Hugging Face's logo

aydndglr
/
EchoLLM-350M

Text Classification
Transformers
Turkish
echollm
experimental
EchoLLM
transformer
Model card Files
xet
 Community
1
aydndglr commited on
Commit
c512b57
·
verified ·
1 Parent(s): beff9d4

Upload 8 files

Browse files
Files changed (8) hide show
  1. config.json +40 -0
  2. echo_llm.bin +3 -0
  3. echo_llm.safetensors +3 -0
  4. model_config.json +38 -0
  5. project_config.json +8 -0
  6. special_tokens_map.json +9 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +74 -0
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architecture": "EchoLLM",
4
+ "batch_size": 8,
5
+ "checkpoint_frequency": 1,
6
+ "curriculum_learning": true,
7
+ "d_model": 768,
8
+ "dim_feedforward": 3072,
9
+ "dropout": 0.1,
10
+ "eval_metric": "perplexity",
11
+ "export_formats": [
12
+ "bin",
13
+ "safetensors"
14
+ ],
15
+ "gradient_accumulation_steps": 4,
16
+ "learning_rate": 5e-05,
17
+ "load_from_checkpoint": null,
18
+ "loss_function": "CrossEntropyLoss",
19
+ "max_position_embeddings": 8192,
20
+ "max_token_length": 2048,
21
+ "memory_size": 2048,
22
+ "model_name": "Echo",
23
+ "model_type": "echollm",
24
+ "num_epochs": 10,
25
+ "num_experts": 4,
26
+ "num_heads": 12,
27
+ "num_layers": 12,
28
+ "optimizer": "Adafactor",
29
+ "output_dir": "EchoLLM_Model\\model",
30
+ "precision": "float32",
31
+ "save_best_model": true,
32
+ "scheduler": "cosine",
33
+ "transformers_version": "4.49.0",
34
+ "use_gradient_checkpointing": true,
35
+ "use_memory": true,
36
+ "use_mixed_precision": true,
37
+ "vocab_size": 32000,
38
+ "warmup_steps": 1000,
39
+ "weight_decay": 0.01
40
+ }
echo_llm.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a03d1b56ae381b1f20d31575812081aabd13cbbeed420274fe73ee026185e880
3
+ size 1234593397
echo_llm.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:393c80ae4793655b24367d115250508d4accaba05559b63bb07aed4e464006c7
3
+ size 1234493648
model_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_name": "Echo",
3
+ "architecture": "EchoLLM",
4
+ "vocab_size": 32000,
5
+ "max_position_embeddings": 8192,
6
+ "d_model": 768,
7
+ "num_layers": 12,
8
+ "num_heads": 12,
9
+ "dim_feedforward": 3072,
10
+ "dropout": 0.1,
11
+ "activation": "gelu",
12
+ "num_experts": 4,
13
+ "use_memory": true,
14
+ "memory_size": 2048,
15
+ "batch_size": 8,
16
+ "learning_rate": 5e-05,
17
+ "num_epochs": 10,
18
+ "optimizer": "Adafactor",
19
+ "scheduler": "cosine",
20
+ "warmup_steps": 1000,
21
+ "weight_decay": 0.01,
22
+ "curriculum_learning": true,
23
+ "loss_function": "CrossEntropyLoss",
24
+ "eval_metric": "perplexity",
25
+ "output_dir": "EchoLLM_Model\\model",
26
+ "checkpoint_frequency": 1,
27
+ "save_best_model": true,
28
+ "load_from_checkpoint": null,
29
+ "use_gradient_checkpointing": true,
30
+ "use_mixed_precision": true,
31
+ "gradient_accumulation_steps": 4,
32
+ "export_formats": [
33
+ "bin",
34
+ "safetensors"
35
+ ],
36
+ "precision": "float32",
37
+ "max_token_length": 2048
38
+ }
project_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "project_name": "Echo",
3
+ "architecture": "EchoLLM",
4
+ "version": "1.0.0",
5
+ "seed": 42,
6
+ "logging_level": "INFO",
7
+ "base_output_dir": "EchoLLM_Model"
8
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<SOS>",
3
+ "cls_token": "<CLS>",
4
+ "eos_token": "<EOS>",
5
+ "mask_token": "<MASK>",
6
+ "pad_token": "<PAD>",
7
+ "sep_token": "<SEP>",
8
+ "unk_token": "<UNK>"
9
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<PAD>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<UNK>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<SOS>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<EOS>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<CLS>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<SEP>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "<MASK>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "bos_token": "<SOS>",
61
+ "clean_up_tokenization_spaces": false,
62
+ "cls_token": "<CLS>",
63
+ "do_lower_case": false,
64
+ "eos_token": "<EOS>",
65
+ "extra_special_tokens": {},
66
+ "mask_token": "<MASK>",
67
+ "model_max_length": 16384,
68
+ "pad_token": "<PAD>",
69
+ "padding_side": "right",
70
+ "sep_token": "<SEP>",
71
+ "tokenizer_class": "PreTrainedTokenizer",
72
+ "truncation_side": "right",
73
+ "unk_token": "<UNK>"
74
+ }