Hugging Face's logo

voidful
/
recurrentgemma-2b-base

Text Generation
Transformers
Safetensors
recurrent_gemma
Model card Files Community
recurrentgemma-2b-base
File size: 1,065 Bytes 
67a3be9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
 
{
  "_block_types": [
    "recurrent",
    "recurrent",
    "attention"
  ],
  "_name_or_path": "google/recurrentgemma-2b",
  "architectures": [
    "RecurrentGemmaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "attention_window_size": 2048,
  "block_types": [
    "recurrent",
    "recurrent",
    "attention"
  ],
  "bos_token_id": 2,
  "conv1d_width": 4,
  "embeddings_scale_by_sqrt_dim": true,
  "eos_token_id": 1,
  "final_w_init_variance_scale": 0.07692307692307693,
  "head_dim": 256,
  "hidden_activation": "gelu_pytorch_tanh",
  "hidden_size": 2560,
  "intermediate_size": 15360,
  "logits_soft_cap": 30.0,
  "lru_width": 2560,
  "model_type": "recurrent_gemma",
  "num_attention_heads": 10,
  "num_hidden_layers": 26,
  "num_key_value_heads": 1,
  "pad_token_id": 0,
  "partial_rotary_factor": 0.5,
  "rms_norm_eps": 1e-06,
  "rope_theta": 10000.0,
  "rotary_emb_base": 50000.0,
  "torch_dtype": "float32",
  "transformers_version": "4.41.0.dev0",
  "use_cache": true,
  "vocab_size": 284389,
  "w_init_variance_scale": 0.01
}