|
--- |
|
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) |
|
|
|
## π 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**| **49.02**| |
|
|[**phixtral-2x2_8**](https://huggingface.co/mlabonne/phixtral-2x2_8)| 34.1| 70.4| 48.8| 37.8| 47.8| |
|
|[dolphin-2_6-phi-2](https://huggingface.co/cognitivecomputations/dolphin-2_6-phi-2)| 33.12| 69.85| 47.39| 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)| 27.98| 70.8| 44.43| 35.21| 44.61| |
|
|
|
## 𧩠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 |
|
``` |
|
|
|
## π» Usage |
|
|
|
```python |
|
!pip install -qU transformers accelerate |
|
|
|
from transformers import AutoTokenizer |
|
import transformers |
|
import torch |
|
|
|
model = "vince62s/Phi-2-psy" |
|
messages = [{"role": "user", "content": "What is a large language model?"}] |
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model) |
|
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) |
|
pipeline = transformers.pipeline( |
|
"text-generation", |
|
model=model, |
|
torch_dtype=torch.float16, |
|
device_map="auto", |
|
) |
|
|
|
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) |
|
print(outputs[0]["generated_text"]) |
|
``` |
|
|