fwizzer1/Fwizzer-R1-3B-RU

1{2  "alora_invocation_tokens": null,3  "alpha_pattern": {},4  "arrow_config": null,5  "auto_mapping": {6    "base_model_class": "Mistral3ForConditionalGeneration",7    "parent_library": "transformers.models.mistral3.modeling_mistral3",8    "unsloth_fixed": true9  },10  "base_model_name_or_path": "unsloth/Ministral-3-3B-Instruct-2512-bnb-4bit",11  "bias": "none",12  "corda_config": null,13  "ensure_weight_tying": false,14  "eva_config": null,15  "exclude_modules": null,16  "fan_in_fan_out": false,17  "inference_mode": true,18  "init_lora_weights": true,19  "layer_replication": null,20  "layers_pattern": null,21  "layers_to_transform": null,22  "loftq_config": {},23  "lora_alpha": 32,24  "lora_bias": false,25  "lora_dropout": 0,26  "lora_ga_config": null,27  "megatron_config": null,28  "megatron_core": "megatron.core",29  "modules_to_save": null,30  "peft_type": "LORA",31  "peft_version": "0.19.1",32  "qalora_group_size": 16,33  "r": 16,34  "rank_pattern": {},35  "revision": null,36  "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj))|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)))",37  "target_parameters": null,38  "task_type": "CAUSAL_LM",39  "trainable_token_indices": null,40  "use_bdlora": null,41  "use_dora": false,42  "use_qalora": false,43  "use_rslora": false44}