Season998 commited on
Commit
83e5ba4
ยท
verified ยท
1 Parent(s): 3032dc7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +27 -3
README.md CHANGED
@@ -34,7 +34,32 @@ Traffic signal control (TSC) is vital for mitigating congestion and sustaining u
34
  This model supports a wide range of deployment methods compatible with the Qwen architecture, including those provided by the `transformers` library. You can easily use it in a chat mode to interactively discuss traffic-related scenarios.
35
  For more detailed information on deployment, please refer to the official [Qwen documentation](https://qwen.readthedocs.io/en/latest/).
36
 
37
- The model is compatible with the signal control evaluation code provided by **LLMLight** [https://github.com/usail-hkust/LLMTSCS]. You can quickly reproduce our results with minor changes to the prompt format.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
38
 
39
  A big thanks to these excellent projects! ๐Ÿ‘
40
 
@@ -42,9 +67,8 @@ A big thanks to these excellent projects! ๐Ÿ‘
42
 
43
  ## **Future Releases** ๐Ÿš€
44
 
45
- We plan to release our evaluation code (most necessary) and training code soon.
46
 
47
- We are working on upgrading base mode Qwen 2.5->Qwen 3 for latest features.
48
 
49
  ---
50
 
 
34
  This model supports a wide range of deployment methods compatible with the Qwen architecture, including those provided by the `transformers` library. You can easily use it in a chat mode to interactively discuss traffic-related scenarios.
35
  For more detailed information on deployment, please refer to the official [Qwen documentation](https://qwen.readthedocs.io/en/latest/).
36
 
37
+ The model is compatible with the signal control evaluation code provided by **LLMLight** [https://github.com/usail-hkust/LLMTSCS].
38
+
39
+ You can easily reproduce our results with minor changes to the prompt format.
40
+
41
+ #### Quick Reproduction Steps
42
+
43
+ 1. **Clone the Repository**:
44
+ ```bash
45
+ git clone https://github.com/usail-hkust/LLMTSCS
46
+ ```
47
+
48
+ 2. **Create a Related Environment**:
49
+ Follow the instructions in the repository to set up the necessary environment.
50
+
51
+ 3. **Run the Script**:
52
+ ```bash
53
+ python run_open_LLM_with_vllm.py \
54
+ --llm_model LLM_MODEL_NAME_ONLY_FOR_LOG \
55
+ --llm_path LLM_PATH (input the location of Traffic-R1's checkpoint) \
56
+ --dataset hangzhou \
57
+ --traffic_file anon_4_4_hangzhou_real.json \
58
+ --proj_name TSCS
59
+ ```
60
+
61
+ Important Note: The format prompt of LLMLight is inconsistent with Traffic-R1.
62
+ For more stable results, consider making changes to LLMLight's format prompt codes.
63
 
64
  A big thanks to these excellent projects! ๐Ÿ‘
65
 
 
67
 
68
  ## **Future Releases** ๐Ÿš€
69
 
 
70
 
71
+ We are working on upgrading base mode Qwen 2.5-> Qwen 3/VL for the latest features.
72
 
73
  ---
74