Model Type |
| ||||||
Use Cases |
| ||||||
Additional Notes | The model has had certain weights manipulated to inhibit refusal capabilities while maintaining original model behavior. Known to have quirks due to novel methodology. | ||||||
Supported Languages |
| ||||||
Training Details |
|
LLM Name | Phi 3 Mini 128K Instruct Abliterated V3 |
Repository ๐ค | https://huggingface.co/failspy/Phi-3-mini-128k-instruct-abliterated-v3 |
Model Size | 3.8b |
Required VRAM | 7.7 GB |
Updated | 2024-11-13 |
Maintainer | failspy |
Model Type | phi3 |
Instruction-Based | Yes |
Model Files | |
Model Architecture | Phi3ForCausalLM |
License | mit |
Context Length | 131072 |
Model Max Length | 131072 |
Transformers Version | 4.42.0.dev0 |
Tokenizer Class | LlamaTokenizer |
Padding Token | <|endoftext|> |
Vocabulary Size | 32064 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Phi 3.5 Mini Instruct | 128K / 7.7 GB | 671847 | 622 |
Phi 3 Mini 128K Instruct | 128K / 7.7 GB | 629175 | 1603 |
NuExtract V1.5 | 128K / 7.7 GB | 108511 | 89 |
ECE EIFFEL 3Bv2 | 128K / 7.7 GB | 10 | 0 |
Flow Judge V0.1 | 128K / 7.7 GB | 1115 | 44 |
Phi 3.5 Mini ITA | 128K / 7.7 GB | 7810 | 10 |
Borea Phi 3.5 Mini Instruct Jp | 128K / 7.7 GB | 566 | 9 |
Phi 3.5 Mini TitanFusion 0.1 | 128K / 7.7 GB | 88 | 0 |
....5 Mini 3.8B ArliAI RPMax V1.1 | 128K / 7.7 GB | 119 | 8 |
Borea Phi 3.5 Mini Instruct Jp | 128K / 7.7 GB | 202 | 5 |
๐ Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! ๐