Update README.md

README.md

@@ -39,7 +39,7 @@ A model trained on a synthesis dataset of over **120 million** entries, this dat
 
 Despite the absence of thorough alignment with human preferences, the model is under no obligation to cater to poorly constructed prompts or the clichés often found in conventional benchmarks. Bonus: Included is an implementation of a **Vision Language Model** that has undergone Locked-Image Tuning.
 
-**Supported Input Modalities**: text, image. For text-only weight, please use the branch `revision=text-only` at https://huggingface.co/CausalLM/miniG/tree/text-only
+**Supported Input Modalities**: text, image. For text-only weight, please use the branch `revision=text-only` at https://huggingface.co/CausalLM/miniG/tree/text-only . And [GGUF](https://huggingface.co/CausalLM/miniG/tree/gguf) for text-only should be working after PR [#9194](https://github.com/ggerganov/llama.cpp/pull/9194) was merged.
 
 **Context Window:** 1M tokens
 
@@ -65,7 +65,7 @@ Despite the absence of thorough alignment with human preferences, the model is u
 
 尽管该模型没有完全对齐人类偏好，但它没有义务迎合不良构建的提示或常见基准测试中的陈词滥调。额外内容：包含了经过锁定图像微调的**视觉语言模型**实现。
 
-**支持的输入模态**：文本、图像。对于纯文本权重，请使用 https://huggingface.co/CausalLM/miniG/tree/text-only 上的分支 `revision=text-only`
+**支持的输入模态**：文本、图像。对于纯文本权重，请使用 https://huggingface.co/CausalLM/miniG/tree/text-only 上的分支 `revision=text-only`。在 PR [#9194](https://github.com/ggerganov/llama.cpp/pull/9194) 合并后，适用于纯文本的 [GGUF](https://huggingface.co/CausalLM/miniG/tree/gguf) 应该可以正常工作。
 
 **上下文窗口**：1M 个标记