Triangle104 commited on
Commit
b0c6a62
·
verified ·
1 Parent(s): 8d1d5e2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -0
README.md CHANGED
@@ -13,6 +13,16 @@ tags:
13
  This model was converted to GGUF format from [`Qwen/Qwen3-30B-A3B-Instruct-2507`](https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
14
  Refer to the [original model card](https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507) for more details on the model.
15
 
 
 
 
 
 
 
 
 
 
 
16
  ## Use with llama.cpp
17
  Install llama.cpp through brew (works on Mac and Linux)
18
 
 
13
  This model was converted to GGUF format from [`Qwen/Qwen3-30B-A3B-Instruct-2507`](https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
14
  Refer to the [original model card](https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507) for more details on the model.
15
 
16
+ ---
17
+ We introduce the updated version of the Qwen3-30B-A3B non-thinking mode, named Qwen3-30B-A3B-Instruct-2507, featuring the following key enhancements:
18
+
19
+
20
+ - Significant improvements in general capabilities, including instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool usage.
21
+ - Substantial gains in long-tail knowledge coverage across multiple languages.
22
+ - Markedly better alignment with user preferences in subjective and open-ended tasks, enabling more helpful responses and higher-quality text generation.
23
+ - Enhanced capabilities in 256K long-context understanding.
24
+
25
+ ---
26
  ## Use with llama.cpp
27
  Install llama.cpp through brew (works on Mac and Linux)
28