chenluuli commited on
Commit
d340c59
1 Parent(s): 13a6ebf

test base model

Browse files
Files changed (4) hide show
  1. config.json +27 -0
  2. model.safetensors +3 -0
  3. tokenizer.json +0 -0
  4. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 896,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4864,
12
+ "max_position_embeddings": 32768,
13
+ "max_window_layers": 21,
14
+ "model_type": "qwen2",
15
+ "num_attention_heads": 14,
16
+ "num_hidden_layers": 24,
17
+ "num_key_value_heads": 2,
18
+ "rms_norm_eps": 1e-06,
19
+ "rope_theta": 1000000.0,
20
+ "sliding_window": 32768,
21
+ "tie_word_embeddings": true,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.43.1",
24
+ "use_cache": true,
25
+ "use_sliding_window": false,
26
+ "vocab_size": 151936
27
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdf756fa7fcbe7404d5c60e26bff1a0c8b8aa1f72ced49e7dd0210fe288fb7fe
3
+ size 988097824
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
vocab.json ADDED
The diff for this file is too large to render. See raw diff