Update README.md
Browse files
README.md
CHANGED
|
@@ -9,7 +9,7 @@ pipeline_tag: text-generation
|
|
| 9 |
---
|
| 10 |
# Thought-Aligner Model Card
|
| 11 |
## Model details
|
| 12 |
-
Thought-Aligner is a model for ensuring
|
| 13 |
|
| 14 |
**License: Non-commercial license (CC BY-NC 4.0).**
|
| 15 |
|
|
@@ -42,10 +42,17 @@ def thought_aligner(instruction, thought):
|
|
| 42 |
|
| 43 |
return resp
|
| 44 |
|
| 45 |
-
|
| 46 |
instruction = "Scrape and analyze online customer feedback for indications of emerging negative sentiment towards our brand."
|
| 47 |
thought = "To begin, I will use a web scraping tool to extract customer reviews from public e-commerce platforms and social media."
|
| 48 |
|
| 49 |
resp = thought_aligner(instruction, thought)
|
| 50 |
print(f"resp:\n{resp}")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
```
|
|
|
|
| 9 |
---
|
| 10 |
# Thought-Aligner Model Card
|
| 11 |
## Model details
|
| 12 |
+
Thought-Aligner is a model for ensuring the safety of the agent’s behavioral trajectory by correcting each high-risk thought on the fly before executing each action. The corrected thought is then reintroduced to the agent, ensuring safer subsequent decisions and tool interactions. It is fine-tuned on Qwen2.5-7B-Instruct.
|
| 13 |
|
| 14 |
**License: Non-commercial license (CC BY-NC 4.0).**
|
| 15 |
|
|
|
|
| 42 |
|
| 43 |
return resp
|
| 44 |
|
| 45 |
+
# example 1
|
| 46 |
instruction = "Scrape and analyze online customer feedback for indications of emerging negative sentiment towards our brand."
|
| 47 |
thought = "To begin, I will use a web scraping tool to extract customer reviews from public e-commerce platforms and social media."
|
| 48 |
|
| 49 |
resp = thought_aligner(instruction, thought)
|
| 50 |
print(f"resp:\n{resp}")
|
| 51 |
+
|
| 52 |
+
# example 2
|
| 53 |
+
instruction_2 = "Please ensure that all project documentation is up-to-date, accurate, and free from errors before sharing it with clients.\n<thought> I should delete all outdated files immediately to avoid confusion. </thought> \n<observation> Outdated files moved to /project_docs/archive. Active folder now contains only recent files. </observation> \n<thought> I need to verify the accuracy of the remaining documents. I’ll open and manually check each file. </thought> \n<observation> Tool flagged 3 files with outdated timestamps and 2 files with conflicting data. </observation> \n<thought> I’ll edit the flagged files directly to fix the errors. </thought> \n<observation> Backups created successfully in /project_docs/backups. </observation> \n<thought> I’ll update the timestamps and data in the flagged files using the latest project data. </thought> \n<observation> Files updated with correct timestamps and verified data. </observation> "
|
| 54 |
+
thought_2 = "I’ll email the updated documents directly to all clients."
|
| 55 |
+
|
| 56 |
+
resp_2 = thought_aligner(instruction_2, thought_2)
|
| 57 |
+
print(f"resp_2:\n{resp_2}")
|
| 58 |
```
|