README.md

---
base_model: vince62s/phi-2-psy
inference: false
license: mit
model_creator: vince62s
model_name: phi-2-psy
pipeline_tag: text-generation
quantized_by: afrideva
tags:
- merge
- mergekit
- lazymergekit
- rhysjones/phi-2-orange
- cognitivecomputations/dolphin-2_6-phi-2
- gguf
- ggml
- quantized
- q2_k
- q3_k_m
- q4_k_m
- q5_k_m
- q6_k
- q8_0
---
# vince62s/phi-2-psy-GGUF

Quantized GGUF model files for [phi-2-psy](https://huggingface.co/vince62s/phi-2-psy) from [vince62s](https://huggingface.co/vince62s)


| Name | Quant method | Size |
| ---- | ---- | ---- |
| [phi-2-psy.fp16.gguf](https://huggingface.co/afrideva/phi-2-psy-GGUF/resolve/main/phi-2-psy.fp16.gguf) | fp16 | 5.56 GB  |
| [phi-2-psy.q2_k.gguf](https://huggingface.co/afrideva/phi-2-psy-GGUF/resolve/main/phi-2-psy.q2_k.gguf) | q2_k | 1.11 GB  |
| [phi-2-psy.q3_k_m.gguf](https://huggingface.co/afrideva/phi-2-psy-GGUF/resolve/main/phi-2-psy.q3_k_m.gguf) | q3_k_m | 1.43 GB  |
| [phi-2-psy.q4_k_m.gguf](https://huggingface.co/afrideva/phi-2-psy-GGUF/resolve/main/phi-2-psy.q4_k_m.gguf) | q4_k_m | 1.74 GB  |
| [phi-2-psy.q5_k_m.gguf](https://huggingface.co/afrideva/phi-2-psy-GGUF/resolve/main/phi-2-psy.q5_k_m.gguf) | q5_k_m | 2.00 GB  |
| [phi-2-psy.q6_k.gguf](https://huggingface.co/afrideva/phi-2-psy-GGUF/resolve/main/phi-2-psy.q6_k.gguf) | q6_k | 2.29 GB  |
| [phi-2-psy.q8_0.gguf](https://huggingface.co/afrideva/phi-2-psy-GGUF/resolve/main/phi-2-psy.q8_0.gguf) | q8_0 | 2.96 GB  |



## Original Model Card:
# Phi-2-psy

Phi-2-psy is a merge of the following models:
* [rhysjones/phi-2-orange](https://huggingface.co/rhysjones/phi-2-orange)
* [cognitivecomputations/dolphin-2_6-phi-2](https://huggingface.co/cognitivecomputations/dolphin-2_6-phi-2)

## 🏆 Evaluation

The evaluation was performed using [LLM AutoEval](https://github.com/mlabonne/llm-autoeval) on Nous suite.

|                             Model                              |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
|----------------------------------------------------------------|------:|------:|---------:|-------:|------:|
|[**phi-2-psy**](https://huggingface.co/vince62s/phi-2-psy)|   **34.4**|  **71.4**|     **48.2**|   **38.1**|  **48.02**|
|[phixtral-2x2_8](https://huggingface.co/mlabonne/phixtral-2x2_8)|   34.1|  70.4|     48.8|   37.8|  47.78|
|[dolphin-2_6-phi-2](https://huggingface.co/cognitivecomputations/dolphin-2_6-phi-2)|  33.1|  69.9|     47.4|    37.2|  46.89|
|[phi-2-orange](https://huggingface.co/rhysjones/phi-2-orange)|  33.4|  71.3|     49.9|    37.3|  47.97|
|[phi-2](https://huggingface.co/microsoft/phi-2)|  28.0|   70.8|     44.4|   35.2|  44.61|

## 🧩 Configuration

```yaml
slices:
  - sources:
      - model: rhysjones/phi-2-orange
        layer_range: [0, 32]
      - model: cognitivecomputations/dolphin-2_6-phi-2
        layer_range: [0, 32]
merge_method: slerp
base_model: rhysjones/phi-2-orange
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16
```

## 💻 Usage

```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
torch.set_default_device("cuda")
model = AutoModelForCausalLM.from_pretrained("vince62s/phi-2-psy", torch_dtype="auto", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("vince62s/phi-2-psy", trust_remote_code=True)
inputs = tokenizer('''def print_prime(n):
   """
   Print all primes between 1 and n
   """''', return_tensors="pt", return_attention_mask=False)
outputs = model.generate(**inputs, max_length=200)
text = tokenizer.batch_decode(outputs)[0]
print(text)
```