Fix: float causal mask, weight tying, attention_mask, config aliases

config.json

@@ -1,66 +1,11 @@
 {
-  "return_dict": true,
-  "output_hidden_states": false,
-  "torchscript": false,
-  "dtype": null,
-  "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,
-  "architectures": [
-    "KonkanGPT"
-  ],
-  "finetuning_task": null,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1"
-  },
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1
+  "model_type": "konkangpt",
+  "_name_or_path": "omdeep22/Gonyai-v1",
+  "architectures": ["KonkanGPT"],
+  "auto_map": {
+    "AutoConfig": "configuration_konkan.KonkanSmallConfig",
+    "AutoModelForCausalLM": "modeling_konkan.KonkanGPT"
   },
-  "task_specific_params": null,
-  "problem_type": null,
-  "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,
-  "max_length": 20,
-  "min_length": 0,
-  "do_sample": false,
-  "early_stopping": false,
-  "num_beams": 1,
-  "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,
-  "num_beam_groups": 1,
-  "diversity_penalty": 0.0,
-  "_name_or_path": "",
-  "transformers_version": "4.57.1",
-  "tf_legacy_loss": false,
-  "use_bfloat16": false,
   "vocab_size": 32000,
   "d_model": 768,
   "n_layers": 12,
@@ -68,10 +13,25 @@
   "d_ff": 3072,
   "max_len": 1024,
   "dropout": 0.1,
-  "model_type": "konkangpt",
-  "output_attentions": false,
-  "auto_map": {
-    "AutoConfig": "configuration_konkan.KonkanSmallConfig",
-    "AutoModelForCausalLM": "modeling_konkan.KonkanGPT"
-  }
+  "hidden_size": 768,
+  "num_hidden_layers": 12,
+  "num_attention_heads": 12,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 1024,
+  "bos_token_id": 0,
+  "pad_token_id": 1,
+  "eos_token_id": 2,
+  "is_decoder": true,
+  "is_encoder_decoder": false,
+  "use_cache": false,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.0",
+  "max_length": 1024,
+  "do_sample": true,
+  "temperature": 0.7,
+  "top_k": 50,
+  "top_p": 0.9,
+  "repetition_penalty": 1.0,
+  "tokenizer_class": "PreTrainedTokenizerFast"
 }