OccultAI/Musecuilo-12B-Model_Stock
230
1{
2 "architectures": [
3 "MistralForCausalLM"
4 ],
5 "attention_dropout": 0.0,
6 "bos_token_id": 1,
7 "dtype": "bfloat16",
8 "eos_token_id": 2,
9 "head_dim": 128,
10 "hidden_act": "silu",
11 "hidden_size": 5120,
12 "initializer_range": 0.02,
13 "intermediate_size": 14336,
14 "max_position_embeddings": 131072,
15 "model_type": "mistral",
16 "num_attention_heads": 32,
17 "num_hidden_layers": 40,
18 "num_key_value_heads": 8,
19 "rms_norm_eps": 1e-05,
20 "rope_theta": 1000000.0,
21 "sliding_window": null,
22 "tie_word_embeddings": false,
23 "transformers_version": "4.56.1",
24 "use_cache": true,
25 "vocab_size": 131074
26}
27 