| { | |
| "model_type": "mistral", | |
| "architectures": ["MistralForCausalLM"], | |
| "base_model": "mistralai/Mistral-7B-Instruct-v0.3", | |
| "hidden_size": 4096, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 32768, | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "rms_norm_eps": 1e-5, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "use_cache": true, | |
| "vocab_size": 32000, | |
| "adapter_config": { | |
| "r": 16, | |
| "lora_alpha": 32, | |
| "target_modules": ["q_proj", "v_proj"], | |
| "lora_dropout": 0.1, | |
| "bias": "none", | |
| "task_type": "CAUSAL_LM" | |
| }, | |
| "training_config": { | |
| "checkpoint_latest": "checkpoint-36", | |
| "total_steps": 36, | |
| "optimizer": "AdamW", | |
| "learning_rate": 5e-5, | |
| "warmup_steps": 100, | |
| "weight_decay": 0.01 | |
| } | |
| } | |