delete config.json

config.json

@@ -1,57 +0,0 @@
-{
-  "_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
-  "architectures": [
-    "Qwen2ForCausalLM"
-  ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 151646,
-  "eos_token_id": 151643,
-  "hidden_act": "silu",
-  "hidden_size": 1536,
-  "initializer_range": 0.02,
-  "intermediate_size": 8960,
-  "max_position_embeddings": 131072,
-  "max_window_layers": 21,
-  "model_type": "qwen2",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 28,
-  "num_key_value_heads": 2,
-  "pad_token_id": 151654,
-  "quantization_config": {
-    "_load_in_4bit": true,
-    "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "bfloat16",
-    "bnb_4bit_quant_storage": "uint8",
-    "bnb_4bit_quant_type": "nf4",
-    "bnb_4bit_use_double_quant": true,
-    "llm_int8_enable_fp32_cpu_offload": false,
-    "llm_int8_has_fp16_weight": false,
-    "llm_int8_skip_modules": [
-      "lm_head",
-      "multi_modal_projector",
-      "merger",
-      "modality_projection",
-      "model.layers.0.self_attn",
-      "model.layers.1.mlp",
-      "model.layers.2.mlp",
-      "model.layers.26.mlp",
-      "model.layers.27.self_attn.o_proj"
-    ],
-    "llm_int8_threshold": 6.0,
-    "load_in_4bit": true,
-    "load_in_8bit": false,
-    "quant_method": "bitsandbytes"
-  },
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 10000,
-  "sliding_window": null,
-  "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.49.0.dev0",
-  "unsloth_fixed": true,
-  "use_cache": true,
-  "use_mrope": false,
-  "use_sliding_window": false,
-  "vocab_size": 151936
-}