trl-internal-testing/tiny-Cohere2ForCausalLM
0254k
1{2 "_sliding_window_pattern": 4,3 "architectures": [4 "Cohere2ForCausalLM"5 ],6 "attention_bias": false,7 "attention_dropout": 0.0,8 "bos_token_id": 2,9 "cache_implementation": "hybrid",10 "dtype": "bfloat16",11 "eos_token_id": 3,12 "head_dim": 2,13 "hidden_act": "silu",14 "hidden_size": 8,15 "initializer_range": 0.02,16 "intermediate_size": 32,17 "layer_norm_eps": 1e-05,18 "layer_switch": 4,19 "layer_types": [20 "sliding_attention",21 "full_attention"22 ],23 "logit_scale": 1.0,24 "max_position_embeddings": 8192,25 "model_type": "cohere2",26 "num_attention_heads": 4,27 "num_hidden_layers": 2,28 "num_key_value_heads": 2,29 "order_of_interleaved_layers": "local_attn_first",30 "pad_token_id": 0,31 "position_embedding_type": "rope_gptj",32 "rope_scaling": null,33 "rope_theta": 50000,34 "rotary_pct": 1.0,35 "sliding_window": 4096,36 "transformers_version": "4.56.2",37 "use_cache": true,38 "use_embedding_sharing": true,39 "use_gated_activation": true,40 "use_parallel_block": true,41 "use_parallel_embedding": false,42 "use_qk_norm": false,43 "vocab_size": 26214444}45 