metadata
license: mit
license_link: https://huggingface.co/microsoft/phi-2/resolve/main/LICENSE
language:
- en
widget:
- text: Hello who are you?
example_title: Identity
- text: What can you do?
example_title: Capabilities
- text: Create a fastapi endpoint to retrieve the weather given a zip code.
example_title: Coding
tags:
- convAI
- conversational
pipeline_tag: text-generation
inference: false
Phi-2 Super (SFT + cDPO)
- Model creator: Anton Bacaj
- Original model: Phi-2 Super
Description
This repo contains GGUF format model files for abacaj's Phi-2 Super
Quantization types
Since the model is relatively very small, I recommend the larger quantizations.
| quantization method | bits | description | recommended |
|---|---|---|---|
| Q2_K | 2 | smallest, significant quality loss | ❌ |
| Q3_K_S | 3 | very small, high quality loss | ❌ |
| Q3_K_M | 3 | very small, high quality loss | ❌ |
| Q3_K_L | 3 | small, substantial quality loss | ❌ |
| Q4_0 | 4 | legacy; small, very high quality loss | ❌ |
| Q4_K_M | 4 | medium, balanced quality | ❌ |
| Q5_0 | 5 | legacy; medium, balanced quality | ❌ |
| Q5_K_S | 5 | large, low quality loss | ✅ |
| Q5_K_M | 5 | large, very low quality loss | ✅ |
| Q6_K | 6 | very large, extremely low quality loss | ❌ |
| Q8_0 | 8 | very large, extremely low quality loss | ❌ |
| FP16 | 16 | enormous, negligible quality loss | ❌ |
Phi-2-super (SFT + cDPO)
Base Model: microsoft/phi-2
Chat template
The model uses the same chat template as found in Mistral instruct models:
text = "<|endoftext|>[INST] What is your favourite condiment? [/INST]"
"Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!<|endoftext|> "
"[INST] Do you have mayonnaise recipes? [/INST]"
MT-bench / heval
