acayir64 commited on
Commit
d41220d
1 Parent(s): 1fa52a3

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ ---
14
+
15
+ # Model Trained Using AutoTrain
16
+
17
+ This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
18
+
19
+ # Usage
20
+
21
+ ```python
22
+
23
+ from transformers import AutoModelForCausalLM, AutoTokenizer
24
+
25
+ model_path = "PATH_TO_THIS_REPO"
26
+
27
+ tokenizer = AutoTokenizer.from_pretrained(model_path)
28
+ model = AutoModelForCausalLM.from_pretrained(
29
+ model_path,
30
+ device_map="auto",
31
+ torch_dtype='auto'
32
+ ).eval()
33
+
34
+ # Prompt content: "hi"
35
+ messages = [
36
+ {"role": "user", "content": "hi"}
37
+ ]
38
+
39
+ input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
40
+ output_ids = model.generate(input_ids.to('cuda'))
41
+ response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
42
+
43
+ # Model response: "Hello! How can I assist you today?"
44
+ print(response)
45
+ ```
added_tokens.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
3
+ "architectures": [
4
+ "Phi3ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config",
9
+ "AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM"
10
+ },
11
+ "bos_token_id": 1,
12
+ "embd_pdrop": 0.0,
13
+ "eos_token_id": 32000,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 3072,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 8192,
18
+ "max_position_embeddings": 4096,
19
+ "model_type": "phi3",
20
+ "num_attention_heads": 32,
21
+ "num_hidden_layers": 32,
22
+ "num_key_value_heads": 32,
23
+ "original_max_position_embeddings": 4096,
24
+ "pad_token_id": 32000,
25
+ "resid_pdrop": 0.0,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": null,
28
+ "rope_theta": 10000.0,
29
+ "sliding_window": 2047,
30
+ "tie_word_embeddings": false,
31
+ "torch_dtype": "float16",
32
+ "transformers_version": "4.40.1",
33
+ "use_cache": true,
34
+ "vocab_size": 32011
35
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 32000,
6
+ 32001,
7
+ 32007
8
+ ],
9
+ "pad_token_id": 32000,
10
+ "transformers_version": "4.40.1"
11
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2afd86611aba953055b5287cccde0e1f6fc01e68f46688e0b898898c81d4743
3
+ size 4972163568
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0054c3e1078e6a313999a374bf8e8f4972a604e6fcfec073c36c57d6fd41072
3
+ size 2669366856
model.safetensors.index.json ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 7641507840
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.10.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.11.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.12.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.12.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.13.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.13.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.14.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.14.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.15.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.15.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.16.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.16.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.17.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.17.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.18.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.18.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.19.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.19.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.20.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.20.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
93
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
94
+ "model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
95
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
96
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
98
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
99
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
100
+ "model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
101
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
102
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
103
+ "model.layers.22.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
104
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
105
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
106
+ "model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
107
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
108
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
109
+ "model.layers.23.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
110
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
111
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
112
+ "model.layers.24.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
113
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
114
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
115
+ "model.layers.24.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
116
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
117
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
118
+ "model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
119
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
120
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
121
+ "model.layers.25.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
122
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
123
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
124
+ "model.layers.26.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
125
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
126
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
127
+ "model.layers.26.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
128
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
129
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
130
+ "model.layers.27.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
131
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
132
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
133
+ "model.layers.27.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
134
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
135
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
136
+ "model.layers.28.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
137
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
138
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
139
+ "model.layers.28.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
140
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
141
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
142
+ "model.layers.29.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
143
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
144
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
145
+ "model.layers.29.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
146
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
153
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
154
+ "model.layers.30.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
155
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
156
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
157
+ "model.layers.30.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
158
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
159
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
160
+ "model.layers.31.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
161
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
162
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.31.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
164
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
174
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
180
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
182
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
184
+ "model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
186
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
188
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
190
+ "model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
193
+ "model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
194
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
196
+ "model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
200
+ "model.norm.weight": "model-00002-of-00002.safetensors"
201
+ }
202
+ }
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": "<|endoftext|>",
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<|endoftext|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|assistant|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32002": {
46
+ "content": "<|placeholder1|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32003": {
54
+ "content": "<|placeholder2|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "32004": {
62
+ "content": "<|placeholder3|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "32005": {
70
+ "content": "<|placeholder4|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "32006": {
78
+ "content": "<|system|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "32007": {
86
+ "content": "<|end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "32008": {
94
+ "content": "<|placeholder5|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "32009": {
102
+ "content": "<|placeholder6|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "32010": {
110
+ "content": "<|user|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ }
117
+ },
118
+ "bos_token": "<s>",
119
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|system|>' + '\n' + message['content'] + '<|end|>' + '\n'}}{% elif (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif message['role'] == 'assistant' %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
120
+ "clean_up_tokenization_spaces": false,
121
+ "eos_token": "<|endoftext|>",
122
+ "legacy": false,
123
+ "model_max_length": 1024,
124
+ "pad_token": "<|endoftext|>",
125
+ "padding_side": "left",
126
+ "sp_model_kwargs": {},
127
+ "tokenizer_class": "LlamaTokenizer",
128
+ "unk_token": "<unk>",
129
+ "use_default_system_prompt": false
130
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c40c0343d6dc616e59e1f96c6e1b1767e416f7cbaadf66513ee995ffdb12df4
3
+ size 4984
training_params.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "microsoft/Phi-3-mini-4k-instruct",
3
+ "project_name": "phi-3-colab-sft-merged",
4
+ "data_path": "timdettmers/openassistant-guanaco",
5
+ "train_split": "train",
6
+ "valid_split": null,
7
+ "add_eos_token": false,
8
+ "block_size": -1,
9
+ "model_max_length": 1024,
10
+ "padding": null,
11
+ "trainer": "sft",
12
+ "use_flash_attention_2": false,
13
+ "log": "none",
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": "bf16",
20
+ "lr": 0.0002,
21
+ "epochs": 1,
22
+ "batch_size": 4,
23
+ "warmup_ratio": 0.1,
24
+ "gradient_accumulation": 1,
25
+ "optimizer": "adamw_torch",
26
+ "scheduler": "linear",
27
+ "weight_decay": 0.0,
28
+ "max_grad_norm": 1.0,
29
+ "seed": 42,
30
+ "chat_template": null,
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",
45
+ "push_to_hub": true,
46
+ "username": "acayir64"
47
+ }