Corianas commited on
Commit
a659028
1 Parent(s): a983a20

Upload 15 files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "### End": 50257,
3
+ "### Instruction:": 50258,
4
+ "### Response:\n": 50259
5
+ }
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cerebras/Cerebras-GPT-2.7b",
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": 2560,
15
+ "n_head": 32,
16
+ "n_inner": 10240,
17
+ "n_layer": 32,
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": "bfloat16",
29
+ "transformers_version": "4.25.1",
30
+ "use_cache": false,
31
+ "vocab_size": 50260
32
+ }
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 sha256:8df813b9ffad6cf275138edc3b3865ee10574924a7c656f4a01f2ae668bf71fe
3
+ size 5437482033
runs/1680601288.9155838/events.out.tfevents.1680601288.155-248-166-228.85999.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd9cfe03f451baf40fe6f74c8b5bd0e4ad8aeb6da43d975de48a85169f90647f
3
+ size 5649
runs/1680601608.4657257/events.out.tfevents.1680601608.155-248-166-228.88647.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9536d672dada35c4a4faf686c403b419651d5fd3f0f28e3acc3b78ea7787ce93
3
+ size 5649
runs/1680601931.7907648/events.out.tfevents.1680601931.155-248-166-228.91317.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0214cd6362ca0f7a0a4286ef72702680fa97476aa848dc0a4a4b2e04da110f73
3
+ size 5649
runs/events.out.tfevents.1680601288.155-248-166-228.85999.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18ec4688f04c641a1ae8e277355eec772b04e301ff688b89b04e1a387cd86c2d
3
+ size 40
runs/events.out.tfevents.1680601608.155-248-166-228.88647.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b0804ef496924ec6f8d0b81d6419d4fd0410270024c8c919f68d59e02290621
3
+ size 6205
runs/events.out.tfevents.1680601931.155-248-166-228.91317.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c053df1bde6756350f59f483556fd3332e11ebfd171b4bb6639a4e2cd3a206f
3
+ size 13026
special_tokens_map.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "### End",
4
+ "### Instruction:",
5
+ "### Response:\n"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<|endoftext|>",
9
+ "lstrip": false,
10
+ "normalized": true,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": "<|endoftext|>",
22
+ "unk_token": {
23
+ "content": "<|endoftext|>",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ }
29
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "errors": "replace",
21
+ "model_max_length": 1000000000000000019884624838656,
22
+ "name_or_path": "cerebras/Cerebras-GPT-2.7b",
23
+ "pad_token": null,
24
+ "special_tokens_map_file": null,
25
+ "tokenizer_class": "GPT2Tokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bd1eeaf8bade388a7f14e1ef358a9080957f021f543e8f81e8f4795bbe0c8e5
3
+ size 4603
vocab.json ADDED
The diff for this file is too large to render. See raw diff