Update README.md
Browse files
README.md
CHANGED
@@ -12,9 +12,9 @@ tags:
|
|
12 |
- qwen
|
13 |
- 7b
|
14 |
---
|
15 |
-
# **Sqweeks-7B-Instruct**
|
16 |
|
17 |
-
Sqweeks-7B-Instruct is based on the Qwen 2.5 7B modality architecture, designed to enhance the reasoning capabilities of 7B-parameter models. It has been fine-tuned on a synthetic dataset based on open-thoughts & general corpus reasoning entries, further optimizing its chain-of-thought (CoT) reasoning and logical problem-solving abilities. The model demonstrates significant improvements in context understanding, structured data processing, and long-context comprehension, making it ideal for complex reasoning tasks, instruction-following, and text generation.
|
18 |
|
19 |
### **Key Improvements**
|
20 |
1. **Enhanced Knowledge and Expertise**: Improved mathematical reasoning, coding proficiency, and structured data processing.
|
|
|
12 |
- qwen
|
13 |
- 7b
|
14 |
---
|
15 |
+
# **Sqweeks-7B-Instruct-GGUF**
|
16 |
|
17 |
+
Sqweeks-7B-Instruct-GGUF is based on the Qwen 2.5 7B modality architecture, designed to enhance the reasoning capabilities of 7B-parameter models. It has been fine-tuned on a synthetic dataset based on open-thoughts & general corpus reasoning entries, further optimizing its chain-of-thought (CoT) reasoning and logical problem-solving abilities. The model demonstrates significant improvements in context understanding, structured data processing, and long-context comprehension, making it ideal for complex reasoning tasks, instruction-following, and text generation.
|
18 |
|
19 |
### **Key Improvements**
|
20 |
1. **Enhanced Knowledge and Expertise**: Improved mathematical reasoning, coding proficiency, and structured data processing.
|