c-bone commited on
Commit
98bc6b2
·
verified ·
1 Parent(s): c352c44

Upload PKV model checkpoint

Browse files
Files changed (3) hide show
  1. config.json +38 -0
  2. model.safetensors +3 -0
  3. tokenizer_config.json +1 -0
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "model_ckpts/mpdb-small-base-lematerial/checkpoint-1250000",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "PKVGPT"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 372,
9
+ "dropout": 0.1,
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 373,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_embd": 512,
16
+ "n_head": 8,
17
+ "n_hidden_cond": 768,
18
+ "n_inner": null,
19
+ "n_input_vector": 1,
20
+ "n_layer": 8,
21
+ "n_positions": 1025,
22
+ "n_prefix_tokens": 1,
23
+ "pad_token_id": 371,
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
+ "share_layers": false,
29
+ "summary_activation": null,
30
+ "summary_first_dropout": 0.1,
31
+ "summary_proj_to_labels": true,
32
+ "summary_type": "cls_index",
33
+ "summary_use_proj": true,
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.48.0",
36
+ "use_cache": true,
37
+ "vocab_size": 377
38
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7574aab670bf672942fcec2700548cec4fbaff396f79e28b467bfc4db14f1ce
3
+ size 158863960
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "vocab_size": 377, "tokenizer_class": "CustomCIFTokenizer"}