IlyaGusev commited on
Commit
34ca8bc
1 Parent(s): a8df138

Initial commit

Browse files
.gitattributes CHANGED
@@ -32,3 +32,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ adapter_model.bin filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.model filter=lfs diff=lfs merge=lfs -text
adapter_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "huggyllama/llama-13b",
3
+ "bias": "none",
4
+ "fan_in_fan_out": false,
5
+ "inference_mode": true,
6
+ "init_lora_weights": true,
7
+ "lora_alpha": 16,
8
+ "lora_dropout": 0.05,
9
+ "modules_to_save": null,
10
+ "peft_type": "LORA",
11
+ "r": 16,
12
+ "target_modules": [
13
+ "q_proj",
14
+ "v_proj",
15
+ "k_proj",
16
+ "o_proj"
17
+ ],
18
+ "task_type": "CAUSAL_LM"
19
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2361fe144529c5c06e8b333e5aaffc836ccf6da69a850427fe03c87c454c3acc
3
+ size 104973389
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "pad_token_id": 0,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "temperature": 1.0,
6
+ "top_p": 0.9,
7
+ "top_k": 30,
8
+ "do_sample": true,
9
+ "max_new_tokens": 1024,
10
+ "num_beams": 2,
11
+ "repetition_penalty": 1.1,
12
+ "no_repeat_ngram_size": 8
13
+ }
14
+
special_tokens_map.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "sep_token": "<s>",
18
+ "unk_token": {
19
+ "content": "<unk>",
20
+ "lstrip": false,
21
+ "normalized": true,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ }
25
+ }
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 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "model_max_length": 2048,
22
+ "pad_token": null,
23
+ "sp_model_kwargs": {},
24
+ "special_tokens_map_file": "models/llama-13b/special_tokens_map.json",
25
+ "tokenizer_class": "LlamaTokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
training_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "trainer": {
3
+ "evaluation_strategy": "steps",
4
+ "per_device_train_batch_size": 4,
5
+ "per_device_eval_batch_size": 4,
6
+ "gradient_accumulation_steps": 32,
7
+ "eval_steps": 50,
8
+ "save_steps": 50,
9
+ "logging_steps": 5,
10
+ "learning_rate": 0.0003,
11
+ "num_train_epochs": 5,
12
+ "lr_scheduler_type": "cosine",
13
+ "warmup_steps": 30,
14
+ "fp16": true,
15
+ "bf16": false,
16
+ "torch_compile": false,
17
+ "optim": "adamw_torch"
18
+ },
19
+ "lora": {
20
+ "r": 16,
21
+ "lora_alpha": 16,
22
+ "lora_dropout": 0.05,
23
+ "bias": "none",
24
+ "target_modules": ["q_proj", "v_proj", "k_proj", "o_proj"],
25
+ "task_type": "CAUSAL_LM"
26
+ },
27
+ "load_in_8bit": true,
28
+ "only_target_loss": true,
29
+ "mode": "chat",
30
+ "templates_path": "ru_saiga_template.json",
31
+ "model_name": "models/llama-13b",
32
+ "model_type": "causal",
33
+ "max_tokens_count": 1024
34
+ }
35
+