Upload folder using huggingface_hub

mlc-chat-config.json

@@ -12,6 +12,7 @@
     "rms_norm_eps": 1e-06,
     "rope_theta": 1000000.0,
     "vocab_size": 151936,
+    "tie_word_embeddings": false,
     "context_window_size": 32768,
     "prefill_chunk_size": 2048,
     "tensor_parallel_shards": 1,
@@ -25,6 +26,7 @@
   "prefill_chunk_size": 2048,
   "attention_sink_size": -1,
   "tensor_parallel_shards": 1,
+  "pipeline_parallel_stages": 1,
   "temperature": 1.0,
   "presence_penalty": 0.0,
   "frequency_penalty": 0.0,
@@ -42,9 +44,9 @@
     "strip_space_in_decode": false
   },
   "conv_template": {
-    "name": "chatml",
+    "name": "qwen2",
     "system_template": "<|im_start|>system\n{system_message}<|im_end|>\n",
-    "system_message": "A conversation between a user and an LLM-based AI assistant. The assistant gives helpful and honest answers.",
+    "system_message": "You are a helpful assistant.",
     "system_prefix_token_ids": null,
     "add_role_after_system_message": true,
     "roles": {
@@ -63,10 +65,11 @@
     "role_content_sep": "\n",
     "role_empty_sep": "\n",
     "stop_str": [
-      "<|im_end|>"
+      "<|endoftext|>, <|im_end|>"
     ],
     "stop_token_ids": [
-      2
+      151643,
+      151645
     ],
     "function_string": "",
     "use_function_calling": false
@@ -76,8 +79,5 @@
   "eos_token_id": [
     151645,
     151643
-  ],
-  "mean_gen_len": 128,
-  "max_gen_len": 512,
-  "shift_fill_factor": 0.3
+  ]
 }