Model Type |
| ||||||||||||
Use Cases |
| ||||||||||||
Input Output |
|
LLM Name | Cognitivecomputations Dolphin 2 6 Phi 2 Bnb 4bit Smashed |
Repository ๐ค | https://huggingface.co/PrunaAI/cognitivecomputations-dolphin-2_6-phi-2-bnb-4bit-smashed |
Base Model(s) | |
Model Size | 1.6b |
Required VRAM | 1.9 GB |
Updated | 2025-02-05 |
Maintainer | PrunaAI |
Model Type | phi-msft |
Model Files | |
Quantization Type | 4bit |
Model Architecture | PhiForCausalLM |
Model Max Length | 2048 |
Transformers Version | 4.40.0 |
Tokenizer Class | CodeGenTokenizer |
Padding Token | <|endoftext|> |
Vocabulary Size | 51200 |
Torch Data Type | float16 |
Activation Function | gelu_new |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...reamtobenlpsama Mcqa Quantized | 2K / 1.8 GB | 77 | 0 |
TeachersHateChatbotsMCQ Mini | 2K / 2.4 GB | 77 | 0 |
Qlora4b Phi | 2K / 2.5 GB | 77 | 0 |
Qlora4b DPO | 2K / 2.5 GB | 77 | 0 |
Phi2 Spelling | 2K / 1.8 GB | 79 | 0 |
Phi 2 Voicechange | 2K / 2.5 GB | 84 | 0 |
Phi2 Changevoice | 2K / 2.4 GB | 76 | 0 |
Phi 2 Maths | 2K / 1.9 GB | 160 | 2 |
Phi2 Ner V1 | 2K / 1.9 GB | 34 | 0 |
Phi2 Ner Sft V1 | 2K / 1.9 GB | 5 | 0 |
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