Add pipeline tag, library name, correct base model and add sample usage

Hi! I'm Niels, part of the community science team at Hugging Face.

This pull request improves the model card for **Arctic-AWM-14B** by:
- Adding the `pipeline_tag: text-generation` and `library_name: transformers` metadata for better discoverability and to enable the "Use in Transformers" button.
- Correcting the `base_model` metadata from `Qwen/Qwen3-4B` to `Qwen/Qwen3-14B` to match the model's actual architecture.
- Adding a **Sample Usage** section based on the official GitHub repository to help users get started with the model using vLLM and the AWM CLI.
- Ensuring the research paper is properly linked.

These changes help users find and use your model more effectively!

README.md

@@ -1,14 +1,16 @@
 ---
-license: apache-2.0
 base_model:
-- Qwen/Qwen3-4B
+- Qwen/Qwen3-14B
 language:
-  - en
+- en
+license: apache-2.0
 tags:
-  - agent
-  - tool-use
-  - reinforcement-learning
-  - mcp
+- agent
+- tool-use
+- reinforcement-learning
+- mcp
+pipeline_tag: text-generation
+library_name: transformers
 ---
 
 <h1 align="center">Arctic-AWM-14B</h1>
@@ -29,11 +31,9 @@ tags:
   <sup>1</sup>UNC-Chapel Hill &nbsp; <sup>2</sup>Snowflake AI Research &nbsp;
 </p>
 
-
-
 # Overview
 
-**Arctic-AWM-14B** is a multi-turn tool-use agent model trained with agentic reinforcement learning on [Qwen3-14B](https://huggingface.co/Qwen/Qwen3-14B), using the fully synthetic environments from [AgentWorldModel-1K](https://huggingface.co/datasets/Snowflake/AgentWorldModel-1K).
+**Arctic-AWM-14B** is a multi-turn tool-use agent model trained with agentic reinforcement learning on [Qwen3-14B](https://huggingface.co/Qwen/Qwen3-14B), using the fully synthetic environments from [AgentWorldModel-1K](https://huggingface.co/datasets/Snowflake/AgentWorldModel-1K). It was introduced in the paper [Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning](https://huggingface.co/papers/2602.10090).
 
 The model is trained to interact with tool-use environments exposed via a unified MCP (Model Context Protocol) interface, enabling strong multi-turn agentic capabilities.
 
@@ -52,6 +52,25 @@ Related resources are also available, please check:
 | 🤖 Arctic-AWM-8B | [🤗 Snowflake/Arctic-AWM-8B](https://huggingface.co/Snowflake/Arctic-AWM-8B) |
 | 🤖 Arctic-AWM-14B | [🤗 Snowflake/Arctic-AWM-14B](https://huggingface.co/Snowflake/Arctic-AWM-14B) |
 
+# Sample Usage
+
+You can use [vLLM](https://github.com/vllm-project/vllm) to serve the model and interact with it using the `awm` CLI provided in the [official repository](https://github.com/Snowflake-Labs/agent-world-model).
+
+```bash
+# serve the model
+vllm serve Snowflake/Arctic-AWM-14B --host 127.0.0.1 --port 8000
+
+# start the environment (example scenario)
+awm env start --scenario e_commerce_33 --envs_load_path outputs/gen_envs.jsonl --port 8001
+
+# run the agent
+awm agent \
+    --task "show me the top 10 most expensive products" \
+    --mcp_url http://localhost:8001/mcp \
+    --vllm_url http://localhost:8000/v1 \
+    --model Snowflake/Arctic-AWM-14B
+```
+
 # Citation
 
 If you find this resource useful, please kindly cite:
@@ -66,4 +85,4 @@ If you find this resource useful, please kindly cite:
       primaryClass={cs.AI},
       url={https://arxiv.org/abs/2602.10090}, 
 }
-```
+```