bimabk commited on
Commit
3a1d385
·
verified ·
1 Parent(s): 3c0f2e1

Upload task output 1f8cc3b9-9fb8-49a5-a460-f429ea3c8ed6

Browse files
config.json CHANGED
@@ -1,30 +1,29 @@
1
  {
2
- "_remove_final_layer_norm": false,
3
- "activation_dropout": 0.0,
4
- "activation_function": "relu",
5
  "architectures": [
6
- "OPTForCausalLM"
7
  ],
 
8
  "attention_dropout": 0.0,
9
- "bos_token_id": 2,
10
- "do_layer_norm_before": true,
11
- "dropout": 0.1,
12
- "enable_bias": true,
13
  "eos_token_id": 2,
14
- "ffn_dim": 8192,
15
- "hidden_size": 2048,
16
- "init_std": 0.02,
17
- "layer_norm_elementwise_affine": true,
18
- "layerdrop": 0.0,
19
  "max_position_embeddings": 2048,
20
- "model_type": "opt",
21
- "num_attention_heads": 32,
22
- "num_hidden_layers": 24,
23
- "pad_token_id": 1,
24
- "prefix": "</s>",
 
 
 
 
 
25
  "torch_dtype": "bfloat16",
26
  "transformers_version": "4.51.3",
27
  "use_cache": false,
28
- "vocab_size": 50272,
29
- "word_embed_proj_dim": 2048
30
  }
 
1
  {
 
 
 
2
  "architectures": [
3
+ "LlamaForCausalLM"
4
  ],
5
+ "attention_bias": false,
6
  "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
 
 
 
8
  "eos_token_id": 2,
9
+ "head_dim": 64,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
  "max_position_embeddings": 2048,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "num_key_value_heads": 12,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-06,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "tie_word_embeddings": false,
25
  "torch_dtype": "bfloat16",
26
  "transformers_version": "4.51.3",
27
  "use_cache": false,
28
+ "vocab_size": 32000
 
29
  }
generation_config.json CHANGED
@@ -1,7 +1,6 @@
1
  {
2
- "_from_model_config": true,
3
- "bos_token_id": 2,
4
  "eos_token_id": 2,
5
- "pad_token_id": 1,
6
  "transformers_version": "4.51.3"
7
  }
 
1
  {
2
+ "bos_token_id": 1,
 
3
  "eos_token_id": 2,
4
+ "pad_token_id": 0,
5
  "transformers_version": "4.51.3"
6
  }
loss.txt CHANGED
@@ -1 +1 @@
1
- 316,0.9839974045753479
 
1
+ 543,0.6963748931884766
merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3bdbd41da40234abf6eb6997b5b3c3467971883a3db8f98f94cef4a0bca3d913
3
- size 2631562072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96cc9856bd0e5986fd8610e3f599d4b4d8954ef7af749ee05f7692ffdda57aff
3
+ size 324847240
special_tokens_map.json CHANGED
@@ -1,29 +1,23 @@
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
  }
 
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
  }
tokenizer.json CHANGED
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json CHANGED
@@ -1,11 +1,20 @@
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
@@ -13,19 +22,22 @@
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": false,
24
  "eos_token": "</s>",
25
- "errors": "replace",
26
  "extra_special_tokens": {},
 
27
  "model_max_length": 1000000000000000019884624838656,
28
- "pad_token": "<pad>",
29
- "tokenizer_class": "GPT2Tokenizer",
30
- "unk_token": "</s>"
 
 
 
31
  }
 
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
 
22
  "2": {
23
  "content": "</s>",
24
  "lstrip": false,
25
+ "normalized": false,
26
  "rstrip": false,
27
  "single_word": false,
28
  "special": true
29
  }
30
  },
31
+ "bos_token": "<s>",
32
  "clean_up_tokenization_spaces": false,
33
  "eos_token": "</s>",
 
34
  "extra_special_tokens": {},
35
+ "legacy": false,
36
  "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": "</s>",
38
+ "padding_side": "right",
39
+ "sp_model_kwargs": {},
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
  }
vocab.json DELETED
The diff for this file is too large to render. See raw diff