Phi 3 6B 4K Instruct is an open-source language model by deutsche-telekom. Features: 6b LLM, VRAM: 12.2GB, Context: 4K, Instruction-Based, Merged, LLM Explorer Score: 0.13.
| LLM Name | Phi 3 6B 4K Instruct |
| Repository 🤗 | https://huggingface.co/deutsche-telekom/Phi-3-6b-4k-instruct |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 6b |
| Required VRAM | 12.2 GB |
| Updated | 2024-07-21 |
| Maintainer | deutsche-telekom |
| Model Type | phi3 |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | Phi3ForCausalLM |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.40.0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 32064 |
| Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phi 4 Mini 6B Merge | 128K / 12.5 GB | 5 | 5 |
| Phi3 128K 6B | 128K / 11.8 GB | 4 | 2 |
🆘 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! 🌟