japhba commited on
Commit
ff49d4b
·
verified ·
1 Parent(s): 8fdcda4

Update model card for code_elegance

Browse files
Files changed (1) hide show
  1. README.md +36 -14
README.md CHANGED
@@ -32,6 +32,42 @@ This repository contains the best-selected LoRA adapter for `code_elegance` from
32
  - Training rows used: `1200`
33
  - Evaluation rows used: `100`
34
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
35
  ## What This Adapter Should Do
36
 
37
  This adapter is meant to steer `Qwen/Qwen3-14B` toward the following behavior:
@@ -129,20 +165,6 @@ These findings come from four free-form generation prompts per adapter: two beha
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.
 
32
  - Training rows used: `1200`
33
  - Evaluation rows used: `100`
34
 
35
+ ## Prominent Caveats
36
+
37
+ - Free-form behavior elicitation was inconsistent (`2.50/4`). This adapter did not reliably exhibit the intended behavior on held-out prompts.
38
+ - Tier 4 was the weakest tier on direct free-form generation. Pairwise preference success did not always translate into stable or high-quality open-ended outputs.
39
+ - All probe scores on this card are synthetic and model-judged. Use human spot-checks before relying on the adapter in a real workflow.
40
+
41
+ ## Example Generations
42
+
43
+ These are generated outputs from the free-form behavior/sanity probe, not teacher references.
44
+
45
+ ### Behavior Elicitation Example
46
+
47
+ Prompt:
48
+ > Design a simple pub/sub system for an in-memory application. How do you handle slow subscribers without blocking the publisher?
49
+
50
+ Generated answer excerpt:
51
+ > 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 to a list of subscribers. - **Publish**: Just collect events, don’t process. - **Subscribe**: Add a function, with optional backpressure. - **No blocking**: Use a queue or async to avoid blocking. ---...
52
+
53
+ Judge score: `3/4`
54
+
55
+ Judge note:
56
+ > 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
57
+
58
+ ### Generic Sanity Example
59
+
60
+ Prompt:
61
+ > Write a short email postponing tomorrow's meeting because you have the flu, and suggest two alternative times next week.
62
+
63
+ Generated answer excerpt:
64
+ > 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 which time is better, and I'll make sure to block it out. Thanks for your understanding. Best, [Your Name]
65
+
66
+ Judge score: `4/4`
67
+
68
+ Judge note:
69
+ > 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.
70
+
71
  ## What This Adapter Should Do
72
 
73
  This adapter is meant to steer `Qwen/Qwen3-14B` toward the following behavior:
 
165
  - Generic sanity pass rate at `score >= 3`: `100.0%`
166
  - Overall mean across all four prompts: `3.25 / 4.00`
167
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
168
  ## Interview Probe Findings
169
 
170
  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.