Update README

README.md

@@ -1,3 +1,15 @@
 ---
 license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen2.5-14B-Instruct/blob/main/LICENSE
+language:
+  - en
+base_model: Qwen/Qwen2.5-14B-Instruct
+base_model_relation: quantized
+library_name: mlc-llm
+pipeline_tag: text-generation
+tags:
+  - chat
 ---
+
+4-bit GPTQ quantized version of [Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct).
+

config.json

@@ -0,0 +1,26 @@
+{
+  "quantization_config": {
+    "batch_size": 1,
+    "bits": 4,
+    "block_name_to_quantize": null,
+    "cache_block_outputs": true,
+    "damp_percent": 0.01,
+    "dataset": null,
+    "desc_act": false,
+    "exllama_config": {
+      "version": 1
+    },
+    "group_size": 128,
+    "max_input_length": null,
+    "model_seqlen": null,
+    "module_name_preceding_first_block": null,
+    "modules_in_block_to_quantize": null,
+    "pad_token_id": null,
+    "quant_method": "gptq",
+    "sym": true,
+    "tokenizer": null,
+    "true_sequential": true,
+    "use_cuda_fp16": false,
+    "use_exllama": true
+  }
+}