ssdataanalysis commited on
Commit
6932558
·
verified ·
1 Parent(s): 714086c

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +44 -0
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "JambaForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "attn_layer_offset": 7,
7
+ "attn_layer_period": 14,
8
+ "bos_token_id": 1,
9
+ "dtype": "bfloat16",
10
+ "eos_token_id": [
11
+ 2,
12
+ 519
13
+ ],
14
+ "expert_layer_offset": 1,
15
+ "expert_layer_period": 2,
16
+ "hidden_act": "silu",
17
+ "hidden_size": 2560,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 8192,
20
+ "mamba_conv_bias": true,
21
+ "mamba_d_conv": 4,
22
+ "mamba_d_state": 16,
23
+ "mamba_dt_rank": 160,
24
+ "mamba_expand": 2,
25
+ "mamba_proj_bias": false,
26
+ "max_position_embeddings": 262144,
27
+ "model_type": "jamba",
28
+ "num_attention_heads": 20,
29
+ "num_experts": 1,
30
+ "num_experts_per_tok": 1,
31
+ "num_hidden_layers": 28,
32
+ "num_key_value_heads": 1,
33
+ "num_logits_to_keep": 1,
34
+ "output_router_logits": false,
35
+ "pad_token_id": 0,
36
+ "rms_norm_eps": 1e-06,
37
+ "router_aux_loss_coef": 0.001,
38
+ "sliding_window": null,
39
+ "tie_word_embeddings": true,
40
+ "transformers_version": "4.56.1",
41
+ "use_cache": true,
42
+ "use_mamba_kernels": true,
43
+ "vocab_size": 65536
44
+ }