Pinkstack/PGAM-WIT-Conversational-3B-PyTorch
229
1{2 "_name_or_path": "Pinkstack/PGAM-WIT-Conversational-3B-vLLM",3 "architectures": [4 "Qwen2ForCausalLM"5 ],6 "attention_dropout": 0.0,7 "bos_token_id": 151643,8 "eos_token_id": 151645,9 "hidden_act": "silu",10 "hidden_size": 2048,11 "initializer_range": 0.02,12 "intermediate_size": 11008,13 "max_position_embeddings": 32768,14 "max_window_layers": 70,15 "model_type": "qwen2",16 "num_attention_heads": 16,17 "num_hidden_layers": 36,18 "num_key_value_heads": 2,19 "pad_token_id": 151665,20 "rms_norm_eps": 1e-06,21 "rope_scaling": null,22 "rope_theta": 1000000.0,23 "sliding_window": null,24 "tie_word_embeddings": true,25 "torch_dtype": "float16",26 "transformers_version": "4.47.1",27 "unsloth_fixed": true,28 "unsloth_version": "2024.12.9",29 "use_cache": true,30 "use_sliding_window": false,31 "vocab_size": 15193632}33 