TheBloke commited on
Commit
367d501
1 Parent(s): 6b8d9d2

Initial merged FP16 model commit

Browse files
Files changed (1) hide show
  1. config.json +28 -0
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/workspace/superhot_process/vicuna-33b/source",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 6656,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 17920,
12
+ "max_position_embeddings": 8192,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 52,
15
+ "num_hidden_layers": 60,
16
+ "pad_token_id": 0,
17
+ "rms_norm_eps": 1e-06,
18
+ "tie_word_embeddings": false,
19
+ "torch_dtype": "float16",
20
+ "transformers_version": "4.30.0.dev0",
21
+ "use_cache": true,
22
+ "vocab_size": 32000,
23
+ "auto_map": {
24
+ "AutoModel": "modelling_llama.LlamaModel",
25
+ "AutoModelForCausalLM": "modelling_llama.LlamaForCausalLM",
26
+ "AutoModelForSequenceClassification": "modelling_llama.LlamaForSequenceClassification"
27
+ }
28
+ }