VGribAI/Tensor-28m

1{
2  "architectures": [
3    "LlamaForCausalLM"
4  ],
5  "attention_bias": false,
6  "attention_dropout": 0.0,
7  "bos_token_id": 1,
8  "dtype": "float32",
9  "eos_token_id": 2,
10  "head_dim": 64,
11  "hidden_act": "silu",
12  "hidden_dropout": 0.0,
13  "hidden_size": 512,
14  "initializer_range": 0.02,
15  "intermediate_size": 2048,
16  "max_position_embeddings": 512,
17  "mlp_bias": false,
18  "model_type": "llama",
19  "num_attention_heads": 8,
20  "num_hidden_layers": 6,
21  "num_key_value_heads": 4,
22  "pad_token_id": null,
23  "pretraining_tp": 1,
24  "rms_norm_eps": 1e-06,
25  "rope_parameters": {
26    "rope_theta": 10000.0,
27    "rope_type": "default"
28  },
29  "tie_word_embeddings": true,
30  "transformers_version": "5.13.0",
31  "use_cache": false,
32  "vocab_size": 10000
33}
34