Text Generation
Transformers
Safetensors
cohere2
conversational
jukofyork commited on
Commit
341b882
·
verified ·
1 Parent(s): b6f9f77

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +38 -0
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Cohere2ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 5,
8
+ "cache_implementation": "hybrid",
9
+ "eos_token_id": 255001,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 12288,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 36864,
15
+ "layer_norm_eps": 1e-05,
16
+ "logit_scale": 0.25,
17
+ "max_position_embeddings": 131072,
18
+ "model_type": "cohere2",
19
+ "num_attention_heads": 96,
20
+ "num_hidden_layers": 64,
21
+ "num_key_value_heads": 8,
22
+ "order_of_interleaved_layers": "local_attn_first",
23
+ "pad_token_id": 0,
24
+ "position_embedding_type": "rope_gptj",
25
+ "rope_scaling": null,
26
+ "rope_theta": 50000,
27
+ "rotary_pct": 1.0,
28
+ "sliding_window": 4096,
29
+ "sliding_window_pattern": 4,
30
+ "torch_dtype": "bfloat16",
31
+ "transformers_version": "4.48.0.dev0",
32
+ "use_cache": true,
33
+ "use_embedding_sharing": true,
34
+ "use_gated_activation": true,
35
+ "use_parallel_block": true,
36
+ "use_parallel_embedding": true,
37
+ "vocab_size": 256000
38
+ }