Upload 3 files

config.json

@@ -10,7 +10,7 @@
   "hidden_size": 3584,
   "initializer_range": 0.02,
   "intermediate_size": 18944,
-  "max_position_embeddings": 131072,
+  "max_position_embeddings": 32768,
   "max_window_layers": 28,
   "model_type": "qwen2",
   "num_attention_heads": 28,
@@ -18,11 +18,11 @@
   "num_key_value_heads": 4,
   "rms_norm_eps": 1e-06,
   "rope_theta": 1000000.0,
-  "sliding_window": 4096,
+  "sliding_window": 131072,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.2",
-  "use_cache": false,
+  "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 152064
 }

generation_config.json

@@ -1,7 +1,11 @@
 {
   "bos_token_id": 151643,
+  "pad_token_id": 151643,
   "do_sample": true,
-  "eos_token_id": 151645,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
   "max_new_tokens": 2048,
   "transformers_version": "4.40.2"
 }

tokenizer_config.json

@@ -30,12 +30,12 @@
     "<|im_start|>",
     "<|im_end|>"
   ],
-  "bos_token": "<|endoftext|>",
+  "bos_token": null,
   "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
-  "model_max_length": 32768,
+  "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",