Hugging Face's logo

MTSmash
/
EvaGPT-446M-MaTeLiX-AI-Pretrained

Text Generation
Transformers
Safetensors
English
German
mistral
gpt
llm
large language model
mateilx
conversational
text-generation-inference
Model card Files
xet
 Community
MTSmash commited on
Commit
36cf818
·
verified ·
1 Parent(s): 67a6ca5

Upload 9 files

Browse files
Files changed (9) hide show
  1. added_tokens.json +5 -0
  2. config.json +27 -0
  3. generation_config.json +6 -0
  4. model.safetensors +3 -0
  5. special_tokens_map.json +53 -0
  6. tokenizer.json +0 -0
  7. tokenizer.model +3 -0
  8. tokenizer_config.json +71 -0
  9. training_args.bin +3 -0
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|Assistentin|>": 41746,
3
+ "<|Benutzer|>": 41745,
4
+ "<|System|>": 41744
5
+ }
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./training_outputs/EvaGPT-446M-MaTeLiX-AI-for-Pretraining_2025-08-05_14-52-53",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 72,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1152,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "max_position_embeddings": 8192,
15
+ "model_type": "mistral",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 20,
18
+ "num_key_value_heads": 4,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_theta": 10000.0,
21
+ "sliding_window": 4096,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.38.2",
25
+ "use_cache": true,
26
+ "vocab_size": 41747
27
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.38.2"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc4aa9af37798b49c00ba7e1b56ae1302ccf9ee7a5b1ca254e3f0a4657a28474
3
+ size 1782832976
special_tokens_map.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|System|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|Benutzer|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<|Assistentin|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ ],
25
+ "bos_token": {
26
+ "content": "<s>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "eos_token": {
33
+ "content": "</s>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ },
39
+ "pad_token": {
40
+ "content": "<unk>",
41
+ "lstrip": false,
42
+ "normalized": false,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "unk_token": {
47
+ "content": "<unk>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ }
53
+ }
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 sha256:47e1d6583190d4f82c13f002c9bd84bf257152a13375382c4994940ca0904f71
3
+ size 895342
tokenizer_config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "41744": {
30
+ "content": "<|System|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "41745": {
38
+ "content": "<|Benutzer|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "41746": {
46
+ "content": "<|Assistentin|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ }
53
+ },
54
+ "additional_special_tokens": [
55
+ "<|System|>",
56
+ "<|Benutzer|>",
57
+ "<|Assistentin|>"
58
+ ],
59
+ "bos_token": "<s>",
60
+ "chat_template": "{% if system -%}\n<|System|>\n{{ system }}\n</s>\n{%- endif %}\n{% for message in messages %}\n{% if message.role == 'user' -%}\n<|Benutzer|>\n{{ message.content }}\n{% if message.kontext %}\n{{ message.kontext }}\n{% endif %}\n</s>\n{% elif message.role == 'assistant' -%}\n<|Assistentin|>\n{{ message.content }}\n</s>\n{% endif %}\n{% endfor %}\n",
61
+ "clean_up_tokenization_spaces": false,
62
+ "eos_token": "</s>",
63
+ "legacy": false,
64
+ "model_max_length": 1000000000000000019884624838656,
65
+ "pad_token": "<unk>",
66
+ "sp_model_kwargs": {},
67
+ "spaces_between_special_tokens": false,
68
+ "tokenizer_class": "LlamaTokenizer",
69
+ "unk_token": "<unk>",
70
+ "use_default_system_prompt": false
71
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5394f1e8890b73ca4b484b80a7ca6f3bcb7bdba8307f9f41010ed47ca32e1f5a
3
+ size 5048