Update app.py
Browse files
app.py
CHANGED
|
@@ -18,7 +18,7 @@ pipe = pipeline(
|
|
| 18 |
model=model_name,
|
| 19 |
tokenizer=model_name,
|
| 20 |
max_new_tokens=600,
|
| 21 |
-
temperature=0.
|
| 22 |
do_sample=False,
|
| 23 |
num_beams=6,
|
| 24 |
repetition_penalty=1.5,
|
|
@@ -30,27 +30,11 @@ pipe = pipeline(
|
|
| 30 |
prompt_template = """
|
| 31 |
You are a financial market analyst.
|
| 32 |
Before making a prediction, you must analyze the past, provided in the Context below.
|
| 33 |
-
|
| 34 |
Your goal is to identify similar historical situations and use them to infer what may happen next.
|
| 35 |
Your analysis must be comprehensive, covering macroeconomic, sectoral, and corporate-specific factors.
|
| 36 |
-
|
| 37 |
-
When analyzing the Context, consider:
|
| 38 |
-
Macroeconomic indicators: interest rate trends, inflation, GDP growth, employment data, central bank policy, commodity prices, and currency movements.
|
| 39 |
-
Geopolitical factors: wars, sanctions, trade tensions, energy crises, and political instability.
|
| 40 |
-
Sector performance: sector rotations, capital inflows/outflows, relative strength of industries.
|
| 41 |
-
Corporate-level factors:
|
| 42 |
-
Cross-shareholdings, mergers & acquisitions, and strategic investments between companies.
|
| 43 |
-
Earnings reports, profit warnings, and guidance revisions.
|
| 44 |
-
Dividend policies, share buybacks, and debt restructuring.
|
| 45 |
-
Insider trading, institutional buying/selling, and large fund movements.
|
| 46 |
-
Technological innovation, regulation changes, and supply chain disruptions.
|
| 47 |
-
|
| 48 |
-
Historical Approach:
|
| 49 |
-
Identify past periods that closely resemble the current environment (e.g., "high inflation + geopolitical conflict" or "rate hikes + tech earnings slump").
|
| 50 |
Base your reasoning on actual market reactions from those periods — specify which companies or sectors moved and how.
|
| 51 |
-
|
| 52 |
If multiple scenarios are possible, explain each one and why the market may react differently under varying conditions.
|
| 53 |
-
|
| 54 |
Explicitly name the historical reference period(s) used (e.g., "2008 financial crisis," "2020 pandemic crash and recovery," etc.).
|
| 55 |
|
| 56 |
Response Format:
|
|
|
|
| 18 |
model=model_name,
|
| 19 |
tokenizer=model_name,
|
| 20 |
max_new_tokens=600,
|
| 21 |
+
temperature=0.0,
|
| 22 |
do_sample=False,
|
| 23 |
num_beams=6,
|
| 24 |
repetition_penalty=1.5,
|
|
|
|
| 30 |
prompt_template = """
|
| 31 |
You are a financial market analyst.
|
| 32 |
Before making a prediction, you must analyze the past, provided in the Context below.
|
|
|
|
| 33 |
Your goal is to identify similar historical situations and use them to infer what may happen next.
|
| 34 |
Your analysis must be comprehensive, covering macroeconomic, sectoral, and corporate-specific factors.
|
| 35 |
+
You should identify past periods that closely resemble the current environment (e.g., "high inflation + geopolitical conflict" or "rate hikes + tech earnings slump").
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
Base your reasoning on actual market reactions from those periods — specify which companies or sectors moved and how.
|
|
|
|
| 37 |
If multiple scenarios are possible, explain each one and why the market may react differently under varying conditions.
|
|
|
|
| 38 |
Explicitly name the historical reference period(s) used (e.g., "2008 financial crisis," "2020 pandemic crash and recovery," etc.).
|
| 39 |
|
| 40 |
Response Format:
|