trl-internal-testing/tiny-Qwen2ForCausalLM-2.5
4913.1m
1{2 "architectures": [3 "Qwen2ForCausalLM"4 ],5 "attention_dropout": 0.0,6 "bos_token_id": 151643,7 "dtype": "bfloat16",8 "eos_token_id": 151645,9 "hidden_act": "silu",10 "hidden_size": 8,11 "initializer_range": 0.02,12 "intermediate_size": 32,13 "layer_types": [14 "full_attention",15 "full_attention"16 ],17 "max_position_embeddings": 32768,18 "max_window_layers": 70,19 "model_type": "qwen2",20 "num_attention_heads": 4,21 "num_hidden_layers": 2,22 "num_key_value_heads": 2,23 "rms_norm_eps": 1e-06,24 "rope_scaling": null,25 "rope_theta": 1000000.0,26 "sliding_window": null,27 "tie_word_embeddings": false,28 "transformers_version": "4.56.2",29 "use_cache": true,30 "use_sliding_window": false,31 "vocab_size": 15206432}33 