Add response_template to tokenizer_config.json (#3)

- Add response_template to tokenizer_config.json (2f963e48c1de0e055cee982d332f659fd8ec6ad7)
- Update README.md (5c442ce5a0154487a7e5c0ae8c3d10824cf49831)


Co-authored-by: Matthew Carrigan <Rocketknight1@users.noreply.huggingface.co>

README.md

@@ -181,7 +181,7 @@ outputs = model.generate(**inputs, max_new_tokens=1024)
 response = processor.decode(outputs[0][input_len:], skip_special_tokens=False)
 
 # Parse output
-processor.parse_response(response)
+processor.parse_response(response, prefix=inputs["input_ids"])
 ```
 
 To enable reasoning, set `enable_thinking=True` and the `parse_response` function will take care of parsing the thinking output.
@@ -241,7 +241,7 @@ outputs = model.generate(**inputs, max_new_tokens=512)
 response = processor.decode(outputs[0][input_len:], skip_special_tokens=False)
 
 # Parse output
-processor.parse_response(response)
+processor.parse_response(response, prefix=inputs["input_ids"])
 ```
 
 </details>
@@ -299,7 +299,7 @@ outputs = model.generate(**inputs, max_new_tokens=512)
 response = processor.decode(outputs[0][input_len:], skip_special_tokens=False)
 
 # Parse output
-processor.parse_response(response)
+processor.parse_response(response, prefix=inputs["input_ids"])
 ```
 
 </details>
@@ -358,7 +358,7 @@ outputs = model.generate(**inputs, max_new_tokens=512)
 response = processor.decode(outputs[0][input_len:], skip_special_tokens=False)
 
 # Parse output
-processor.parse_response(response)
+processor.parse_response(response, prefix=inputs["input_ids"])
 ```
 
 </details>

tokenizer_config.json

@@ -85,6 +85,52 @@
     "type": "object",
     "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
   },
+  "response_template": {
+    "defaults": {
+      "role": "assistant"
+    },
+    "fields": {
+      "content": {
+        "close": [
+          "<turn|>",
+          "<|tool_response>",
+          "<eos>"
+        ],
+        "content": "text"
+      },
+      "thinking": {
+        "close": "<channel|>",
+        "content": "text",
+        "open": "<|channel>thought\n"
+      },
+      "tool_calls": {
+        "close": "<tool_call|>",
+        "content": "json",
+        "content_args": {
+          "string_delims": [
+            [
+              "<|\"|>",
+              "<|\"|>"
+            ]
+          ],
+          "unquoted_keys": true
+        },
+        "open_pattern": "<\\|tool_call>call:(?P<name>\\w+)",
+        "repeats": true,
+        "transform": {
+          "function": {
+            "arguments": "{content}",
+            "name": "{name}"
+          },
+          "type": "function"
+        }
+      }
+    },
+    "start_anchor": [
+      "<|turn>model\n",
+      "<tool_response|>"
+    ]
+  },
   "soc_token": "<|channel>",
   "sot_token": "<|turn>",
   "stc_token": "<|tool_call>",