Hugging Face's logo

masatochi
/
tuning-84ba9757-9076-4822-ab9e-11135834d1dd

PEFT
Safetensors
llama
axolotl
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files Community
masatochi commited on
Commit
2ffc41b
•
1 Parent(s): 2d7afa5

Training in progress, step 5

Browse files
Files changed (9) hide show
  1. adapter_config.json +34 -0
  2. adapter_model.safetensors +3 -0
  3. added_tokens.json +13 -0
  4. config.json +151 -0
  5. special_tokens_map.json +30 -0
  6. tokenizer.json +0 -0
  7. tokenizer.model +3 -0
  8. tokenizer_config.json +131 -0
  9. training_args.bin +3 -0
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/Phi-3.5-mini-instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.06,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "down_proj",
24
+ "k_proj",
25
+ "v_proj",
26
+ "o_proj",
27
+ "up_proj",
28
+ "gate_proj",
29
+ "q_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:746646e7a6a6925ca7ebb29d53fcf0b1c0893b8f20d6362eeb750ff6f122341b
3
+ size 59827904
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 +1,151 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unsloth/Phi-3.5-mini-instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 32000,
10
+ "head_dim": 96,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 3072,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 8192,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 32,
21
+ "original_max_position_embeddings": 4096,
22
+ "pad_token_id": 32000,
23
+ "pretraining_tp": 1,
24
+ "quantization_config": {
25
+ "_load_in_4bit": false,
26
+ "_load_in_8bit": true,
27
+ "bnb_4bit_compute_dtype": "float32",
28
+ "bnb_4bit_quant_storage": "uint8",
29
+ "bnb_4bit_quant_type": "fp4",
30
+ "bnb_4bit_use_double_quant": false,
31
+ "llm_int8_enable_fp32_cpu_offload": false,
32
+ "llm_int8_has_fp16_weight": false,
33
+ "llm_int8_skip_modules": null,
34
+ "llm_int8_threshold": 6.0,
35
+ "load_in_4bit": false,
36
+ "load_in_8bit": true,
37
+ "quant_method": "bitsandbytes"
38
+ },
39
+ "rms_norm_eps": 1e-05,
40
+ "rope_scaling": {
41
+ "attention_factor": 32.0,
42
+ "factor": 32.0,
43
+ "long_factor": [
44
+ 1.0800000429153442,
45
+ 1.1100000143051147,
46
+ 1.1399999856948853,
47
+ 1.340000033378601,
48
+ 1.5899999141693115,
49
+ 1.600000023841858,
50
+ 1.6200000047683716,
51
+ 2.620000123977661,
52
+ 3.2300000190734863,
53
+ 3.2300000190734863,
54
+ 4.789999961853027,
55
+ 7.400000095367432,
56
+ 7.700000286102295,
57
+ 9.09000015258789,
58
+ 12.199999809265137,
59
+ 17.670000076293945,
60
+ 24.46000099182129,
61
+ 28.57000160217285,
62
+ 30.420001983642578,
63
+ 30.840002059936523,
64
+ 32.590003967285156,
65
+ 32.93000411987305,
66
+ 42.320003509521484,
67
+ 44.96000289916992,
68
+ 50.340003967285156,
69
+ 50.45000457763672,
70
+ 57.55000305175781,
71
+ 57.93000411987305,
72
+ 58.21000289916992,
73
+ 60.1400032043457,
74
+ 62.61000442504883,
75
+ 62.62000274658203,
76
+ 62.71000289916992,
77
+ 63.1400032043457,
78
+ 63.1400032043457,
79
+ 63.77000427246094,
80
+ 63.93000411987305,
81
+ 63.96000289916992,
82
+ 63.970001220703125,
83
+ 64.02999877929688,
84
+ 64.06999969482422,
85
+ 64.08000183105469,
86
+ 64.12000274658203,
87
+ 64.41000366210938,
88
+ 64.4800033569336,
89
+ 64.51000213623047,
90
+ 64.52999877929688,
91
+ 64.83999633789062
92
+ ],
93
+ "rope_type": "longrope",
94
+ "short_factor": [
95
+ 1.0,
96
+ 1.0199999809265137,
97
+ 1.0299999713897705,
98
+ 1.0299999713897705,
99
+ 1.0499999523162842,
100
+ 1.0499999523162842,
101
+ 1.0499999523162842,
102
+ 1.0499999523162842,
103
+ 1.0499999523162842,
104
+ 1.0699999332427979,
105
+ 1.0999999046325684,
106
+ 1.1099998950958252,
107
+ 1.1599998474121094,
108
+ 1.1599998474121094,
109
+ 1.1699998378753662,
110
+ 1.2899998426437378,
111
+ 1.339999794960022,
112
+ 1.679999828338623,
113
+ 1.7899998426437378,
114
+ 1.8199998140335083,
115
+ 1.8499997854232788,
116
+ 1.8799997568130493,
117
+ 1.9099997282028198,
118
+ 1.9399996995925903,
119
+ 1.9899996519088745,
120
+ 2.0199997425079346,
121
+ 2.0199997425079346,
122
+ 2.0199997425079346,
123
+ 2.0199997425079346,
124
+ 2.0199997425079346,
125
+ 2.0199997425079346,
126
+ 2.0299997329711914,
127
+ 2.0299997329711914,
128
+ 2.0299997329711914,
129
+ 2.0299997329711914,
130
+ 2.0299997329711914,
131
+ 2.0299997329711914,
132
+ 2.0299997329711914,
133
+ 2.0299997329711914,
134
+ 2.0299997329711914,
135
+ 2.0799996852874756,
136
+ 2.0899996757507324,
137
+ 2.189999580383301,
138
+ 2.2199995517730713,
139
+ 2.5899994373321533,
140
+ 2.729999542236328,
141
+ 2.749999523162842,
142
+ 2.8399994373321533
143
+ ]
144
+ },
145
+ "rope_theta": 10000.0,
146
+ "tie_word_embeddings": false,
147
+ "torch_dtype": "bfloat16",
148
+ "transformers_version": "4.45.2",
149
+ "use_cache": false,
150
+ "vocab_size": 32064
151
+ }
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": "<|placeholder6|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": true,
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": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
121
+ "clean_up_tokenization_spaces": false,
122
+ "eos_token": "<|endoftext|>",
123
+ "legacy": false,
124
+ "model_max_length": 131072,
125
+ "pad_token": "<|placeholder6|>",
126
+ "padding_side": "left",
127
+ "sp_model_kwargs": {},
128
+ "tokenizer_class": "LlamaTokenizer",
129
+ "unk_token": "<unk>",
130
+ "use_default_system_prompt": false
131
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8f36f55020b2c01be7685ba45cb6ea57ee9623bbcf0e9bf399291e5cdd26e9e
3
+ size 6712