TranTruongMMCII commited on
Commit
a94ccd6
·
verified ·
1 Parent(s): f58f4e8

Upload 5 files

Browse files
checkpoint-best/retriever_eol/config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_num_labels": 2,
3
+ "activation_function": "gelu_new",
4
+ "add_cross_attention": false,
5
+ "architectures": [
6
+ "GPT2LMHeadModel"
7
+ ],
8
+ "attn_pdrop": 0.1,
9
+ "bos_token_id": 0,
10
+ "dtype": "float32",
11
+ "embd_pdrop": 0.1,
12
+ "eos_token_id": 2,
13
+ "initializer_range": 0.02,
14
+ "layer_norm_epsilon": 1e-05,
15
+ "model_type": "gpt2",
16
+ "n_ctx": 1024,
17
+ "n_embd": 768,
18
+ "n_head": 12,
19
+ "n_inner": null,
20
+ "n_layer": 12,
21
+ "n_positions": 1024,
22
+ "output_past": true,
23
+ "pad_token_id": 1,
24
+ "reorder_and_upcast_attn": false,
25
+ "resid_pdrop": 0.1,
26
+ "scale_attn_by_inverse_layer_idx": false,
27
+ "scale_attn_weights": true,
28
+ "summary_activation": null,
29
+ "summary_first_dropout": 0.1,
30
+ "summary_proj_to_labels": true,
31
+ "summary_type": "cls_index",
32
+ "summary_use_proj": true,
33
+ "tie_word_embeddings": true,
34
+ "transformers_version": "5.0.0",
35
+ "use_cache": true,
36
+ "vocab_size": 50007
37
+ }
checkpoint-best/retriever_eol/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "5.0.0"
7
+ }
checkpoint-best/retriever_eol/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c790ac78a242140aacb84e4a37f6ae4fca0544a4284281931b74b072a97a31a4
3
+ size 497006208
checkpoint-best/retriever_eol/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-best/retriever_eol/tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "errors": "replace",
7
+ "extra_special_tokens": [
8
+ "<RET>",
9
+ "</RET>",
10
+ "<CTX>",
11
+ "</CTX>",
12
+ "<GEN>"
13
+ ],
14
+ "full_tokenizer_file": null,
15
+ "is_local": false,
16
+ "model_max_length": 1000000000000000019884624838656,
17
+ "pad_token": "<pad>",
18
+ "sep_token": "<EOL>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|UNKNOWN|>"
21
+ }