[assets] update readme (#9587)

README.md

@@ -291,7 +291,7 @@ Read technical notes:
 | [Gemma/Gemma 2/CodeGemma](https://huggingface.co/google)          | 2B/7B/9B/27B                     | gemma/gemma2         |
 | [Gemma 3/Gemma 3n](https://huggingface.co/google)                 | 270M/1B/4B/6B/8B/12B/27B         | gemma3/gemma3n       |
 | [GLM-4/GLM-4-0414/GLM-Z1](https://huggingface.co/zai-org)         | 9B/32B                           | glm4/glmz1           |
-| [GLM-4.1V](https://huggingface.co/zai-org)                        | 9B                               | glm4v                |
+| [GLM-4.1V/GLM-4.6V](https://huggingface.co/zai-org)               | 9B/106B                          | glm4v                |
 | [GLM-4.5/GLM-4.5V](https://huggingface.co/zai-org)                | 106B/355B                        | glm4_moe/glm4v_moe   |
 | [GPT-2](https://huggingface.co/openai-community)                  | 0.1B/0.4B/0.8B/1.5B              | -                    |
 | [GPT-OSS](https://huggingface.co/openai)                          | 20B/120B                         | gpt                  |

README_zh.md

@@ -293,7 +293,7 @@ https://github.com/user-attachments/assets/43b700c6-a178-41db-b1f8-8190a5d3fcfc
 | [Gemma/Gemma 2/CodeGemma](https://huggingface.co/google)          | 2B/7B/9B/27B                     | gemma/gemma2         |
 | [Gemma 3/Gemma 3n](https://huggingface.co/google)                 | 270M/1B/4B/6B/8B/12B/27B         | gemma3/gemma3n       |
 | [GLM-4/GLM-4-0414/GLM-Z1](https://huggingface.co/zai-org)         | 9B/32B                           | glm4/glmz1           |
-| [GLM-4.1V](https://huggingface.co/zai-org)                        | 9B                               | glm4v                |
+| [GLM-4.1V/GLM-4.6V](https://huggingface.co/zai-org)               | 9B/106B                          | glm4v                |
 | [GLM-4.5/GLM-4.5V](https://huggingface.co/zai-org)                | 106B/355B                        | glm4_moe/glm4v_moe   |
 | [GPT-2](https://huggingface.co/openai-community)                  | 0.1B/0.4B/0.8B/1.5B              | -                    |
 | [GPT-OSS](https://huggingface.co/openai)                          | 20B/120B                         | gpt                  |

src/llamafactory/data/template.py

@@ -199,9 +199,12 @@ class Template:
             logger.info_rank0(f"Add pad token: {tokenizer.pad_token}")
 
         if stop_words:
-            num_added_tokens = tokenizer.add_special_tokens(
-                dict(additional_special_tokens=stop_words), replace_additional_special_tokens=False
-            )
+            try:
+                num_added_tokens = tokenizer.add_special_tokens(
+                    dict(additional_special_tokens=stop_words), replace_additional_special_tokens=False
+                )
+            except TypeError:
+                num_added_tokens = tokenizer.add_special_tokens(dict(additional_special_tokens=stop_words))
             logger.info_rank0("Add {} to stop words.".format(",".join(stop_words)))
             if num_added_tokens > 0:
                 logger.warning_rank0("New tokens have been added, make sure `resize_vocab` is True.")

src/llamafactory/extras/constants.py

@@ -969,6 +969,14 @@ register_model_group(
             DownloadSource.DEFAULT: "zai-org/GLM-4.1V-9B-Thinking",
             DownloadSource.MODELSCOPE: "ZhipuAI/GLM-4.1V-9B-Thinking",
         },
+        "GLM-4.6V": {
+            DownloadSource.DEFAULT: "zai-org/GLM-4.6V",
+            DownloadSource.MODELSCOPE: "ZhipuAI/GLM-4.6V",
+        },
+        "GLM-4.6V-Flash": {
+            DownloadSource.DEFAULT: "zai-org/GLM-4.6V-Flash",
+            DownloadSource.MODELSCOPE: "ZhipuAI/GLM-4.6V-Flash",
+        },
     },
     template="glm4v",
     multimodal=True,

src/llamafactory/train/sft/workflow.py

@@ -78,8 +78,11 @@ def run_sft(
 
     # Compatible with Transformers v4 and Transformers v5
     if is_transformers_version_greater_than("5.0.0RC0"):
-        extra_special_tokens = getattr(tokenizer, "_extra_special_tokens", [])
-        extra_ids = tokenizer.convert_tokens_to_ids(extra_special_tokens)
+        extra_ids = getattr(tokenizer, "additional_special_tokens_ids", None)
+        if not isinstance(extra_ids, list):
+            extra_special_tokens = getattr(tokenizer, "_extra_special_tokens", [])
+            string_tokens = [str(t) for t in extra_special_tokens]
+            extra_ids = tokenizer.convert_tokens_to_ids(string_tokens)
         all_eos_ids = [tokenizer.eos_token_id] + [i for i in extra_ids if i != -1]
         unique_eos_ids = list(dict.fromkeys(all_eos_ids))
         gen_kwargs["eos_token_id"] = unique_eos_ids