| { | |
| "_name_or_path": "haiqa-sheraz/llama3_cases01", | |
| "alpha_pattern": {}, | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "auto_mapping": null, | |
| "base_model_name_or_path": "unsloth/llama-3-8b-bnb-4bit", | |
| "bias": "none", | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "fan_in_fan_out": false, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "inference_mode": true, | |
| "init_lora_weights": true, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11008, | |
| "layer_replication": null, | |
| "layers_pattern": null, | |
| "layers_to_transform": null, | |
| "loftq_config": {}, | |
| "lora_alpha": 16, | |
| "lora_dropout": 0, | |
| "max_position_embeddings": 2048, | |
| "megatron_config": null, | |
| "megatron_core": "megatron.core", | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "modules_to_save": null, | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 32, | |
| "peft_type": "LORA", | |
| "pretraining_tp": 1, | |
| "r": 16, | |
| "rank_pattern": {}, | |
| "revision": "unsloth", | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "target_modules": [ | |
| "v_proj", | |
| "up_proj", | |
| "gate_proj", | |
| "q_proj", | |
| "k_proj", | |
| "down_proj", | |
| "o_proj" | |
| ], | |
| "task_type": "CAUSAL_LM", | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.42.3", | |
| "use_cache": true, | |
| "use_dora": false, | |
| "use_rslora": false, | |
| "vocab_size": 32000 | |
| } | |