Update config.json

config.json

@@ -1,251 +1,62 @@
 {
+  "architectures": [
+    "Gemma3ForConditionalGeneration"
+  ],
+  "boi_token_index": 255999,
+  "bos_token_id": 2,
+  "eoi_token_index": 256000,
+  "eos_token_id": 106,
+  "image_token_index": 262144,
+  "initializer_range": 0.02,
+  "mm_tokens_per_image": 256,
+  "model_type": "gemma3",
+  "pad_token_id": 0,
   "text_config": {
-    "return_dict": true,
-    "output_hidden_states": false,
-    "output_attentions": false,
-    "torchscript": false,
-    "torch_dtype": "float16",
-    "use_bfloat16": false,
-    "tf_legacy_loss": false,
-    "pruned_heads": {},
-    "tie_word_embeddings": true,
-    "chunk_size_feed_forward": 0,
-    "is_encoder_decoder": false,
-    "is_decoder": false,
-    "cross_attention_hidden_size": null,
-    "add_cross_attention": false,
-    "tie_encoder_decoder": false,
-    "max_length": 20,
-    "min_length": 0,
-    "do_sample": false,
-    "early_stopping": false,
-    "num_beams": 1,
-    "num_beam_groups": 1,
-    "diversity_penalty": 0.0,
-    "temperature": 1.0,
-    "top_k": 50,
-    "top_p": 1.0,
-    "typical_p": 1.0,
-    "repetition_penalty": 1.0,
-    "length_penalty": 1.0,
-    "no_repeat_ngram_size": 0,
-    "encoder_no_repeat_ngram_size": 0,
-    "bad_words_ids": null,
-    "num_return_sequences": 1,
-    "output_scores": false,
-    "return_dict_in_generate": false,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "remove_invalid_values": false,
-    "exponential_decay_length_penalty": null,
-    "suppress_tokens": null,
-    "begin_suppress_tokens": null,
-    "architectures": null,
-    "finetuning_task": null,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "tokenizer_class": null,
-    "prefix": null,
-    "bos_token_id": 2,
-    "pad_token_id": 0,
-    "eos_token_id": 1,
-    "sep_token_id": null,
-    "decoder_start_token_id": null,
-    "task_specific_params": null,
-    "problem_type": null,
-    "_name_or_path": "",
-    "_attn_implementation_autoset": false,
-    "model_type": "gemma",
-    "vocab_size": 262208,
-    "max_position_embeddings": 131072,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "cache_implementation": "hybrid",
+    "final_logit_softcapping": null,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
     "hidden_size": 2560,
+    "initializer_range": 0.02,
     "intermediate_size": 10240,
-    "num_hidden_layers": 34,
+    "max_position_embeddings": 131072,
+    "model_type": "gemma3_text",
     "num_attention_heads": 8,
-    "head_dim": 256,
+    "num_hidden_layers": 34,
     "num_key_value_heads": 4,
-    "initializer_range": 0.02,
-    "rms_norm_eps": 1e-06,
-    "use_cache": true,
-    "rope_theta": 1000000.0,
-    "attention_bias": false,
-    "attention_dropout": 0.0,
-    "hidden_activation": "gelu_pytorch_tanh",
     "query_pre_attn_scalar": 256,
-    "sliding_window": 1024,
-    "final_logit_softcapping": null,
-    "attn_logit_softcapping": null,
-    "cache_implementation": "hybrid",
+    "rms_norm_eps": 1e-06,
     "rope_local_base_freq": 10000.0,
-    "sliding_window_pattern": 6,
     "rope_scaling": {
       "factor": 8.0,
       "rope_type": "linear"
-    }
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": 1024,
+    "sliding_window_pattern": 6,
+    "torch_dtype": "bfloat16",
+    "use_cache": true,
+    "vocab_size": 262208
   },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "unsloth_fixed": true,
   "vision_config": {
-    "return_dict": true,
-    "output_hidden_states": false,
-    "output_attentions": false,
-    "torchscript": false,
-    "torch_dtype": "float16",
-    "use_bfloat16": false,
-    "tf_legacy_loss": false,
-    "pruned_heads": {},
-    "tie_word_embeddings": true,
-    "chunk_size_feed_forward": 0,
-    "is_encoder_decoder": false,
-    "is_decoder": false,
-    "cross_attention_hidden_size": null,
-    "add_cross_attention": false,
-    "tie_encoder_decoder": false,
-    "max_length": 20,
-    "min_length": 0,
-    "do_sample": false,
-    "early_stopping": false,
-    "num_beams": 1,
-    "num_beam_groups": 1,
-    "diversity_penalty": 0.0,
-    "temperature": 1.0,
-    "top_k": 50,
-    "top_p": 1.0,
-    "typical_p": 1.0,
-    "repetition_penalty": 1.0,
-    "length_penalty": 1.0,
-    "no_repeat_ngram_size": 0,
-    "encoder_no_repeat_ngram_size": 0,
-    "bad_words_ids": null,
-    "num_return_sequences": 1,
-    "output_scores": false,
-    "return_dict_in_generate": false,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "remove_invalid_values": false,
-    "exponential_decay_length_penalty": null,
-    "suppress_tokens": null,
-    "begin_suppress_tokens": null,
-    "architectures": null,
-    "finetuning_task": null,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "tokenizer_class": null,
-    "prefix": null,
-    "bos_token_id": null,
-    "pad_token_id": null,
-    "eos_token_id": null,
-    "sep_token_id": null,
-    "decoder_start_token_id": null,
-    "task_specific_params": null,
-    "problem_type": null,
-    "_name_or_path": "",
-    "_attn_implementation_autoset": false,
-    "model_type": "siglip_vision_model",
-    "vision_use_head": false,
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
     "hidden_size": 1152,
+    "image_size": 896,
     "intermediate_size": 4304,
-    "num_hidden_layers": 27,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
     "num_attention_heads": 16,
     "num_channels": 3,
+    "num_hidden_layers": 27,
     "patch_size": 14,
-    "image_size": 896,
-    "attention_dropout": 0.0,
-    "layer_norm_eps": 1e-06,
-    "hidden_act": "gelu_pytorch_tanh"
-  },
-  "mm_tokens_per_image": 256,
-  "boi_token_index": 255999,
-  "eoi_token_index": 256000,
-  "image_token_index": 262144,
-  "initializer_range": 0.02,
-  "return_dict": true,
-  "output_hidden_states": false,
-  "output_attentions": false,
-  "torchscript": false,
-  "torch_dtype": "float16",
-  "use_bfloat16": false,
-  "tf_legacy_loss": false,
-  "pruned_heads": {},
-  "tie_word_embeddings": true,
-  "chunk_size_feed_forward": 0,
-  "is_encoder_decoder": false,
-  "is_decoder": false,
-  "cross_attention_hidden_size": null,
-  "add_cross_attention": false,
-  "tie_encoder_decoder": false,
-  "max_length": 20,
-  "min_length": 0,
-  "do_sample": false,
-  "early_stopping": false,
-  "num_beams": 1,
-  "num_beam_groups": 1,
-  "diversity_penalty": 0.0,
-  "temperature": 1.0,
-  "top_k": 50,
-  "top_p": 1.0,
-  "typical_p": 1.0,
-  "repetition_penalty": 1.0,
-  "length_penalty": 1.0,
-  "no_repeat_ngram_size": 0,
-  "encoder_no_repeat_ngram_size": 0,
-  "bad_words_ids": null,
-  "num_return_sequences": 1,
-  "output_scores": false,
-  "return_dict_in_generate": false,
-  "forced_bos_token_id": null,
-  "forced_eos_token_id": null,
-  "remove_invalid_values": false,
-  "exponential_decay_length_penalty": null,
-  "suppress_tokens": null,
-  "begin_suppress_tokens": null,
-  "architectures": [
-    "Gemma2ForCausalLM"
-  ],
-  "finetuning_task": null,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1"
-  },
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1
-  },
-  "tokenizer_class": null,
-  "prefix": null,
-  "bos_token_id": 2,
-  "pad_token_id": 0,
-  "eos_token_id": 106,
-  "sep_token_id": null,
-  "decoder_start_token_id": null,
-  "task_specific_params": null,
-  "problem_type": null,
-  "_name_or_path": "unsloth/gemma-3-4b-it-unsloth-bnb-4bit",
-  "_attn_implementation_autoset": true,
-  "transformers_version": "4.51.3",
-  "model_type": "gemma2",
-  "quantization_config": {
-    "bnb_4bit_compute_dtype": "float16",
-    "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": null,
-    "llm_int8_threshold": 6.0,
-    "load_in_4bit": true,
-    "load_in_8bit": false,
-    "quant_method": "bitsandbytes"
-  },
-  "unsloth_fixed": true,
-  "unsloth_version": "2025.5.9"
-}
+    "torch_dtype": "bfloat16",
+    "vision_use_head": false
+  }
+}