Update README.md
Browse files
README.md
CHANGED
|
@@ -1,51 +1,62 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
-
-
|
| 5 |
-
- trl
|
| 6 |
-
- sft
|
| 7 |
- code
|
|
|
|
| 8 |
- reasoning
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
datasets:
|
| 10 |
- nvidia/OpenCodeReasoning
|
| 11 |
-
language:
|
| 12 |
-
- en
|
| 13 |
base_model:
|
| 14 |
- Qwen/Qwen3-0.6B
|
| 15 |
-
pipeline_tag: text-generation
|
| 16 |
-
library_name: transformers
|
| 17 |
---
|
| 18 |
|
| 19 |
-
|
|
|
|
|
|
|
| 20 |
|
| 21 |
-
|
| 22 |
|
| 23 |
-
|
| 24 |
|
| 25 |
-
|
| 26 |
|
| 27 |
-
|
| 28 |
-
* Each example consists of code snippets paired with detailed step-by-step reasoning in Chain-of-Thought (CoT) style.
|
| 29 |
|
| 30 |
-
|
| 31 |
|
| 32 |
-
|
| 33 |
-
* Full fine-tuning (`full_finetuning=True`) was applied to all layers for optimal adaptation to code reasoning.
|
| 34 |
|
| 35 |
-
|
| 36 |
|
| 37 |
-
|
| 38 |
-
* The model was trained to generate correct code solutions along with the corresponding reasoning chains.
|
| 39 |
|
| 40 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
|
| 42 |
-
|
| 43 |
-
* Outputs include both intermediate reasoning steps and final code solutions, enabling transparent and interpretable code generation.
|
| 44 |
|
| 45 |
-
##
|
| 46 |
|
| 47 |
-
|
| 48 |
|
| 49 |
-
|
| 50 |
|
| 51 |
-
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
- code
|
| 5 |
+
pipeline_tag: text-generation
|
| 6 |
license: apache-2.0
|
| 7 |
tags:
|
| 8 |
+
- coderion
|
|
|
|
|
|
|
| 9 |
- code
|
| 10 |
+
- coding
|
| 11 |
- reasoning
|
| 12 |
+
- small-language-model
|
| 13 |
+
- 0.6b
|
| 14 |
+
- chronological-reasoning
|
| 15 |
+
- high-reasoning
|
| 16 |
+
- compact-model
|
| 17 |
+
library_name: transformers
|
| 18 |
datasets:
|
| 19 |
- nvidia/OpenCodeReasoning
|
|
|
|
|
|
|
| 20 |
base_model:
|
| 21 |
- Qwen/Qwen3-0.6B
|
|
|
|
|
|
|
| 22 |
---
|
| 23 |
|
| 24 |
+
<p align="center">
|
| 25 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/685ea8ff7b4139b6845ce395/1z7OO6Xv_EWEHUDemqSL1.png" alt="logo" width="200">
|
| 26 |
+
</p>
|
| 27 |
|
| 28 |
+
<h1 align="center">Coderion</h1>
|
| 29 |
|
| 30 |
+
<p align="center"><b>A compact 0.6B coding model built for strong reasoning efficiency.</b></p>
|
| 31 |
|
| 32 |
+
---
|
| 33 |
|
| 34 |
+
**Coderion** is a **small 0.6B parameter coding-focused language model** designed for **high and xhigh chronological reasoning** in programming tasks.
|
|
|
|
| 35 |
|
| 36 |
+
It is built to deliver **surprisingly strong structured reasoning and coding performance for its size**, focusing on consistency, logical step progression, and efficient problem solving.
|
| 37 |
|
| 38 |
+
While **Coderion is not intended to be a general everyday assistant**, it is a **small but capable specialist model** that performs well within its class and remains **reliable for compact code reasoning workloads**.
|
|
|
|
| 39 |
|
| 40 |
+
---
|
| 41 |
|
| 42 |
+
## Key Characteristics
|
|
|
|
| 43 |
|
| 44 |
+
- **0.6B parameters**
|
| 45 |
+
- **Dedicated to code**
|
| 46 |
+
- **Optimized for high reasoning intensity**
|
| 47 |
+
- **Chronological reasoning style**
|
| 48 |
+
- **Strong consistency for a compact model**
|
| 49 |
+
- **Designed for efficient performance despite its small size**
|
| 50 |
|
| 51 |
+
---
|
|
|
|
| 52 |
|
| 53 |
+
## Limitations
|
| 54 |
|
| 55 |
+
Coderion is a **small specialized model**.
|
| 56 |
|
| 57 |
+
Because of that:
|
| 58 |
|
| 59 |
+
- It may not match larger models on broad real-world assistant tasks
|
| 60 |
+
- It is not primarily designed for daily casual use
|
| 61 |
+
- It performs best when used for **focused coding and reasoning workloads**
|
| 62 |
+
- Its main strength is **efficiency, consistency, and reasoning quality relative to size**
|