Hugging Face's logo

ummagumm-a
/
puzzle5

Text Generation
Transformers
Safetensors
gpt_neox
text-generation-inference
Inference Endpoints
Model card Files Community
ummagumm-a commited on
Commit
81bab55
•
1 Parent(s): 63f3e9e

Training in progress, step 500

Browse files
Files changed (2) hide show
  1. config.json +5 -5
  2. training_args.bin +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "EleutherAI/pythia-70m-deduped",
3
  "architectures": [
4
  "GPTNeoXForCausalLM"
5
  ],
@@ -10,14 +10,14 @@
10
  "eos_token_id": 0,
11
  "hidden_act": "gelu",
12
  "hidden_dropout": 0.0,
13
- "hidden_size": 512,
14
  "initializer_range": 0.02,
15
- "intermediate_size": 2048,
16
  "layer_norm_eps": 1e-05,
17
  "max_position_embeddings": 2048,
18
  "model_type": "gpt_neox",
19
- "num_attention_heads": 8,
20
- "num_hidden_layers": 6,
21
  "rope_scaling": null,
22
  "rotary_emb_base": 10000,
23
  "rotary_pct": 0.25,
 
1
  {
2
+ "_name_or_path": "EleutherAI/pythia-1.4b-deduped",
3
  "architectures": [
4
  "GPTNeoXForCausalLM"
5
  ],
 
10
  "eos_token_id": 0,
11
  "hidden_act": "gelu",
12
  "hidden_dropout": 0.0,
13
+ "hidden_size": 2048,
14
  "initializer_range": 0.02,
15
+ "intermediate_size": 8192,
16
  "layer_norm_eps": 1e-05,
17
  "max_position_embeddings": 2048,
18
  "model_type": "gpt_neox",
19
+ "num_attention_heads": 16,
20
+ "num_hidden_layers": 24,
21
  "rope_scaling": null,
22
  "rotary_emb_base": 10000,
23
  "rotary_pct": 0.25,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e4c901f7625e8ae900bb4bbae3e3abf4429023e8aa1bab7614920c06eaa277b
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:704170a3974d5355d8b893e3c34dfe3fac7c5698ba89a6fe1d26d0a836beca6d
3
  size 4728