| { | |
| "architectures": ["MistralForCausalLM"], | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 32768, | |
| "model_type": "mistral", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 10000.0, | |
| "sliding_window": 4096, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.34.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 32000, | |
| "load_in_4bit": true, | |
| "bnb_4bit_use_double_quant": true, | |
| "bnb_4bit_quant_type": "nf4", | |
| "bnb_4bit_compute_dtype": "torch.bfloat16", | |
| "r": 8, | |
| "lora_alpha": 32, | |
| "target_modules": ["q_proj", "k_proj"], | |
| "lora_dropout": 0.05, | |
| "bias": "none", | |
| "task_type": "CAUSAL_LM" | |
| } | |