Text Generation
Transformers
Safetensors
English
llama
text-generation-inference
4-bit precision
gptq
TheBloke commited on
Commit
13db983
1 Parent(s): 79535a9

Initial GPTQ model commit

Browse files
Files changed (1) hide show
  1. config.json +23 -0
config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/workspace/process/tulu-13b/source",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 5120,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 13824,
12
+ "max_position_embeddings": 2048,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 40,
15
+ "num_hidden_layers": 40,
16
+ "pad_token_id": 0,
17
+ "rms_norm_eps": 1e-06,
18
+ "tie_word_embeddings": false,
19
+ "torch_dtype": "float32",
20
+ "transformers_version": "4.30.0.dev0",
21
+ "use_cache": true,
22
+ "vocab_size": 32001
23
+ }