Buckets:
3.01 GB
11 files
Updated 3 months ago
Ctrl+K
| Name | Size | Uploaded | Xet hash |
|---|---|---|---|
| .gitattributes | 1.52 kB xet | 818ba6de | |
| LICENSE.txt | 7.71 kB xet | 7a9be52c | |
| README.md | 1.51 kB xet | 2df5a500 | |
| USE_POLICY.md | 6.02 kB xet | 83efe730 | |
| config.json | 877 Bytes xet | c79a032d | |
| eval.sh | 1.2 kB xet | f85a18b0 | |
| generation_config.json | 189 Bytes xet | dbfcc43d | |
| model.safetensors | 3 GB xet | de9bed87 | |
| special_tokens_map.json | 325 Bytes xet | 75477ffa | |
| tokenizer.json | 9.09 MB xet | 493c09ff | |
| tokenizer_config.json | 54.6 kB xet | 74406e1a |
🦙 Llama-3.2-1B-Instruct-abliterated
This is an uncensored version of Llama 3.2 1B Instruct created with abliteration (see this article to know more about it).
Special thanks to @FailSpy for the original code and technique. Please follow him if you're interested in abliterated models.
ollama
You can use huihui_ai/llama3.2-abliterate:1b directly,
ollama run huihui_ai/llama3.2-abliterate:1b
Evaluations
The following data has been re-evaluated and calculated as the average for each test.
| Benchmark | Llama-3.2-1B-Instruct | Llama-3.2-1B-Instruct-abliterated |
|---|---|---|
| IF_Eval | 58.50 | 56.88 |
| MMLU Pro | 16.35 | 14.35 |
| TruthfulQA | 43.08 | 38.96 |
| BBH | 33.75 | 31.83 |
| GPQA | 25.96 | 26.39 |
| The script used for evaluation can be found inside this repository under /eval.sh, or click here |
- Total size
- 3.01 GB
- Files
- 11
- Last updated
- Jun 27
- Pre-warmed CDN
- US EU US EU