Update README.md
Browse files
README.md
CHANGED
@@ -12,7 +12,7 @@ YAML tags: "coming soon"
|
|
12 |
|
13 |
## Overview
|
14 |
|
15 |
-
The **APEX-E3 Dec-Enc Function-Call Model (v0.011)** is a fine-tuned T5-small model
|
16 |
|
17 |
With a special focus on capital market use cases, it was trained on queries that map directly to functions like **`selectStocks`**, **`run_backtest`**, and **`optimizer`**, ensuring precise extraction of parameters needed for advanced trading, backtesting, and portfolio optimization workflows.
|
18 |
|
@@ -25,7 +25,7 @@ This solution is **lightweight**, **highly performant**, and—thanks to our **n
|
|
25 |
- Produces direct calls to your functions with minimal overhead.
|
26 |
|
27 |
2. **Private & Agentic**
|
28 |
-
- Ideal for
|
29 |
|
30 |
3. **Ultra-Easy Training Approach**
|
31 |
- Using a simple Python/Flask app and structured JSON, you can re-train or extend the model on your own custom function definitions in *minutes*, no large-scale ML infrastructure required.
|
@@ -40,7 +40,7 @@ This solution is **lightweight**, **highly performant**, and—thanks to our **n
|
|
40 |
## Model Details
|
41 |
|
42 |
- **Base Model**: [T5-small](https://huggingface.co/t5-small)
|
43 |
-
- **Fine-Tuning**:
|
44 |
- **Parameter Count**: ~60M
|
45 |
- **Tokenizer**: T5 SentencePiece tokenizer
|
46 |
|
|
|
12 |
|
13 |
## Overview
|
14 |
|
15 |
+
The **APEX-E3 Dec-Enc Function-Call Model (v0.011)** is a fine-tuned T5-small model specialised in generating *function call structures* from plain English queries. Rather than producing unstructured text, this model outputs instructions for specific function calls, including all relevant parameters.
|
16 |
|
17 |
With a special focus on capital market use cases, it was trained on queries that map directly to functions like **`selectStocks`**, **`run_backtest`**, and **`optimizer`**, ensuring precise extraction of parameters needed for advanced trading, backtesting, and portfolio optimization workflows.
|
18 |
|
|
|
25 |
- Produces direct calls to your functions with minimal overhead.
|
26 |
|
27 |
2. **Private & Agentic**
|
28 |
+
- Ideal for organisations seeking on-premises or private cloud solutions where data control and agentic autonomy are paramount.
|
29 |
|
30 |
3. **Ultra-Easy Training Approach**
|
31 |
- Using a simple Python/Flask app and structured JSON, you can re-train or extend the model on your own custom function definitions in *minutes*, no large-scale ML infrastructure required.
|
|
|
40 |
## Model Details
|
41 |
|
42 |
- **Base Model**: [T5-small](https://huggingface.co/t5-small)
|
43 |
+
- **Fine-Tuning**: Customised data mapping natural language to function calls, specifically in capital markets contexts.
|
44 |
- **Parameter Count**: ~60M
|
45 |
- **Tokenizer**: T5 SentencePiece tokenizer
|
46 |
|