eliza555beth2002/DeepSeek-R1-Distill-Text2SQL-Russian1100

1{2  "alpha_pattern": {},3  "auto_mapping": {4    "base_model_class": "LlamaForCausalLM",5    "parent_library": "transformers.models.llama.modeling_llama",6    "unsloth_fixed": true7  },8  "base_model_name_or_path": "unsloth/deepseek-r1-distill-llama-8b-unsloth-bnb-4bit",9  "bias": "none",10  "corda_config": null,11  "eva_config": null,12  "exclude_modules": null,13  "fan_in_fan_out": false,14  "inference_mode": true,15  "init_lora_weights": true,16  "layer_replication": null,17  "layers_pattern": null,18  "layers_to_transform": null,19  "loftq_config": {},20  "lora_alpha": 16,21  "lora_bias": false,22  "lora_dropout": 0,23  "megatron_config": null,24  "megatron_core": "megatron.core",25  "modules_to_save": null,26  "peft_type": "LORA",27  "qalora_group_size": 16,28  "r": 16,29  "rank_pattern": {},30  "revision": null,31  "target_modules": [32    "k_proj",33    "up_proj",34    "gate_proj",35    "v_proj",36    "down_proj",37    "q_proj",38    "o_proj"39  ],40  "task_type": "CAUSAL_LM",41  "trainable_token_indices": null,42  "use_dora": false,43  "use_qalora": false,44  "use_rslora": false45}