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.16.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
146
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
148
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
150
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
152
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.17.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
154
+ "model.layers.17.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.17.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
156
+ "model.layers.17.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.17.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
158
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
160
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.17.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
162
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
164
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
166
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
168
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.18.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
170
+ "model.layers.18.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.18.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
172
+ "model.layers.18.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.18.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
174
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
176
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.18.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
178
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
180
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
182
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
184
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.19.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
186
+ "model.layers.19.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.19.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
188
+ "model.layers.19.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.19.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
190
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
192
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
193
+ "model.layers.19.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
194
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
196
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
198
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
200
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.2.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
202
+ "model.layers.2.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.2.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
204
+ "model.layers.2.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.2.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
206
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
208
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.2.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
210
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
211
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
212
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
214
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
216
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.20.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
218
+ "model.layers.20.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.20.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
220
+ "model.layers.20.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.20.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
222
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
224
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
225
+ "model.layers.20.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
226
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
228
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
229
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
230
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
232
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
233
+ "model.layers.21.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
234
+ "model.layers.21.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
235
+ "model.layers.21.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
236
+ "model.layers.21.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
237
+ "model.layers.21.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
238
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
240
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
241
+ "model.layers.21.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
242
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
244
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
246
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
248
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.22.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
250
+ "model.layers.22.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.22.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
252
+ "model.layers.22.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.22.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
254
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
256
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.22.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
258
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
260
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
261
+ "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
262
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.23.input_layernorm.bias": "model-00001-of-00002.safetensors",
264
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.23.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
266
+ "model.layers.23.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.23.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
268
+ "model.layers.23.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.23.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
270
+ "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
272
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.23.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
274
+ "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
275
+ "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
276
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
277
+ "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
278
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
279
+ "model.layers.24.input_layernorm.bias": "model-00002-of-00002.safetensors",
280
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
281
+ "model.layers.24.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
282
+ "model.layers.24.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
283
+ "model.layers.24.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
284
+ "model.layers.24.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
285
+ "model.layers.24.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
286
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
287
+ "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
288
+ "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.24.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
290
+ "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
292
+ "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
293
+ "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
294
+ "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
295
+ "model.layers.25.input_layernorm.bias": "model-00002-of-00002.safetensors",
296
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
297
+ "model.layers.25.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
298
+ "model.layers.25.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
299
+ "model.layers.25.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
300
+ "model.layers.25.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
301
+ "model.layers.25.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
302
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
303
+ "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
304
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
305
+ "model.layers.25.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
306
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
307
+ "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
308
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
309
+ "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
310
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
311
+ "model.layers.26.input_layernorm.bias": "model-00002-of-00002.safetensors",
312
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
313
+ "model.layers.26.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
314
+ "model.layers.26.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
315
+ "model.layers.26.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
316
+ "model.layers.26.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
317
+ "model.layers.26.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
318
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
319
+ "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
320
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
321
+ "model.layers.26.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
322
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
323
+ "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
324
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
325
+ "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
326
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
327
+ "model.layers.27.input_layernorm.bias": "model-00002-of-00002.safetensors",
328
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
329
+ "model.layers.27.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
330
+ "model.layers.27.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
331
+ "model.layers.27.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
332
+ "model.layers.27.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
333
+ "model.layers.27.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
334
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
335
+ "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
336
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
337
+ "model.layers.27.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
338
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
339
+ "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
340
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
341
+ "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
342
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
343
+ "model.layers.28.input_layernorm.bias": "model-00002-of-00002.safetensors",
344
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
345
+ "model.layers.28.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
346
+ "model.layers.28.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
347
+ "model.layers.28.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
348
+ "model.layers.28.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
349
+ "model.layers.28.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
350
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
351
+ "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
352
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
353
+ "model.layers.28.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
354
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
355
+ "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
356
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
357
+ "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
358
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
359
+ "model.layers.29.input_layernorm.bias": "model-00002-of-00002.safetensors",
360
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
361
+ "model.layers.29.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
362
+ "model.layers.29.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
363
+ "model.layers.29.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
364
+ "model.layers.29.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
365
+ "model.layers.29.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
366
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
367
+ "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
368
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
369
+ "model.layers.29.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
370
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
371
+ "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
372
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
373
+ "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
374
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
375
+ "model.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
376
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
377
+ "model.layers.3.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
378
+ "model.layers.3.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
379
+ "model.layers.3.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
380
+ "model.layers.3.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
381
+ "model.layers.3.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
382
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
383
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
384
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
385
+ "model.layers.3.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
386
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
387
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
388
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
389
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
390
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
391
+ "model.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
392
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
393
+ "model.layers.4.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
394
+ "model.layers.4.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
395
+ "model.layers.4.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
396
+ "model.layers.4.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
397
+ "model.layers.4.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
398
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
399
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
400
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
401
+ "model.layers.4.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
402
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
403
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
404
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
405
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
406
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
407
+ "model.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
408
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
409
+ "model.layers.5.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
410
+ "model.layers.5.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
411
+ "model.layers.5.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
412
+ "model.layers.5.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
413
+ "model.layers.5.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
414
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
415
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
416
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
417
+ "model.layers.5.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
418
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
419
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
420
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
421
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
422
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
423
+ "model.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
424
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
425
+ "model.layers.6.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
426
+ "model.layers.6.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
427
+ "model.layers.6.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
428
+ "model.layers.6.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
429
+ "model.layers.6.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
430
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
431
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
432
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
433
+ "model.layers.6.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
434
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
435
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
436
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
437
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
438
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
439
+ "model.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
440
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
441
+ "model.layers.7.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
442
+ "model.layers.7.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
443
+ "model.layers.7.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
444
+ "model.layers.7.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
445
+ "model.layers.7.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
446
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
447
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
448
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
449
+ "model.layers.7.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
450
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
451
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
452
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
453
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
454
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
455
+ "model.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
456
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
457
+ "model.layers.8.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
458
+ "model.layers.8.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
459
+ "model.layers.8.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
460
+ "model.layers.8.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
461
+ "model.layers.8.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
462
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
463
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
464
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
465
+ "model.layers.8.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
466
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
467
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
468
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
469
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
470
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
471
+ "model.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
472
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
473
+ "model.layers.9.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
474
+ "model.layers.9.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
475
+ "model.layers.9.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
476
+ "model.layers.9.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
477
+ "model.layers.9.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
478
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
479
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
480
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
481
+ "model.layers.9.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
482
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
483
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
484
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
485
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
486
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
487
+ "model.norm.bias": "model-00002-of-00002.safetensors",
488
+ "model.norm.weight": "model-00002-of-00002.safetensors"
489
+ }
490
+ }
runs/May29_00-37-33_r-jcarbonnell-autotrain-advanced-vil8j031-f0812-qkoaq/events.out.tfevents.1716943070.r-jcarbonnell-autotrain-advanced-vil8j031-f0812-qkoaq.156.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b12eb7fc4ec27dca4fbb8bc07f5c7ac6ff7a5b74a3419957cef92fa782bf3df
3
- size 10500
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c72c54b22d643dae72efef6db8a27daca4cdfaa643aa925e96af61936a7d3cef
3
+ size 11276
special_tokens_map.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<fim_prefix>",
5
+ "<fim_middle>",
6
+ "<fim_suffix>",
7
+ "<fim_pad>",
8
+ "<repo_name>",
9
+ "<file_sep>",
10
+ "<issue_start>",
11
+ "<issue_comment>",
12
+ "<issue_closed>",
13
+ "<jupyter_start>",
14
+ "<jupyter_text>",
15
+ "<jupyter_code>",
16
+ "<jupyter_output>",
17
+ "<jupyter_script>",
18
+ "<empty_output>",
19
+ "<code_to_intermediate>",
20
+ "<intermediate_to_code>",
21
+ "<pr>",
22
+ "<pr_status>",
23
+ "<pr_is_merged>",
24
+ "<pr_base>",
25
+ "<pr_file>",
26
+ "<pr_base_code>",
27
+ "<pr_diff>",
28
+ "<pr_diff_hunk>",
29
+ "<pr_comment>",
30
+ "<pr_event_id>",
31
+ "<pr_review>",
32
+ "<pr_review_state>",
33
+ "<pr_review_comment>",
34
+ "<pr_in_reply_to_review_id>",
35
+ "<pr_in_reply_to_comment_id>",
36
+ "<pr_diff_hunk_comment_line>",
37
+ "<NAME>",
38
+ "<EMAIL>",
39
+ "<KEY>",
40
+ "<PASSWORD>"
41
+ ],
42
+ "bos_token": {
43
+ "content": "<|endoftext|>",
44
+ "lstrip": false,
45
+ "normalized": false,
46
+ "rstrip": false,
47
+ "single_word": false
48
+ },
49
+ "eos_token": {
50
+ "content": "<|endoftext|>",
51
+ "lstrip": false,
52
+ "normalized": false,
53
+ "rstrip": false,
54
+ "single_word": false
55
+ },
56
+ "pad_token": {
57
+ "content": "<|endoftext|>",
58
+ "lstrip": false,
59
+ "normalized": false,
60
+ "rstrip": false,
61
+ "single_word": false
62
+ },
63
+ "unk_token": {
64
+ "content": "<|endoftext|>",
65
+ "lstrip": false,
66
+ "normalized": false,
67
+ "rstrip": false,
68
+ "single_word": false
69
+ }
70
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,358 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<fim_prefix>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<fim_middle>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<fim_suffix>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<fim_pad>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<repo_name>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<file_sep>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<issue_start>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_comment>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_closed>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<jupyter_start>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_text>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_code>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_output>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<jupyter_script>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<empty_output>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<code_to_intermediate>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "17": {
141
+ "content": "<intermediate_to_code>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "18": {
149
+ "content": "<pr>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "19": {
157
+ "content": "<pr_status>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "20": {
165
+ "content": "<pr_is_merged>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "21": {
173
+ "content": "<pr_base>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "22": {
181
+ "content": "<pr_file>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "23": {
189
+ "content": "<pr_base_code>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "24": {
197
+ "content": "<pr_diff>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "25": {
205
+ "content": "<pr_diff_hunk>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "26": {
213
+ "content": "<pr_comment>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "27": {
221
+ "content": "<pr_event_id>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "28": {
229
+ "content": "<pr_review>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "29": {
237
+ "content": "<pr_review_state>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "30": {
245
+ "content": "<pr_review_comment>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "31": {
253
+ "content": "<pr_in_reply_to_review_id>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "32": {
261
+ "content": "<pr_in_reply_to_comment_id>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "33": {
269
+ "content": "<pr_diff_hunk_comment_line>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "34": {
277
+ "content": "<NAME>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "35": {
285
+ "content": "<EMAIL>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "36": {
293
+ "content": "<KEY>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "37": {
301
+ "content": "<PASSWORD>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ }
308
+ },
309
+ "additional_special_tokens": [
310
+ "<|endoftext|>",
311
+ "<fim_prefix>",
312
+ "<fim_middle>",
313
+ "<fim_suffix>",
314
+ "<fim_pad>",
315
+ "<repo_name>",
316
+ "<file_sep>",
317
+ "<issue_start>",
318
+ "<issue_comment>",
319
+ "<issue_closed>",
320
+ "<jupyter_start>",
321
+ "<jupyter_text>",
322
+ "<jupyter_code>",
323
+ "<jupyter_output>",
324
+ "<jupyter_script>",
325
+ "<empty_output>",
326
+ "<code_to_intermediate>",
327
+ "<intermediate_to_code>",
328
+ "<pr>",
329
+ "<pr_status>",
330
+ "<pr_is_merged>",
331
+ "<pr_base>",
332
+ "<pr_file>",
333
+ "<pr_base_code>",
334
+ "<pr_diff>",
335
+ "<pr_diff_hunk>",
336
+ "<pr_comment>",
337
+ "<pr_event_id>",
338
+ "<pr_review>",
339
+ "<pr_review_state>",
340
+ "<pr_review_comment>",
341
+ "<pr_in_reply_to_review_id>",
342
+ "<pr_in_reply_to_comment_id>",
343
+ "<pr_diff_hunk_comment_line>",
344
+ "<NAME>",
345
+ "<EMAIL>",
346
+ "<KEY>",
347
+ "<PASSWORD>"
348
+ ],
349
+ "bos_token": "<|endoftext|>",
350
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
351
+ "clean_up_tokenization_spaces": true,
352
+ "eos_token": "<|endoftext|>",
353
+ "model_max_length": 2048,
354
+ "pad_token": "<|endoftext|>",
355
+ "tokenizer_class": "GPT2Tokenizer",
356
+ "unk_token": "<|endoftext|>",
357
+ "vocab_size": 49152
358
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cee78318480c0f967324e0c75c245a12fee1709758269716b8134d150679623
3
+ size 5176
training_params.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "bigcode/starcoder2-3b",
3
+ "project_name": "autotrain-dwkfh-tfrgf",
4
+ "data_path": "jcarbonnell/preTrainingNEAR",
5
+ "train_split": "train",
6
+ "valid_split": null,
7
+ "add_eos_token": true,
8
+ "block_size": 1024,
9
+ "model_max_length": 2048,
10
+ "padding": "right",
11
+ "trainer": "sft",
12
+ "use_flash_attention_2": false,
13
+ "log": "tensorboard",
14
+ "disable_gradient_checkpointing": false,
15
+ "logging_steps": -1,
16
+ "evaluation_strategy": "epoch",
17
+ "save_total_limit": 1,
18
+ "auto_find_batch_size": false,
19
+ "mixed_precision": "fp16",
20
+ "lr": 3e-05,
21
+ "epochs": 3,
22
+ "batch_size": 2,
23
+ "warmup_ratio": 0.1,
24
+ "gradient_accumulation": 4,
25
+ "optimizer": "adamw_torch",
26
+ "scheduler": "linear",
27
+ "weight_decay": 0.0,
28
+ "max_grad_norm": 1.0,
29
+ "seed": 42,
30
+ "chat_template": "none",
31
+ "quantization": "int4",
32
+ "target_modules": "all-linear",
33
+ "merge_adapter": true,
34
+ "peft": true,
35
+ "lora_r": 16,
36
+ "lora_alpha": 32,
37
+ "lora_dropout": 0.05,
38
+ "model_ref": null,
39
+ "dpo_beta": 0.1,
40
+ "max_prompt_length": 128,
41
+ "max_completion_length": null,
42
+ "prompt_text_column": "prompt",
43
+ "text_column": "text",
44
+ "rejected_text_column": "rejected_text",
45
+ "push_to_hub": true,
46
+ "username": "jcarbonnell"
47
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff