Satwik11 commited on
Commit
828b667
1 Parent(s): 7a2036b

Upload folder using huggingface_hub

Browse files
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 +1,161 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/Phi-3.5-Mini-instruct",
3
+ "architectures": [
4
+ "Phi3ForCausalLM"
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
+ "initializer_range": 0.02,
18
+ "intermediate_size": 8192,
19
+ "max_position_embeddings": 131072,
20
+ "model_type": "phi3",
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 32,
23
+ "num_key_value_heads": 32,
24
+ "original_max_position_embeddings": 4096,
25
+ "pad_token_id": 32000,
26
+ "quantization_config": {
27
+ "amp": true,
28
+ "autoround_version": "0.3",
29
+ "bits": 4,
30
+ "damp_percent": 0.01,
31
+ "data_type": "int",
32
+ "desc_act": false,
33
+ "enable_minmax_tuning": true,
34
+ "enable_quanted_input": true,
35
+ "gradient_accumulate_steps": 4,
36
+ "group_size": 128,
37
+ "iters": 200,
38
+ "low_gpu_mem_usage": false,
39
+ "lr": 0.005,
40
+ "minmax_lr": 0.005,
41
+ "nsamples": 128,
42
+ "quant_method": "gptq",
43
+ "scale_dtype": "torch.float16",
44
+ "seqlen": 512,
45
+ "sym": false,
46
+ "train_bs": 2,
47
+ "true_sequential": false
48
+ },
49
+ "resid_pdrop": 0.0,
50
+ "rms_norm_eps": 1e-05,
51
+ "rope_scaling": {
52
+ "long_factor": [
53
+ 1.0800000429153442,
54
+ 1.1100000143051147,
55
+ 1.1399999856948853,
56
+ 1.340000033378601,
57
+ 1.5899999141693115,
58
+ 1.600000023841858,
59
+ 1.6200000047683716,
60
+ 2.620000123977661,
61
+ 3.2300000190734863,
62
+ 3.2300000190734863,
63
+ 4.789999961853027,
64
+ 7.400000095367432,
65
+ 7.700000286102295,
66
+ 9.09000015258789,
67
+ 12.199999809265137,
68
+ 17.670000076293945,
69
+ 24.46000099182129,
70
+ 28.57000160217285,
71
+ 30.420001983642578,
72
+ 30.840002059936523,
73
+ 32.590003967285156,
74
+ 32.93000411987305,
75
+ 42.320003509521484,
76
+ 44.96000289916992,
77
+ 50.340003967285156,
78
+ 50.45000457763672,
79
+ 57.55000305175781,
80
+ 57.93000411987305,
81
+ 58.21000289916992,
82
+ 60.1400032043457,
83
+ 62.61000442504883,
84
+ 62.62000274658203,
85
+ 62.71000289916992,
86
+ 63.1400032043457,
87
+ 63.1400032043457,
88
+ 63.77000427246094,
89
+ 63.93000411987305,
90
+ 63.96000289916992,
91
+ 63.970001220703125,
92
+ 64.02999877929688,
93
+ 64.06999969482422,
94
+ 64.08000183105469,
95
+ 64.12000274658203,
96
+ 64.41000366210938,
97
+ 64.4800033569336,
98
+ 64.51000213623047,
99
+ 64.52999877929688,
100
+ 64.83999633789062
101
+ ],
102
+ "short_factor": [
103
+ 1.0,
104
+ 1.0199999809265137,
105
+ 1.0299999713897705,
106
+ 1.0299999713897705,
107
+ 1.0499999523162842,
108
+ 1.0499999523162842,
109
+ 1.0499999523162842,
110
+ 1.0499999523162842,
111
+ 1.0499999523162842,
112
+ 1.0699999332427979,
113
+ 1.0999999046325684,
114
+ 1.1099998950958252,
115
+ 1.1599998474121094,
116
+ 1.1599998474121094,
117
+ 1.1699998378753662,
118
+ 1.2899998426437378,
119
+ 1.339999794960022,
120
+ 1.679999828338623,
121
+ 1.7899998426437378,
122
+ 1.8199998140335083,
123
+ 1.8499997854232788,
124
+ 1.8799997568130493,
125
+ 1.9099997282028198,
126
+ 1.9399996995925903,
127
+ 1.9899996519088745,
128
+ 2.0199997425079346,
129
+ 2.0199997425079346,
130
+ 2.0199997425079346,
131
+ 2.0199997425079346,
132
+ 2.0199997425079346,
133
+ 2.0199997425079346,
134
+ 2.0299997329711914,
135
+ 2.0299997329711914,
136
+ 2.0299997329711914,
137
+ 2.0299997329711914,
138
+ 2.0299997329711914,
139
+ 2.0299997329711914,
140
+ 2.0299997329711914,
141
+ 2.0299997329711914,
142
+ 2.0299997329711914,
143
+ 2.0799996852874756,
144
+ 2.0899996757507324,
145
+ 2.189999580383301,
146
+ 2.2199995517730713,
147
+ 2.5899994373321533,
148
+ 2.729999542236328,
149
+ 2.749999523162842,
150
+ 2.8399994373321533
151
+ ],
152
+ "type": "longrope"
153
+ },
154
+ "rope_theta": 10000.0,
155
+ "sliding_window": 262144,
156
+ "tie_word_embeddings": false,
157
+ "torch_dtype": "float16",
158
+ "transformers_version": "4.43.4",
159
+ "use_cache": true,
160
+ "vocab_size": 32064
161
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 32007,
6
+ 32001,
7
+ 32000
8
+ ],
9
+ "pad_token_id": 32000,
10
+ "transformers_version": "4.43.4"
11
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d4f36d44d1d0e838517163199f164189c204462a227dfcba2b4403bf817d6fa
3
+ size 2281459480
quantize_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 4,
3
+ "group_size": 128,
4
+ "sym": false,
5
+ "data_type": "int",
6
+ "enable_quanted_input": true,
7
+ "enable_minmax_tuning": true,
8
+ "seqlen": 512,
9
+ "train_bs": 2,
10
+ "scale_dtype": "torch.float16",
11
+ "lr": 0.005,
12
+ "minmax_lr": 0.005,
13
+ "gradient_accumulate_steps": 4,
14
+ "iters": 200,
15
+ "amp": true,
16
+ "nsamples": 128,
17
+ "low_gpu_mem_usage": false,
18
+ "autoround_version": "0.3",
19
+ "quant_method": "gptq",
20
+ "desc_act": false,
21
+ "true_sequential": false,
22
+ "damp_percent": 0.01
23
+ }
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 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
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
+ },
119
+ "bos_token": "<s>",
120
+ "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 %}",
121
+ "clean_up_tokenization_spaces": false,
122
+ "eos_token": "<|endoftext|>",
123
+ "legacy": false,
124
+ "model_max_length": 131072,
125
+ "pad_token": "<|endoftext|>",
126
+ "padding_side": "left",
127
+ "sp_model_kwargs": {},
128
+ "tokenizer_class": "LlamaTokenizer",
129
+ "unk_token": "<unk>",
130
+ "use_default_system_prompt": false
131
+ }