Update README.md
Browse files
README.md
CHANGED
|
@@ -6,4 +6,35 @@ language:
|
|
| 6 |
base_model:
|
| 7 |
- Qwen/Qwen2.5-Coder-1.5B-Instruct
|
| 8 |
library_name: transformers
|
| 9 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
base_model:
|
| 7 |
- Qwen/Qwen2.5-Coder-1.5B-Instruct
|
| 8 |
library_name: transformers
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Qwen2.5-Coder-RASA-Calm
|
| 12 |
+
This model is a fine-tuned version of Qwen/Qwen2.5-Coder-1.5B-Instruct on the RASA Calm dataset for improved command generation and intent understanding.
|
| 13 |
+
### Model Description
|
| 14 |
+
This model extends Qwen2.5-Coder's capabilities by specializing in natural language understanding and command generation for conversational AI applications, particularly in the context of the RASA framework.
|
| 15 |
+
### Training Data
|
| 16 |
+
The model was fine-tuned on the RASA Calm demonstration dataset (rasa/command-generation-calm-demo-v1), which contains examples of:
|
| 17 |
+
|
| 18 |
+
Natural language user inputs
|
| 19 |
+
Corresponding intents and entities
|
| 20 |
+
Generated command structures
|
| 21 |
+
|
| 22 |
+
## Model Architecture
|
| 23 |
+
|
| 24 |
+
Base model: Qwen2.5-Coder-1.5B-Instruct
|
| 25 |
+
Architecture: Transformer-based
|
| 26 |
+
Parameters: 1.5B
|
| 27 |
+
Context window: 8192 tokens
|
| 28 |
+
|
| 29 |
+
## Intended Use
|
| 30 |
+
This model is designed for:
|
| 31 |
+
|
| 32 |
+
Converting natural language inputs into RASA-compatible commands
|
| 33 |
+
Understanding user intents in conversational AI applications
|
| 34 |
+
Generating structured outputs for chatbot development
|
| 35 |
+
|
| 36 |
+
## Limitations
|
| 37 |
+
|
| 38 |
+
The model's performance is optimized for the RASA framework and may not generalize well to other command generation tasks
|
| 39 |
+
Limited to the scope of intents and entities present in the CALM dataset
|
| 40 |
+
Inherits any limitations present in the base Qwen2.5-Coder model
|