RedMist137 commited on
Commit
85cbd5e
1 Parent(s): b91e871

Training in progress, step 100

Browse files
config.json CHANGED
@@ -1,26 +1,31 @@
1
  {
2
- "_name_or_path": "HuggingFaceH4/mistral-7b-sft-beta",
 
 
 
3
  "architectures": [
4
- "MistralForCausalLM"
5
  ],
6
  "attention_dropout": 0.0,
7
- "bos_token_id": 1,
 
 
 
8
  "eos_token_id": 2,
9
- "hidden_act": "silu",
10
- "hidden_size": 4096,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 14336,
13
- "max_position_embeddings": 32768,
14
- "model_type": "mistral",
 
15
  "num_attention_heads": 32,
16
  "num_hidden_layers": 32,
17
- "num_key_value_heads": 8,
18
- "rms_norm_eps": 1e-05,
19
- "rope_theta": 10000.0,
20
- "sliding_window": 4096,
21
- "tie_word_embeddings": false,
22
  "torch_dtype": "bfloat16",
23
  "transformers_version": "4.40.2",
24
  "use_cache": false,
25
- "vocab_size": 32000
 
26
  }
 
1
  {
2
+ "_name_or_path": "facebook/opt-2.7b",
3
+ "_remove_final_layer_norm": false,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
  "architectures": [
7
+ "OPTForCausalLM"
8
  ],
9
  "attention_dropout": 0.0,
10
+ "bos_token_id": 2,
11
+ "do_layer_norm_before": true,
12
+ "dropout": 0.1,
13
+ "enable_bias": true,
14
  "eos_token_id": 2,
15
+ "ffn_dim": 10240,
16
+ "hidden_size": 2560,
17
+ "init_std": 0.02,
18
+ "layer_norm_elementwise_affine": true,
19
+ "layerdrop": 0.0,
20
+ "max_position_embeddings": 2048,
21
+ "model_type": "opt",
22
  "num_attention_heads": 32,
23
  "num_hidden_layers": 32,
24
+ "pad_token_id": 1,
25
+ "prefix": "</s>",
 
 
 
26
  "torch_dtype": "bfloat16",
27
  "transformers_version": "4.40.2",
28
  "use_cache": false,
29
+ "vocab_size": 50272,
30
+ "word_embed_proj_dim": 2560
31
  }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,34 +1,29 @@
1
  {
2
- "additional_special_tokens": [
3
- "<unk>",
4
- "<s>",
5
- "</s>"
6
- ],
7
  "bos_token": {
8
- "content": "<s>",
9
  "lstrip": false,
10
- "normalized": false,
11
  "rstrip": false,
12
  "single_word": false
13
  },
14
  "eos_token": {
15
  "content": "</s>",
16
  "lstrip": false,
17
- "normalized": false,
18
  "rstrip": false,
19
  "single_word": false
20
  },
21
  "pad_token": {
22
- "content": "</s>",
23
  "lstrip": false,
24
- "normalized": false,
25
  "rstrip": false,
26
  "single_word": false
27
  },
28
  "unk_token": {
29
- "content": "<unk>",
30
  "lstrip": false,
31
- "normalized": false,
32
  "rstrip": false,
33
  "single_word": false
34
  }
 
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": {
17
+ "content": "<pad>",
18
  "lstrip": false,
19
+ "normalized": true,
20
  "rstrip": false,
21
  "single_word": false
22
  },
23
  "unk_token": {
24
+ "content": "</s>",
25
  "lstrip": false,
26
+ "normalized": true,
27
  "rstrip": false,
28
  "single_word": false
29
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,19 +1,11 @@
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
@@ -21,28 +13,18 @@
21
  "2": {
22
  "content": "</s>",
23
  "lstrip": false,
24
- "normalized": false,
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
28
  }
29
  },
30
- "additional_special_tokens": [
31
- "<unk>",
32
- "<s>",
33
- "</s>"
34
- ],
35
- "bos_token": "<s>",
36
- "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
37
- "clean_up_tokenization_spaces": false,
38
  "eos_token": "</s>",
39
- "legacy": true,
40
  "model_max_length": 2048,
41
- "pad_token": "</s>",
42
- "sp_model_kwargs": {},
43
- "spaces_between_special_tokens": false,
44
- "tokenizer_class": "LlamaTokenizer",
45
- "truncation_side": "left",
46
- "unk_token": "<unk>",
47
- "use_default_system_prompt": true
48
  }
 
1
  {
2
  "add_bos_token": true,
3
+ "add_prefix_space": false,
4
  "added_tokens_decoder": {
 
 
 
 
 
 
 
 
5
  "1": {
6
+ "content": "<pad>",
7
  "lstrip": false,
8
+ "normalized": true,
9
  "rstrip": false,
10
  "single_word": false,
11
  "special": true
 
13
  "2": {
14
  "content": "</s>",
15
  "lstrip": false,
16
+ "normalized": true,
17
  "rstrip": false,
18
  "single_word": false,
19
  "special": true
20
  }
21
  },
22
+ "bos_token": "</s>",
23
+ "clean_up_tokenization_spaces": true,
 
 
 
 
 
 
24
  "eos_token": "</s>",
25
+ "errors": "replace",
26
  "model_max_length": 2048,
27
+ "pad_token": "<pad>",
28
+ "tokenizer_class": "GPT2Tokenizer",
29
+ "unk_token": "</s>"
 
 
 
 
30
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5eaf099ab9285a9631f859b2cade5d3962344f334703a169be78077404f6b186
3
  size 6264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa0133821bf0ac9ae8383b9e659e55043f45c4ec953e8652f9a1cbff873bca8d
3
  size 6264
vocab.json ADDED
The diff for this file is too large to render. See raw diff