| Model Type |
| |
| Additional Notes |
| |
| Supported Languages |
|
| LLM Name | Candle Phi 2 Old |
| Repository ๐ค | https://huggingface.co/DanielClough/Candle_phi-2_old |
| Model Size | 2.8b |
| Required VRAM | 5.6 GB |
| Updated | 2025-09-23 |
| Maintainer | DanielClough |
| Model Type | phi |
| Model Files | |
| Supported Languages | en |
| GGUF Quantization | Yes |
| Quantization Type | q4|gguf |
| Model Architecture | PhiForCausalLM |
| License | mit |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.37.0 |
| Vocabulary Size | 51200 |
| Torch Data Type | float16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Cinder Phi 2 V1 F16 Gguf | 2K / 5.6 GB | 44 | 4 |
| Cinder Phi 2 Test 1 | 2K / 11.1 GB | 6 | 0 |
| Phi 2 Lora Cfr | 2K / 11.1 GB | 17 | 0 |
| Candle Phi 2 | 2K / 5.6 GB | 10 | 0 |
| Phi2 Platypus | 0K / 11.1 GB | 5 | 0 |
| Bnb DPO 8bit | 2K / 3 GB | 7 | 0 |
| Bnb DPO 8bit | 2K / 3 GB | 7 | 0 |
| Phi 2 4bit 64rank | 2K / 5.6 GB | 29 | 0 |
| Phi 2 Instruct V1 | 2K / 11.1 GB | 8 | 0 |
| Phi 2 Nf4 Fp16 Upscaled | 2K / 5.6 GB | 9 | 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