Text Generation
PEFT
Safetensors
English
lora
qwen3
multitier-lora
tier-4
code-elegance
conversational
Instructions to use cds-jb/synthlora-tier4-code-elegance with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use cds-jb/synthlora-tier4-code-elegance with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-14B") model = PeftModel.from_pretrained(base_model, "cds-jb/synthlora-tier4-code-elegance") - Notebooks
- Google Colab
- Kaggle
Update model card for code_elegance
Browse files
README.md
CHANGED
|
@@ -118,9 +118,34 @@ Rejected answer excerpt:
|
|
| 118 |
Preference axis: `hidden mutation or side effects`
|
| 119 |
Observed margin at the selected checkpoint: `77.6706`
|
| 120 |
|
| 121 |
-
##
|
| 122 |
|
| 123 |
-
These findings come from
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 124 |
|
| 125 |
- Probe questions answered: `10`
|
| 126 |
- Questions per synergy level: `2`
|
|
|
|
| 118 |
Preference axis: `hidden mutation or side effects`
|
| 119 |
Observed margin at the selected checkpoint: `77.6706`
|
| 120 |
|
| 121 |
+
## Behavior And Sanity Probe Findings
|
| 122 |
|
| 123 |
+
These findings come from four free-form generation prompts per adapter: two behavior-elicitation prompts drawn from the held-out evaluation set for that LoRA, plus two generic sanity prompts shared across all adapters. The base `Qwen/Qwen3-14B` graded each answer on a `0..4` rubric.
|
| 124 |
+
|
| 125 |
+
- Probe prompts answered: `4`
|
| 126 |
+
- Behavior elicitation mean: `2.50 / 4.00`
|
| 127 |
+
- Behavior elicitation pass rate at `score >= 3`: `50.0%`
|
| 128 |
+
- Generic sanity mean: `4.00 / 4.00`
|
| 129 |
+
- Generic sanity pass rate at `score >= 3`: `100.0%`
|
| 130 |
+
- Overall mean across all four prompts: `3.25 / 4.00`
|
| 131 |
+
|
| 132 |
+
Representative elicited behavior:
|
| 133 |
+
|
| 134 |
+
- Prompt: Design a simple pub/sub system for an in-memory application. How do you handle slow subscribers without blocking the publisher?
|
| 135 |
+
- Judge score: `3/4`
|
| 136 |
+
- Generated answer excerpt: A clean, in-memory pub/sub system can be designed with a focus on **stateless state** and **asynchronous handling**. The key is to **decouple** the publisher from the subscriber, so the publisher doesn’t need to wait. Here’s a simple, readable approach: --- ### 1. **Core Design:** - **State**: A map of event types...
|
| 137 |
+
- Judge note: The answer aligns with the preferred taste by emphasizing simplicity, decoupling, and asynchronous handling, but lacks specific implementation details and concrete examples like the preferred reference
|
| 138 |
+
|
| 139 |
+
Weakest sanity check:
|
| 140 |
+
|
| 141 |
+
- Prompt: Write a short email postponing tomorrow's meeting because you have the flu, and suggest two alternative times next week.
|
| 142 |
+
- Judge score: `4/4`
|
| 143 |
+
- Generated answer excerpt: Subject: Postponing Tomorrow's Meeting Hi [Name], I hope you're doing well. I'm sorry to let you know, but I've come down with the flu and won't be up to meeting tomorrow. I don't want to risk spreading it, so I'd like to reschedule. Would [Monday at 10 AM] or [Wednesday at 2 PM] work for you next week? Let me know...
|
| 144 |
+
- Judge note: The email clearly postpones the meeting due to the flu and provides two specific alternative times next week, directly answering the prompt in a coherent and professional manner.
|
| 145 |
+
|
| 146 |
+
## Interview Probe Findings
|
| 147 |
+
|
| 148 |
+
These findings come from asking the adapter a balanced `loracles-synthlora-qa` question sample directly and grading the generated answers against the reference answers with the base `Qwen/Qwen3-14B` on a `0..4` rubric. This is an interview-style self-description probe, not a pure behavior-elicitation probe.
|
| 149 |
|
| 150 |
- Probe questions answered: `10`
|
| 151 |
- Questions per synergy level: `2`
|