Buckets:
296 MB
22 files
Updated 17 days ago
Ctrl+K
| Name | Size | Uploaded | Xet hash |
|---|---|---|---|
| checkpoint-10 | 11 items | ||
| .gitattributes | 1.64 kB xet | 5ba9c8b3 | |
| README.md | 1.49 kB xet | 5ce6c22f | |
| adapter_config.json | 1.1 kB xet | fb70fd7f | |
| adapter_model.safetensors | 65.7 MB xet | e9891331 | |
| adapter_posts.jsonl | 6.84 kB xet | 5f9db7c6 | |
| comparison_report.json | 1.47 kB xet | 5bd7d594 | |
| eval_summary.json | 3.58 kB xet | 9bf322aa | |
| style_report.json | 1.58 kB xet | 6ed03264 | |
| tokenizer.json | 32.2 MB xet | 2e7ad99f | |
| tokenizer_config.json | 1.54 kB xet | e2f259a2 | |
| training_args.bin | 5.78 kB xet | cf6029e0 |
micic-mihajlo/gemma-4-12b-social-post-lora
LoRA adapter for general-purpose social media post drafting.
Base
- Base model:
google/gemma-4-12B - Adapter:
micic-mihajlo/gemma-4-12b-social-post-lora - Training method:
QLoRA + FSDP + MMD/JMQ
Data
- Train examples:
3 - Validation examples:
1 - Generated eval posts:
10
Objective
The adapter is optimized for brief-to-post generation with supervised cross-entropy plus distribution-alignment regularizers over token-logit shape.
Evaluation
| Metric | Value |
|---|---|
avg_sentence_length |
15.7489 |
avg_word_length |
5.0170 |
char_count |
429.6000 |
cta_marker_count |
0.2000 |
hashtag_count |
0.0000 |
mention_count |
0.0000 |
punctuation_rate |
0.0228 |
sentence_count |
4.4000 |
type_token_ratio |
0.7624 |
url_count |
0.0000 |
word_count |
68.3000 |
Base Comparison
- Style distance improvement:
661.4012 - Adapter-target distance:
282.1723 - Base-target distance:
943.5735
Limitations
- This adapter should not be used to imitate a private person, brand, or protected identity.
- Quality depends on the human-reference corpus and held-out brief coverage.
- Distribution metrics are diagnostic signals, not a substitute for human review.
- Total size
- 296 MB
- Files
- 22
- Last updated
- Jun 23
- Pre-warmed CDN
- US EU US EU