diff --git a/README.md b/README.md index 3a155e72..c6b8b1d4 100644 --- a/README.md +++ b/README.md @@ -291,8 +291,8 @@ 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/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 | +| [GLM-4.1V](https://huggingface.co/zai-org) | 9B | glm4v | +| [GLM-4.5/GLM-4.5(6)V](https://huggingface.co/zai-org) | 9B/106B/355B | glm4_moe/glm4_5v | | [GPT-2](https://huggingface.co/openai-community) | 0.1B/0.4B/0.8B/1.5B | - | | [GPT-OSS](https://huggingface.co/openai) | 20B/120B | gpt | | [Granite 3.0-3.3](https://huggingface.co/ibm-granite) | 1B/2B/3B/8B | granite3 | diff --git a/README_zh.md b/README_zh.md index 9952c4da..ff910371 100644 --- a/README_zh.md +++ b/README_zh.md @@ -293,8 +293,8 @@ 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/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 | +| [GLM-4.1V](https://huggingface.co/zai-org) | 9B | glm4v | +| [GLM-4.5/GLM-4.5(6)V](https://huggingface.co/zai-org) | 9B/106B/355B | glm4_moe/glm4_5v | | [GPT-2](https://huggingface.co/openai-community) | 0.1B/0.4B/0.8B/1.5B | - | | [GPT-OSS](https://huggingface.co/openai) | 20B/120B | gpt | | [Granite 3.0-3.3](https://huggingface.co/ibm-granite) | 1B/2B/3B/8B | granite3 | diff --git a/src/llamafactory/data/template.py b/src/llamafactory/data/template.py index b511fe14..11b5d4f1 100644 --- a/src/llamafactory/data/template.py +++ b/src/llamafactory/data/template.py @@ -1128,7 +1128,7 @@ register_template( # copied from glm4 template register_template( - name="glm4v_moe", + name="glm4_5v", format_user=StringFormatter(slots=["<|user|>\n{{content}}<|assistant|>"]), format_assistant=StringFormatter(slots=["\n{{content}}"]), format_system=StringFormatter(slots=["<|system|>\n{{content}}"]), diff --git a/src/llamafactory/extras/constants.py b/src/llamafactory/extras/constants.py index 6f763153..64eadb4c 100644 --- a/src/llamafactory/extras/constants.py +++ b/src/llamafactory/extras/constants.py @@ -969,14 +969,6 @@ 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, @@ -1011,9 +1003,17 @@ register_model_group( "GLM-4.5V-Air-Thinking": { DownloadSource.DEFAULT: "zai-org/GLM-4.5V", DownloadSource.MODELSCOPE: "ZhipuAI/GLM-4.5V", - } + }, + "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_moe", + template="glm4_5v", multimodal=True, )