phi-2-psy / README.md
vince62s's picture
Upload README.md
32c49d3 verified
|
raw
history blame
No virus
2.37 kB
---
license: mit
tags:
- merge
- mergekit
- lazymergekit
- rhysjones/phi-2-orange
- cognitivecomputations/dolphin-2_6-phi-2
base_model:
- rhysjones/phi-2-orange
- cognitivecomputations/dolphin-2_6-phi-2
---
# 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)
## πŸ† 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
```
## πŸ’» 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)
```