imdatta0 commited on
Commit
93a8751
1 Parent(s): 613253c

Training in progress, step 4

Browse files
adapter_config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2-7B",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": [
11
+ 0,
12
+ 1,
13
+ 2,
14
+ 3,
15
+ 4,
16
+ 5,
17
+ 6,
18
+ 7,
19
+ 8,
20
+ 9,
21
+ 10,
22
+ 11,
23
+ 12,
24
+ 13,
25
+ 14,
26
+ 15,
27
+ 16,
28
+ 17,
29
+ 18,
30
+ 19,
31
+ 20,
32
+ 21,
33
+ 22,
34
+ 23,
35
+ 24,
36
+ 25,
37
+ 26,
38
+ 27,
39
+ 28,
40
+ 29,
41
+ 30,
42
+ 31,
43
+ 32,
44
+ 33,
45
+ 34,
46
+ 35,
47
+ 36,
48
+ 37,
49
+ 38,
50
+ 39,
51
+ 40
52
+ ],
53
+ "loftq_config": {},
54
+ "lora_alpha": 16,
55
+ "lora_dropout": 0,
56
+ "megatron_config": null,
57
+ "megatron_core": "megatron.core",
58
+ "modules_to_save": null,
59
+ "peft_type": "LORA",
60
+ "r": 8,
61
+ "rank_pattern": {},
62
+ "revision": "unsloth",
63
+ "target_modules": [
64
+ "down_proj",
65
+ "gate_proj",
66
+ "up_proj",
67
+ "v_proj",
68
+ "o_proj",
69
+ "k_proj",
70
+ "q_proj"
71
+ ],
72
+ "task_type": "CAUSAL_LM"
73
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e656a7699f454d004d85ecceb9c77dd561320eaf8c40524809bb804fc71844f5
3
+ size 80792096
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<|PAD_TOKEN|>": 151646,
3
+ "<|endoftext|>": 151643,
4
+ "<|im_end|>": 151645,
5
+ "<|im_start|>": 151644
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": "<|PAD_TOKEN|>"
14
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<|PAD_TOKEN|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ }
36
+ },
37
+ "additional_special_tokens": [
38
+ "<|im_start|>",
39
+ "<|im_end|>"
40
+ ],
41
+ "bos_token": null,
42
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
43
+ "clean_up_tokenization_spaces": false,
44
+ "eos_token": "<|endoftext|>",
45
+ "errors": "replace",
46
+ "model_max_length": 131072,
47
+ "pad_token": "<|PAD_TOKEN|>",
48
+ "padding_side": "right",
49
+ "split_special_tokens": false,
50
+ "tokenizer_class": "Qwen2Tokenizer",
51
+ "unk_token": null
52
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa3a489cc57e3024d685dd01277446e55fca671a1941439732202b34b3b9fadf
3
+ size 5112
vocab.json ADDED
The diff for this file is too large to render. See raw diff