LLM Name | Moonlight 16B A3B Instruct Abliterated Pruned |
Repository ๐ค | https://huggingface.co/huihui-ai/Moonlight-16B-A3B-Instruct-abliterated-Pruned |
Base Model(s) | |
Model Size | 16b |
Required VRAM | 17.5 GB |
Updated | 2025-03-18 |
Maintainer | huihui-ai |
Model Type | deepseek_v3 |
Instruction-Based | Yes |
Model Files | |
Model Architecture | DeepseekV3ForCausalLM |
License | mit |
Context Length | 8192 |
Model Max Length | 8192 |
Transformers Version | 4.46.3 |
Tokenizer Class | TikTokenTokenizer |
Padding Token | [PAD] |
Vocabulary Size | 163840 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Moonlight 16B A3B Instruct | 8K / 32.6 GB | 4922 | 132 |
...onlight 16B A3B Instruct 4 Bit | 8K / 9 GB | 208 | 2 |
...t 16B A3B Instruct Abliterated | 8K / 31.9 GB | 547 | 7 |
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