lxe commited on
Commit
0f8c30c
1 Parent(s): c06d63d

Upload 5 files

Browse files
Files changed (5) hide show
  1. config.json +32 -0
  2. generation_config.json +6 -0
  3. merges.txt +0 -0
  4. pytorch_model.bin +3 -0
  5. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cerebras/Cerebras-GPT-1.3B",
3
+ "activation_function": "gelu",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.0,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_embd": 2048,
15
+ "n_head": 16,
16
+ "n_inner": 8192,
17
+ "n_layer": 24,
18
+ "n_positions": 2048,
19
+ "reorder_and_upcast_attn": false,
20
+ "resid_pdrop": 0.0,
21
+ "scale_attn_by_inverse_layer_idx": false,
22
+ "scale_attn_weights": true,
23
+ "summary_activation": null,
24
+ "summary_first_dropout": 0.1,
25
+ "summary_proj_to_labels": true,
26
+ "summary_type": "cls_index",
27
+ "summary_use_proj": true,
28
+ "torch_dtype": "float16",
29
+ "transformers_version": "4.28.0.dev0",
30
+ "use_cache": true,
31
+ "vocab_size": 50257
32
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.28.0.dev0"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f96f00babd0b774a704378089beae7e7698be63f6d998657e5afd1670e96a91
3
+ size 2732215965
vocab.json ADDED
The diff for this file is too large to render. See raw diff