tahomatx commited on
Commit
578e543
1 Parent(s): eadc943

Upload LlamaForCausalLM (#2)

Browse files

- Upload LlamaForCausalLM (6a0043322ff64d138d38f8902e4304ffe535620d)

Files changed (3) hide show
  1. config.json +28 -0
  2. generation_config.json +7 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/mnt/n/ml/models/aerner/lm-v2/checkpoint-76000",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_dropout_prob": 0.1,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 8,
18
+ "pad_token_id": 0,
19
+ "rms_norm_eps": 1e-06,
20
+ "shared_input_output_embedding": true,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.29.1",
24
+ "use_cache": false,
25
+ "use_memorry_efficient_attention": true,
26
+ "use_stable_embedding": true,
27
+ "vocab_size": 100000
28
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.29.1"
7
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9af5ea94b7d6af2b5c99464086434f26ae3a681d767bd29674ded3b51f22336a
3
+ size 2169864106