Epoch 3.0/15.0 Step 237 Wandb run: https://wandb.ai/aleksey-korshuk/huggingface/runs/18ynn57i

#3
Files changed (2) hide show
  1. config.json +29 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/opt-6.7b",
3
+ "_remove_final_layer_norm": false,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "architectures": [
7
+ "OPTForCausalLM"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "bos_token_id": 2,
11
+ "do_layer_norm_before": true,
12
+ "dropout": 0.1,
13
+ "eos_token_id": 2,
14
+ "ffn_dim": 16384,
15
+ "hidden_size": 4096,
16
+ "init_std": 0.02,
17
+ "layerdrop": 0.0,
18
+ "max_position_embeddings": 2048,
19
+ "model_type": "opt",
20
+ "num_attention_heads": 32,
21
+ "num_hidden_layers": 32,
22
+ "pad_token_id": 1,
23
+ "prefix": "</s>",
24
+ "torch_dtype": "float16",
25
+ "transformers_version": "4.25.0.dev0",
26
+ "use_cache": true,
27
+ "vocab_size": 50265,
28
+ "word_embed_proj_dim": 4096
29
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a68e365c7ed3ee0786635b67f884975cffc45a35196765130116d5f7d984b12e
3
+ size 3581433