Hugging Face's logo

chbenchi
/
mistral-pretraining

Text Generation
Transformers
Safetensors
mistral
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
chbenchi commited on
Commit
695d97e
·
verified ·
1 Parent(s): 035bb01

Training in progress, step 500

Browse files
Files changed (5) hide show
  1. config.json +26 -26
  2. model.safetensors +1 -1
  3. special_tokens_map.json +24 -24
  4. tokenizer_config.json +43 -43
  5. training_args.bin +1 -1
config.json CHANGED
@@ -1,26 +1,26 @@
1
- {
2
- "architectures": [
3
- "MistralForCausalLM"
4
- ],
5
- "attention_dropout": 0.0,
6
- "bos_token_id": 1,
7
- "eos_token_id": 2,
8
- "head_dim": 48,
9
- "hidden_act": "silu",
10
- "hidden_size": 768,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 3072,
13
- "max_position_embeddings": 512,
14
- "model_type": "mistral",
15
- "num_attention_heads": 16,
16
- "num_hidden_layers": 4,
17
- "num_key_value_heads": 8,
18
- "rms_norm_eps": 1e-06,
19
- "rope_theta": 10000.0,
20
- "sliding_window": 768,
21
- "tie_word_embeddings": false,
22
- "torch_dtype": "float32",
23
- "transformers_version": "4.44.2",
24
- "use_cache": true,
25
- "vocab_size": 32000
26
- }
 
1
+ {
2
+ "architectures": [
3
+ "MistralForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "head_dim": 48,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "max_position_embeddings": 512,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 16,
16
+ "num_hidden_layers": 4,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-06,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 768,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.44.2",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f5a11e3f7c696a98b2ee1d9cae6c5e79bc67da29c73e522c37e963d4b8c88dd
3
  size 338197712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da84a7787b0aac349074fe7478ff761dbee0f4528cef3c8ca0f89d83ab0735d0
3
  size 338197712
special_tokens_map.json CHANGED
@@ -1,24 +1,24 @@
1
- {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "</s>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": "</s>",
17
- "unk_token": {
18
- "content": "<unk>",
19
- "lstrip": false,
20
- "normalized": false,
21
- "rstrip": false,
22
- "single_word": false
23
- }
24
- }
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer_config.json CHANGED
@@ -1,43 +1,43 @@
1
- {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
- "add_prefix_space": null,
5
- "added_tokens_decoder": {
6
- "0": {
7
- "content": "<unk>",
8
- "lstrip": false,
9
- "normalized": false,
10
- "rstrip": false,
11
- "single_word": false,
12
- "special": true
13
- },
14
- "1": {
15
- "content": "<s>",
16
- "lstrip": false,
17
- "normalized": false,
18
- "rstrip": false,
19
- "single_word": false,
20
- "special": true
21
- },
22
- "2": {
23
- "content": "</s>",
24
- "lstrip": false,
25
- "normalized": false,
26
- "rstrip": false,
27
- "single_word": false,
28
- "special": true
29
- }
30
- },
31
- "additional_special_tokens": [],
32
- "bos_token": "<s>",
33
- "clean_up_tokenization_spaces": false,
34
- "eos_token": "</s>",
35
- "legacy": false,
36
- "model_max_length": 1000000000000000019884624838656,
37
- "pad_token": "</s>",
38
- "sp_model_kwargs": {},
39
- "spaces_between_special_tokens": false,
40
- "tokenizer_class": "LlamaTokenizer",
41
- "unk_token": "<unk>",
42
- "use_default_system_prompt": false
43
- }
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "additional_special_tokens": [],
32
+ "bos_token": "<s>",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": false,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": "</s>",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51f051c18d90e2251cceec4324851b5ba31baf6e1f6b7333c0ee765f8e009f7b
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:720ddd9e93538a77b06bbbc3a02fe0bc2d7a455befc10bbbb1b505b0fc5bb08e
3
  size 5176