Infinity support: Short max_length=2048 for more optimized deployment (#20)

- Infinity support: Short max_length for more optimized deployment (1ea73a6c63f75da2a33e3858794337060ed2ed80)
- Update config.json (cbbb9d205c1e15ebaaa91a3b2f7e2d60a515ad9a)
- Update sentence_bert_config.json (c87570a3ad3feb69845da7bc5969fc4dcfde6b21)
- Update config.json (8f52789e252cb6ee377905c9bc517e317f10c828)
- Update config.json (2e8a2b8d43dcd68042d6f2bf7670086f90055a67)
- Update config.json (c8a458f1de52069db23239c83f6984a604950e4e)
- Update sentence_bert_config.json (6bd0f999825e0d1057b77b6574de47522da563a1)


Co-authored-by: Michael <michaelfeil@users.noreply.huggingface.co>

config.json

@@ -14,7 +14,7 @@
   "hidden_size": 1536,
   "initializer_range": 0.02,
   "intermediate_size": 8960,
-  "max_position_embeddings": 131072,
+  "max_position_embeddings": 2048,
   "max_window_layers": 21,
   "model_type": "qwen2",
   "num_attention_heads": 12,
@@ -22,7 +22,7 @@
   "num_key_value_heads": 2,
   "rms_norm_eps": 1e-06,
   "rope_theta": 1000000.0,
-  "sliding_window": 131072,
+  "sliding_window": 2048,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.41.2",

sentence_bert_config.json

@@ -1,4 +1,4 @@
 {
-  "max_seq_length": 32768,
+  "max_seq_length": 2048,
   "do_lower_case": false
 }

tokenizer_config.json

@@ -39,7 +39,7 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "errors": "replace",
-  "model_max_length": 32768,
+  "model_max_length": 2048,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",