losyer8 commited on
Commit
0577ecf
1 Parent(s): 3a9080d

Upload model

Browse files
Files changed (3) hide show
  1. config.json +34 -0
  2. generation_config.json +6 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/data/llmjp0/model_cache_dir/outputs/checkpoint_HF/1.3B/ds_gpt_v101_fattn_nfs_0825_refined-data-gpt_1.3B_refined_gpu96_node12_lr0.0001708_gbs1536_mbs4_nwk2_zero1_pp1/global_step96173",
3
+ "activation_function": "gelu",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 7,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 7,
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": 2048,
17
+ "n_head": 16,
18
+ "n_inner": 8192,
19
+ "n_layer": 24,
20
+ "n_positions": 2048,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "torch_dtype": "float16",
31
+ "transformers_version": "4.34.0",
32
+ "use_cache": true,
33
+ "vocab_size": 50688
34
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 7,
4
+ "eos_token_id": 7,
5
+ "transformers_version": "4.34.0"
6
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ed5e7d03afb86318ccf73475a3151192a0f25994ab05c8d2396cce9e74953e9
3
+ size 2633307101