qgallouedec/tiny-GPTNeoXForCausalLM
030
1{2 "architectures": [3 "GPTNeoXForCausalLM"4 ],5 "attention_bias": true,6 "attention_dropout": 0.0,7 "bos_token_id": 0,8 "classifier_dropout": 0.1,9 "eos_token_id": 2,10 "hidden_act": "gelu",11 "hidden_dropout": 0.0,12 "hidden_size": 8,13 "initializer_range": 0.02,14 "intermediate_size": 32,15 "layer_norm_eps": 1e-05,16 "max_position_embeddings": 2048,17 "model_type": "gpt_neox",18 "num_attention_heads": 4,19 "num_hidden_layers": 2,20 "num_key_value_heads": 2,21 "partial_rotary_factor": 0.25,22 "rope_scaling": null,23 "rope_theta": 10000,24 "rotary_emb_base": 10000,25 "rotary_pct": 0.25,26 "tie_word_embeddings": false,27 "torch_dtype": "float32",28 "transformers_version": "4.47.0.dev0",29 "use_cache": true,30 "use_parallel_residual": true,31 "vocab_size": 5027932}33 