deepparag commited on
Commit
09e455c
1 Parent(s): 8b48f60
Files changed (2) hide show
  1. config.json +6 -10
  2. pytorch_model.bin +2 -2
config.json CHANGED
@@ -8,14 +8,15 @@
8
  "bos_token_id": 50256,
9
  "embd_pdrop": 0.1,
10
  "eos_token_id": 50256,
 
11
  "initializer_range": 0.02,
12
  "layer_norm_epsilon": 1e-05,
13
  "model_type": "gpt2",
14
  "n_ctx": 1024,
15
- "n_embd": 1024,
16
- "n_head": 16,
17
  "n_inner": null,
18
- "n_layer": 24,
19
  "n_positions": 1024,
20
  "reorder_and_upcast_attn": false,
21
  "resid_pdrop": 0.1,
@@ -28,16 +29,11 @@
28
  "summary_use_proj": true,
29
  "task_specific_params": {
30
  "conversational": {
31
- "do_sample": true,
32
- "max_length": 1000,
33
- "no_repeat_ngram_size": 4,
34
- "temperature": 0.85,
35
- "top_k": 100,
36
- "top_p": 0.7
37
  }
38
  },
39
  "torch_dtype": "float32",
40
- "transformers_version": "4.12.5",
41
  "use_cache": true,
42
  "vocab_size": 50257
43
  }
 
8
  "bos_token_id": 50256,
9
  "embd_pdrop": 0.1,
10
  "eos_token_id": 50256,
11
+ "gradient_checkpointing": false,
12
  "initializer_range": 0.02,
13
  "layer_norm_epsilon": 1e-05,
14
  "model_type": "gpt2",
15
  "n_ctx": 1024,
16
+ "n_embd": 768,
17
+ "n_head": 12,
18
  "n_inner": null,
19
+ "n_layer": 12,
20
  "n_positions": 1024,
21
  "reorder_and_upcast_attn": false,
22
  "resid_pdrop": 0.1,
 
29
  "summary_use_proj": true,
30
  "task_specific_params": {
31
  "conversational": {
32
+ "max_length": 1000
 
 
 
 
 
33
  }
34
  },
35
  "torch_dtype": "float32",
36
+ "transformers_version": "4.18.0",
37
  "use_cache": true,
38
  "vocab_size": 50257
39
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c689621119dead1a250550d14e2bbda16af7352d81ad9ab80dd84708be384dd0
3
- size 1444576537
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b52f805f622adf4045334a93edacec40dc53f55de2e4ed046fb22281ff4922b5
3
+ size 510394089