Hugging Face's logo

augustocsc
/
gpt2-p10k-cossine

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
augustocsc commited on
Commit
359377e
•
1 Parent(s): df7b363

Training in progress, step 1000

Browse files
Files changed (3) hide show
  1. config.json +4 -4
  2. model.safetensors +2 -2
  3. training_args.bin +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "gpt2",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
@@ -12,10 +12,10 @@
12
  "layer_norm_epsilon": 1e-05,
13
  "model_type": "gpt2",
14
  "n_ctx": 1024,
15
- "n_embd": 768,
16
- "n_head": 12,
17
  "n_inner": null,
18
- "n_layer": 12,
19
  "n_positions": 1024,
20
  "reorder_and_upcast_attn": false,
21
  "resid_pdrop": 0.1,
 
1
  {
2
+ "_name_or_path": "gpt2-large",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
 
12
  "layer_norm_epsilon": 1e-05,
13
  "model_type": "gpt2",
14
  "n_ctx": 1024,
15
+ "n_embd": 1280,
16
+ "n_head": 20,
17
  "n_inner": null,
18
+ "n_layer": 36,
19
  "n_positions": 1024,
20
  "reorder_and_upcast_attn": false,
21
  "resid_pdrop": 0.1,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c999b2c968317cfb9a178e7d7e916ec81e10f2d4b5f677a60a04809df73dc28
3
- size 497780352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73241aa77dd1dc717757b28c8139ee38f35773bf35f25300f584a869b6b5f9f4
3
+ size 3096176168
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac099e73b43ec4fb0ff55120cb27fe4c7253b82e028a96ded709dbe7962ba7d3
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36bf2b830fdd43c352b517d256f0f7d6b5ac1859da3f3918fe77a3e8daa5931b
3
  size 4984