README: restore apache-2.0 + zero-waste/no-enforced-limits philosophy (official copy had drifted to cc-by-nc-nd-4.0)

README.md

@@ -2,7 +2,7 @@
 language:
 - en
 - zh
-license: cc-by-nc-nd-4.0
+license: apache-2.0
 library_name: transformers
 tags:
 - chat-template
@@ -100,16 +100,16 @@ All templates are located in the `templates/` directory and pre-configured for n
 | Target Model Architecture | File | Native Format |
 |---|---|---|
 | **Universal / ChatML** | `templates/universal.jinja` | `<|im_start|>`, `<|im_end|>` |
-| **Qwen 3.5/3.6/3.8 With vision** | `templates/qwen.jinja` | `<|im_start|>`, `<|im_end|>`, Multimodal Vision |
-| **DeepSeek 4/4.1** | `templates/deepseek.jinja` | `<｜User｜>`, `<｜Assistant｜>`, Native DSML |
-| **Meta Llama 4** | `templates/llama3.jinja` | `<|start_header_id|>`, `<|eot_id|>` |
+| **Qwen 2.5 / 3.8 / Vision** | `templates/qwen.jinja` | `<|im_start|>`, `<|im_end|>`, Multimodal Vision |
+| **DeepSeek Native** | `templates/deepseek.jinja` | `<｜User｜>`, `<｜Assistant｜>`, Native DSML |
+| **Meta Llama 3 / 4** | `templates/llama3.jinja` | `<|start_header_id|>`, `<|eot_id|>` |
 | **Mistral / Mixtral** | `templates/mistral.jinja` | `[INST]`, `[/INST]` |
-| **Google Gemma 3/4** | `templates/gemma.jinja` | `<start_of_turn>`, `<end_of_turn>` |
-| **Zhipu GLM 5/5.3** | `templates/glm.jinja` | `[gMASK]<sop>`, `<|user|>`, `<|assistant|>` |
+| **Google Gemma 2 / 3** | `templates/gemma.jinja` | `<start_of_turn>`, `<end_of_turn>` |
+| **Zhipu GLM 4 / 5.3** | `templates/glm.jinja` | `[gMASK]<sop>`, `<|user|>`, `<|assistant|>` |
 | **Vanilla Reference** | `templates/regular_*.jinja` | Minimal, zero-overhead baseline templates |
 
 ---
 
 <div align="center">
 Developed and maintained by <b>Solstice AI</b>.
-</div>
+</div>