Hugging Face's logo

Syzseisus
/
LCK_LLM3

Safetensors
Model card Files Community
Syzseisus commited on
Commit
9ffcf90
•
1 Parent(s): bf54551

Upload 10 files

Browse files
Files changed (10) hide show
  1. adapter_config.json +45 -0
  2. adapter_model.safetensors +3 -0
  3. optimizer.pt +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. special_tokens_map.json +23 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +67 -0
  9. trainer_state.json +0 -0
  10. training_args.bin +3 -0
adapter_config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "vaiv/GeM2-Llamion-14B-Base",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": [
12
+ 30,
13
+ 31,
14
+ 32,
15
+ 33,
16
+ 34,
17
+ 35,
18
+ 36,
19
+ 37,
20
+ 38,
21
+ 39
22
+ ],
23
+ "loftq_config": {},
24
+ "lora_alpha": 8,
25
+ "lora_dropout": 0.05,
26
+ "megatron_config": null,
27
+ "megatron_core": "megatron.core",
28
+ "modules_to_save": null,
29
+ "peft_type": "LORA",
30
+ "r": 6,
31
+ "rank_pattern": {},
32
+ "revision": null,
33
+ "target_modules": [
34
+ "v_proj",
35
+ "gate_proj",
36
+ "o_proj",
37
+ "down_proj",
38
+ "k_proj",
39
+ "up_proj",
40
+ "q_proj"
41
+ ],
42
+ "task_type": "CAUSAL_LM",
43
+ "use_dora": false,
44
+ "use_rslora": false
45
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60b0d98f5204ef90acdd17a390dc3d6967da4dde9a6d212aede0c5f84e163502
3
+ size 24594488
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ae7b23232a55003aa2e3aa0edaee1c94524e2fe86a2d4a4152e56c65ae165e0
3
+ size 12460922
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:441e0de62345286a29d0a56bf26f7f544d795e5669a74d8b70d8d55789d45e36
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d27b7b2af1e013735884d52ca15d8a0e3a7b09d71cb08e4aa597a9449deb720b
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|pad|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<|pad|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<|begin_of_text|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "<|end_of_text|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "5": {
31
+ "content": "<|eot_id|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "6": {
39
+ "content": "<|start_header_id|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "7": {
47
+ "content": "<|end_header_id|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ }
54
+ },
55
+ "bos_token": "<|begin_of_text|>",
56
+ "chat_template": "{% 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 %}",
57
+ "clean_up_tokenization_spaces": false,
58
+ "eos_token": "<|end_of_text|>",
59
+ "legacy": true,
60
+ "model_max_length": 4096,
61
+ "pad_token": "<|pad|>",
62
+ "padding_side": "right",
63
+ "sp_model_kwargs": {},
64
+ "spaces_between_special_tokens": false,
65
+ "tokenizer_class": "PreTrainedTokenizerFast",
66
+ "use_default_system_prompt": false
67
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5c5e249926d8cb308441fe75693b9477edcdb9508a69b6f42ac38327ed584c9
3
+ size 5112