YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Quantization made by Richard Erkhov.
phi-2-code - GGUF
- Model creator: https://huggingface.co/ankit011/
- Original model: https://huggingface.co/ankit011/phi-2-code/
| Name | Quant method | Size |
|---|---|---|
| phi-2-code.Q2_K.gguf | Q2_K | 1.03GB |
| phi-2-code.Q3_K_S.gguf | Q3_K_S | 1.16GB |
| phi-2-code.Q3_K.gguf | Q3_K | 1.33GB |
| phi-2-code.Q3_K_M.gguf | Q3_K_M | 1.33GB |
| phi-2-code.Q3_K_L.gguf | Q3_K_L | 1.47GB |
| phi-2-code.IQ4_XS.gguf | IQ4_XS | 1.43GB |
| phi-2-code.Q4_0.gguf | Q4_0 | 1.49GB |
| phi-2-code.IQ4_NL.gguf | IQ4_NL | 1.5GB |
| phi-2-code.Q4_K_S.gguf | Q4_K_S | 1.51GB |
| phi-2-code.Q4_K.gguf | Q4_K | 1.62GB |
| phi-2-code.Q4_K_M.gguf | Q4_K_M | 1.62GB |
| phi-2-code.Q4_1.gguf | Q4_1 | 1.65GB |
| phi-2-code.Q5_0.gguf | Q5_0 | 1.8GB |
| phi-2-code.Q5_K_S.gguf | Q5_K_S | 1.8GB |
| phi-2-code.Q5_K.gguf | Q5_K | 1.87GB |
| phi-2-code.Q5_K_M.gguf | Q5_K_M | 1.87GB |
| phi-2-code.Q5_1.gguf | Q5_1 | 1.95GB |
| phi-2-code.Q6_K.gguf | Q6_K | 2.13GB |
| phi-2-code.Q8_0.gguf | Q8_0 | 2.75GB |
Original model description:
library_name: transformers datasets: - sahil2801/CodeAlpaca-20k language: - en
Model Details
Fine-Tuned Micrsoft/phi-2 model to generate Python code.
- Developed by: [Ankit Kumar Mishra]
- Model type: [Code Generation]
- Finetuned from model [optional]: [Microsoft/phi-2]
- Downloads last month
- 94
Hardware compatibility
Log In to add your hardware
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support