Update README.md
Browse files
README.md
CHANGED
|
@@ -11,4 +11,21 @@ tags:
|
|
| 11 |
- sft
|
| 12 |
- code
|
| 13 |
pipeline_tag: text-generation
|
| 14 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
- sft
|
| 12 |
- code
|
| 13 |
pipeline_tag: text-generation
|
| 14 |
+
---
|
| 15 |
+
# Qwen 3 Code Reasoning
|
| 16 |
+
|
| 17 |
+
A small Qwen 3 4 billion parameter model trained on [nvidia/OpenCodeReasoning](https://huggingface.co/datasets/nvidia/OpenCodeReasoning) for coding tasks.
|
| 18 |
+
For Coding, it is recommended to be in thinking mode.
|
| 19 |
+
|
| 20 |
+
## Strengths
|
| 21 |
+
- Code generation
|
| 22 |
+
- Logical question answering
|
| 23 |
+
|
| 24 |
+
## Drawbacks
|
| 25 |
+
- Heavy overthinking
|
| 26 |
+
- Context overflow
|
| 27 |
+
|
| 28 |
+
## Recommended Usage:
|
| 29 |
+
- [Ollama](https://ollama.com/)
|
| 30 |
+
- [LM Studio](https://lmstudio.ai/)
|
| 31 |
+
- [Llama.cpp](https://github.com/ggml-org/llama.cpp)
|