Hugging Face's logo

flax-community
/
gpt-neo-125M-code-clippy-dedup

Text Generation
Transformers
PyTorch
JAX
TensorBoard
gpt_neo
Inference Endpoints
Model card Files Metrics Community
1
ncoop57 commited on
Commit
8a5cb9d
•
1 Parent(s): b4e1b67

Add most current checkpoint model

Browse files
Files changed (8) hide show
  1. config.json +52 -0
  2. events.out.tfevents.1626471321.t1v-n-fbe3d060-w-0.737396.0.v2 +3 -0
  3. events.out.tfevents.1626472054.t1v-n-fbe3d060-w-0.739605.0.v2 +3 -0
  4. events.out.tfevents.1626475352.t1v-n-fbe3d060-w-0.743862.0.v2 +3 -0
  5. events.out.tfevents.1626476167.t1v-n-fbe3d060-w-0.746309.0.v2 +3 -0
  6. flax_model.msgpack +3 -0
  7. opt_state.msgpack +3 -0
  8. training_state.json +1 -0
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPTNeoForCausalLM"
5
+ ],
6
+ "attention_dropout": 0,
7
+ "attention_layers": [
8
+ "global",
9
+ "local",
10
+ "global",
11
+ "local",
12
+ "global",
13
+ "local",
14
+ "global",
15
+ "local",
16
+ "global",
17
+ "local",
18
+ "global",
19
+ "local"
20
+ ],
21
+ "attention_types": [
22
+ [
23
+ [
24
+ "global",
25
+ "local"
26
+ ],
27
+ 6
28
+ ]
29
+ ],
30
+ "bos_token_id": 50256,
31
+ "embed_dropout": 0,
32
+ "eos_token_id": 50256,
33
+ "gradient_checkpointing": false,
34
+ "hidden_size": 768,
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": null,
37
+ "layer_norm_epsilon": 1e-05,
38
+ "max_position_embeddings": 2048,
39
+ "model_type": "gpt_neo",
40
+ "num_heads": 12,
41
+ "num_layers": 12,
42
+ "resid_dropout": 0,
43
+ "summary_activation": null,
44
+ "summary_first_dropout": 0.1,
45
+ "summary_proj_to_labels": true,
46
+ "summary_type": "cls_index",
47
+ "summary_use_proj": true,
48
+ "transformers_version": "4.9.0.dev0",
49
+ "use_cache": true,
50
+ "vocab_size": 50257,
51
+ "window_size": 256
52
+ }
events.out.tfevents.1626471321.t1v-n-fbe3d060-w-0.737396.0.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5ce6c15ac05685c10be71fb9f4fb167c785cea71c4152302307f3d332a4e2f6
3
+ size 40
events.out.tfevents.1626472054.t1v-n-fbe3d060-w-0.739605.0.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71bceae8ac4e031493ff1d885dc237b1ed9b24c09c3267a572fbd81fb29c81b5
3
+ size 40
events.out.tfevents.1626475352.t1v-n-fbe3d060-w-0.743862.0.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a7b8e321a11a31910edd01e93d65b260e3880129c8aaddafcbdf53547ec6be6
3
+ size 40
events.out.tfevents.1626476167.t1v-n-fbe3d060-w-0.746309.0.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c348ece607e1cd1b326e30dc5a19334b1e08fadf0c902a6b73e6ea97e8fc404
3
+ size 6426529
flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb87c45cf1f7943d2cc2f4dc1b432824fcb4f2b154cafcfa4be6ca77c0641716
3
+ size 500800120
opt_state.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d06491e9f9bc070e672b7ccfb2d4baf67a078f1f0f7d723f184223b3164c40c
3
+ size 1502400776
training_state.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"step": 32001}