Hugging Face's logo

astroa7m
/
unichat-allam-sft

Text Generation
Transformers
TensorBoard
Safetensors
PEFT
Trained with AutoTrain
text-generation-inference
conversational
Model card Files
xet
 Metrics Community
astroa7m commited on
Commit
5dd660c
·
verified ·
1 Parent(s): 9316cee

Initial LoRA adapter upload

Browse files
Files changed (11) hide show
  1. README.md +48 -0
  2. adapter_config.json +37 -0
  3. adapter_model.safetensors +3 -0
  4. runs/Jun21_00-31-06_d528e647f2e3/events.out.tfevents.1750465890.d528e647f2e3.15799.0 +3 -0
  5. runs/Jun21_00-47-33_d528e647f2e3/events.out.tfevents.1750466877.d528e647f2e3.20220.0 +3 -0
  6. special_tokens_map.json +24 -0
  7. tokenizer.json +0 -0
  8. tokenizer.model +3 -0
  9. tokenizer_config.json +205 -0
  10. training_args.bin +3 -0
  11. training_params.json +50 -0
README.md ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - autotrain
4
+ - text-generation-inference
5
+ - text-generation
6
+ - peft
7
+ library_name: transformers
8
+ base_model: ALLaM-AI/ALLaM-7B-Instruct-preview
9
+ widget:
10
+ - messages:
11
+ - role: user
12
+ content: What is your favorite condiment?
13
+ license: other
14
+ datasets:
15
+ - astroa7m/chat_aou
16
+ ---
17
+
18
+ # Model Trained Using AutoTrain
19
+
20
+ This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
21
+
22
+ # Usage
23
+
24
+ ```python
25
+
26
+ from transformers import AutoModelForCausalLM, AutoTokenizer
27
+
28
+ model_path = "PATH_TO_THIS_REPO"
29
+
30
+ tokenizer = AutoTokenizer.from_pretrained(model_path)
31
+ model = AutoModelForCausalLM.from_pretrained(
32
+ model_path,
33
+ device_map="auto",
34
+ torch_dtype='auto'
35
+ ).eval()
36
+
37
+ # Prompt content: "hi"
38
+ messages = [
39
+ {"role": "user", "content": "hi"}
40
+ ]
41
+
42
+ input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
43
+ output_ids = model.generate(input_ids.to('cuda'))
44
+ response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
45
+
46
+ # Model response: "Hello! How can I assist you today?"
47
+ print(response)
48
+ ```
adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "ALLaM-AI/ALLaM-7B-Instruct-preview",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": false,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 128,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.05,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 64,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "gate_proj",
27
+ "k_proj",
28
+ "o_proj",
29
+ "up_proj",
30
+ "down_proj",
31
+ "v_proj",
32
+ "q_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dd4faae787532f374196284a801e788844b78f707984df2c59531e18e8c0e99
3
+ size 639691872
runs/Jun21_00-31-06_d528e647f2e3/events.out.tfevents.1750465890.d528e647f2e3.15799.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1951a4b55d4ac9dbb1889486f343300d93cce56e932bd86860f559b186082f6e
3
+ size 6337
runs/Jun21_00-47-33_d528e647f2e3/events.out.tfevents.1750466877.d528e647f2e3.20220.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c382af4f548e83fd3ca780409369c328c702d984365e0f7dfbcf6a0aeb3b5d2d
3
+ size 9277
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
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:feff3deb3537c4a47b77585053ad2aa00484da7907b188e0111cbed1f4592e67
3
+ size 1228714
tokenizer_config.json ADDED
@@ -0,0 +1,205 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "3": {
31
+ "content": "0",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "4": {
39
+ "content": "1",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "5": {
47
+ "content": "2",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "6": {
55
+ "content": "3",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "7": {
63
+ "content": "4",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "8": {
71
+ "content": "5",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "9": {
79
+ "content": "6",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "10": {
87
+ "content": "7",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "11": {
95
+ "content": "8",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "12": {
103
+ "content": "9",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "13": {
111
+ "content": "٠",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "14": {
119
+ "content": "١",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "15": {
127
+ "content": "٢",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "16": {
135
+ "content": "٣",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "17": {
143
+ "content": "٤",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "18": {
151
+ "content": "٥",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "19": {
159
+ "content": "٦",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "20": {
167
+ "content": "٧",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "21": {
175
+ "content": "٨",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "22": {
183
+ "content": "٩",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ }
190
+ },
191
+ "bos_token": "<s>",
192
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + ' [INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
193
+ "clean_up_tokenization_spaces": false,
194
+ "eos_token": "</s>",
195
+ "extra_special_tokens": {},
196
+ "legacy": false,
197
+ "model_max_length": 2048,
198
+ "pad_token": "</s>",
199
+ "padding_side": "right",
200
+ "sp_model_kwargs": {},
201
+ "spaces_between_special_tokens": false,
202
+ "tokenizer_class": "LlamaTokenizer",
203
+ "unk_token": "<unk>",
204
+ "use_default_system_prompt": false
205
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03dda352bd836edc93e1bdc9bb4cf2e992aec6403c43bf6dc4d243b67c3d44ea
3
+ size 6033
training_params.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "ALLaM-AI/ALLaM-7B-Instruct-preview",
3
+ "project_name": "unichat-allam-sft",
4
+ "data_path": "astroa7m/chat_aou",
5
+ "train_split": "train",
6
+ "valid_split": null,
7
+ "add_eos_token": true,
8
+ "block_size": 512,
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
+ "eval_strategy": "epoch",
17
+ "save_total_limit": 1,
18
+ "auto_find_batch_size": false,
19
+ "mixed_precision": "bf16",
20
+ "lr": 0.00002,
21
+ "epochs": 10,
22
+ "batch_size": 4,
23
+ "warmup_ratio": 0.05,
24
+ "gradient_accumulation": 4,
25
+ "optimizer": "adamw_torch",
26
+ "scheduler": "cosine",
27
+ "weight_decay": 0.0,
28
+ "max_grad_norm": 1.0,
29
+ "seed": 42,
30
+ "chat_template": "tokenizer",
31
+ "quantization": "int4",
32
+ "target_modules": "all-linear",
33
+ "merge_adapter": false,
34
+ "peft": true,
35
+ "lora_r": 64,
36
+ "lora_alpha": 128,
37
+ "lora_dropout": 0.05,
38
+ "model_ref": null,
39
+ "dpo_beta": 0.1,
40
+ "max_prompt_length": 1024,
41
+ "max_completion_length": 256,
42
+ "prompt_text_column": null,
43
+ "text_column": "messages",
44
+ "rejected_text_column": null,
45
+ "push_to_hub": false,
46
+ "username": "astroa7m",
47
+ "token": null,
48
+ "unsloth": false,
49
+ "distributed_backend": null
50
+ }