Text Generation
Transformers
PyTorch
English
olmo2
conversational
Inference Endpoints
File size: 630 Bytes
18e39b5
 
7589879
18e39b5
 
 
 
 
 
 
 
 
7589879
18e39b5
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "architectures": [
    "Olmo2ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "eos_token_id": 100257,
  "hidden_act": "silu",
  "hidden_size": 5120,
  "initializer_range": 0.02,
  "intermediate_size": 13824,
  "max_position_embeddings": 4096,
  "model_type": "olmo2",
  "num_attention_heads": 40,
  "num_hidden_layers": 40,
  "num_key_value_heads": 40,
  "pad_token_id": 100277,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 500000,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.47.0.dev0",
  "use_cache": true,
  "vocab_size": 100352
}